Intelligent management system and method for efficient utilization of straw feed resources

Abstract

The invention discloses an intelligent management system and method for efficient utilization of straw feed resources, particularly relates to the technical field of production management, and is used for solving the problem that accurate recognition and dynamic management and control of local structure abnormal phenomena are lacked in the existing straw pretreatment process. Fiber component distribution information is generated through spectral component analysis, a multiple linear regression algorithm is combined to identify a local structure easy-curing risk area, microscopic image acquisition and feature extraction are used to identify a potential curing feature area, and a pre-processing risk adjustment area is generated based on the two areas. The abnormal degree of the risk area is evaluated by analyzing the deviation amplitude of fiber direction arrangement and the asymmetric coupling strength of interface interaction, and finally whether parameter optimization processing needs to be carried out or not is judged according to the evaluation result, so that dynamic monitoring and accurate regulation and control of the straw pretreatment process are achieved, and the straw pretreatment efficiency is improved. The stability of the pretreatment process and the utilization efficiency of straw feed resources are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and more specifically, to an intelligent management system and method for efficient utilization of straw feed resources. Background Art

[0002] With the development of straw resource utilization technology, straw as a feed raw material has gradually become an important part of agriculture and animal husbandry. However, during the pretreatment and fermentation of straw, the structural characteristics of cellulose and hemicellulose in the straw may change due to the influence of high temperature and high humidity environment and complex process conditions. Pretreatment refers to a series of preliminary treatment processes for straw raw materials in order to improve the nutritional value and processing performance of straw during the process of straw feed resource utilization; in local areas, the microstructure of the fibers will show an unbalanced arrangement state. In addition, the interfacial interaction between cellulose and hemicellulose shows a nonlinear response under different process conditions, resulting in instability in the reaction performance of local areas. These phenomena will have a significant impact on the resource utilization efficiency of straw feed.

[0003] The existing technology lacks accurate assessment and control methods for local structural abnormalities during straw pretreatment, which leads to the microstructural solidification of cellulose and hemicellulose in specific areas, thereby significantly reducing the efficiency of subsequent enzymatic hydrolysis. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an intelligent management system and method for efficient utilization of straw feed resources 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: An intelligent management method for efficient utilization of straw feed resources comprises the following steps: Spectral component analysis of straw raw materials is performed to generate fiber component distribution information, and the fiber component distribution information is fitted and processed based on a multivariate linear regression algorithm to determine the local structure solidification risk area; Microscopic images of straw raw materials are collected to generate local microstructure maps, and potential solidification feature areas are marked based on feature extraction and classification identification; Generate pre-treatment risk adjustment areas based on local structural solidification risk areas and potential solidification feature areas; By analyzing the gradient change of fiber arrangement direction in the pretreatment risk adjustment area, it is evaluated whether the deviation amplitude of fiber arrangement direction is normal; by analyzing the interface interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, it is evaluated whether the asymmetric coupling strength of the interface interaction between fiber components is reasonable; Based on the evaluation results of the deviation amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs immediate parameter optimization.

[0006] In a preferred embodiment, spectral component analysis is performed on the straw raw material to generate fiber component distribution information, and the fiber component distribution information is fitted and processed based on a multivariate linear regression algorithm to determine the local structure solidification risk area, specifically including: The spectral characteristics of the straw raw material are collected by near infrared spectroscopy equipment to obtain spectral reflectance data including cellulose and hemicellulose; Extract the distribution characteristics of cellulose and hemicellulose based on the spectral reflectance data to generate fiber component distribution information; The fiber component distribution information was fitted using a multivariate linear regression algorithm. Based on the regression parameter weights obtained from the fitting, local areas where the fiber components had a risk of easy solidification were determined and marked as local structural risk areas of easy solidification.

[0007] In a preferred embodiment, microscopic images of straw raw materials are collected to generate local microstructure maps, and potential solidification feature areas are marked based on feature extraction and classification identification, specifically including: Microscopic images of straw raw materials are collected by using microscopic imaging equipment, and the microscopic images of straw raw materials are denoised and contrast enhanced by using image preprocessing methods. The edge features of fiber microstructure in the microscopic image of straw raw material are extracted by edge detection algorithm; The edge features of the fiber microstructure were classified and identified using the support vector machine classification algorithm, and the potential solidification feature areas in the microscopic images of the straw raw materials were marked according to the classification results.

[0008] In a preferred embodiment, based on the local structure easy solidification risk area and the potential solidification characteristic area, a pre-processing risk adjustment area is generated, which specifically includes: Extract the spatial location data of the local structure prone to solidification risk areas and potential solidification feature areas; The spatial location data of the local structure prone to solidification risk area and the potential solidification feature area are combined to calculate the minimum bounding box covering the two areas and generate the preprocessing risk adjustment area.

[0009] In a preferred embodiment, by analyzing the fiber arrangement direction gradient change in the pre-processing risk adjustment area, evaluating whether the deviation amplitude of the fiber direction arrangement is normal, specifically includes: Extracting fiber arrangement direction data in the pre-processing risk adjustment area, and generating a two-dimensional distribution map of the fiber arrangement direction based on the fiber arrangement direction data; Perform gradient analysis on the two-dimensional distribution map of fiber arrangement direction to calculate the gradient change of fiber arrangement direction at different spatial positions; The deviation amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is calculated based on the gradient change of the fiber arrangement direction at different spatial positions, and the deviation amplitude includes the average gradient change amplitude and the discreteness of the deviation amplitude; The deviation amplitude of the fiber direction arrangement is compared with the preset normal range of the deviation amplitude to evaluate whether the deviation amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is normal.

[0010] In a preferred embodiment, the method for obtaining the discreteness of the average gradient variation amplitude and the offset amplitude is specifically as follows: Average gradient change: ;in, is the average gradient change within the pretreatment risk-adjusted region, is the total number of grids, Represents the row number of the grid in the two-dimensional distribution map, Indicates the column number of the grid in the two-dimensional distribution map, Indicates that the Line The magnitude of the gradient change in the fiber arrangement direction within the grid of the column; Discreteness of offset amplitude: ;in, Represents the discreteness of the magnitude of the shift within the pretreatment risk-adjusted region.

[0011] In a preferred embodiment, by analyzing the interface interaction between cellulose and hemicellulose in the pretreatment risk adjustment region, evaluating whether the asymmetric coupling strength of the fiber component interface interaction is reasonable, specifically including: Extract the spectral data of cellulose and hemicellulose in the pretreatment risk adjustment area, and generate the interface characterization information of fiber components by combining molecular structure detection methods; Preprocess the interface characterization information and extract interface interaction variables by combining chemical feature analysis methods; A high-dimensional feature matrix of interface interaction variables is constructed, and the high-dimensional feature matrix is ​​decomposed by a coupling degree calculation method to obtain the coupling coefficient distribution of the interface interaction between cellulose and hemicellulose. The coupling coefficient distribution includes the correlation strength between the spatial position and the feature dimension, and the correlation strength between the feature dimension and the interface interaction variable. Based on the positive and negative differences in the coupling coefficient distribution, the asymmetric coupling strength of the fiber component interface interaction is calculated; The asymmetric coupling strength is compared with the reasonable range of coupling strength to determine whether the asymmetric coupling strength of the fiber component interface interaction in the pretreatment risk adjustment area is reasonable.

[0012] In a preferred embodiment, based on the evaluation results of the deviation amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs to be immediately optimized, specifically including: When the offset amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is normal and the asymmetric coupling strength of the fiber component interface interaction is reasonable, it is determined that the pretreatment risk adjustment area does not need to be immediately optimized; otherwise, it is determined that the pretreatment risk adjustment area needs to be immediately optimized.

[0013] On the other hand, the present invention provides an intelligent management system for efficient utilization of straw feed resources, including a spectral component analysis module, a microscopic image recognition module, an adjustment area generation module, a fiber deviation evaluation module, an interface interaction evaluation module and a parameter optimization judgment module; Spectral component analysis module: Spectral component analysis of straw raw materials is performed to generate fiber component distribution information, and the fiber component distribution information is processed based on a multivariate linear regression algorithm to determine the local structure solidification risk area; Microscopic image recognition module: collect microscopic images of straw raw materials to generate local microstructure maps, and mark potential solidification feature areas based on feature extraction and classification identification; Adjustment area generation module: Generates pre-processing risk adjustment areas based on local structure easy-to-solidify risk areas and potential solidification feature areas; Fiber deviation assessment module: By analyzing the fiber arrangement direction gradient change in the pre-treatment risk adjustment area, it is assessed whether the deviation amplitude of the fiber direction arrangement is normal; Interface interaction assessment module: By analyzing the interface interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, it is evaluated whether the asymmetric coupling strength of the fiber component interface interaction is reasonable; Parameter optimization judgment module: Based on the evaluation results of the offset amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs to be immediately optimized.

[0014] Technical effects and advantages of an intelligent management system and method for efficient utilization of straw feed resources of the present invention: 1. The distribution information of cellulose and hemicellulose is obtained through spectral component analysis, and the local structural solidification risk area is identified by combining the multivariate linear regression algorithm, which solves the problem of inaccurate identification of local structural abnormalities in the existing technology. At the same time, through microscopic image acquisition and feature extraction, the potential solidification feature area is further identified, and the two are analyzed to generate the pretreatment risk adjustment area, which provides a basis for the subsequent targeted parameter optimization.

[0015] 2. By analyzing the deviation amplitude of fiber direction arrangement in the pretreatment risk adjustment area and the asymmetric coupling strength of the interface interaction between cellulose and hemicellulose, the risk factors of microstructure solidification are comprehensively evaluated, which makes up for the lack of quantitative evaluation of abnormal microstructure state in local areas in the existing technology. Based on the evaluation results, it is judged whether parameter optimization is needed immediately, thereby realizing dynamic control of the pretreatment process, improving the pretreatment effect of cellulose and hemicellulose, reducing the probability of microstructure solidification, and ensuring the efficiency of subsequent enzymatic hydrolysis process and efficient utilization of straw feed resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an intelligent management method for efficient utilization of straw feed resources according to the present invention; Figure 2 The present invention is a structural schematic diagram of an intelligent management system for efficient utilization of straw feed resources. DETAILED DESCRIPTION

[0017] 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.

[0018] Embodiment 1: Figure 1 The present invention provides an intelligent management method for efficient utilization of straw feed resources, which comprises the following steps: Spectral component analysis of straw raw materials is performed to generate fiber component distribution information, which is then fitted based on a multivariate linear regression algorithm to determine the local structural solidification risk area.

[0019] Microscopic images of the straw raw materials are collected to generate local microstructure maps, and potential solidification feature areas are marked based on feature extraction and classification.

[0020] Based on the local structure prone to solidification risk areas and potential solidification feature areas, the pretreatment risk adjustment area is generated.

[0021] By analyzing the gradient changes in the fiber arrangement direction in the pretreatment risk adjustment area, it is evaluated whether the offset amplitude of the fiber arrangement direction is normal; by analyzing the interface interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, it is evaluated whether the asymmetric coupling strength of the interface interaction between fiber components is reasonable.

[0022] Based on the evaluation results of the deviation amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs immediate parameter optimization.

[0023] The fiber component distribution information is generated by spectral component analysis of straw raw materials. The fiber component distribution information is fitted and processed based on the multivariate linear regression algorithm to determine the local structure solidification risk area, including: The spectral characteristics of the straw raw material are collected by near-infrared spectroscopy equipment to obtain spectral reflectance data including cellulose and hemicellulose: A near-infrared spectroscopy device (such as a Fourier transform near-infrared spectrometer with a wavelength range of 800–2500 nm) is used to collect spectral characteristic data of the straw raw material. Specifically, the straw raw material is placed in the detection window of the spectral device under normal temperature and natural humidity conditions. The effective area of ​​the detection window is 5 cm² to ensure uniform coverage of the collected spectral data.

[0024] The collected straw samples were crushed and the particle size was controlled below 0.2 mm to ensure the uniformity of spectral detection; each sample was scanned 32 times and the average value was taken to reduce noise interference; the raw data output by the near-infrared spectroscopy equipment was a spectral reflectance curve (a function of reflectance changing with wavelength), which included the spectral response characteristics of cellulose and hemicellulose at different wavelengths.

[0025] The distribution characteristics of cellulose and hemicellulose are extracted based on the spectral reflectance data to generate fiber component distribution information: The spectral reflectance was normalized to between 0 and 1 to eliminate the influence of intensity differences. The Savitzky-Golay smoothing filter method was used for denoising, and the filter window was set to 11 points to retain signal details. The spectral change rate was extracted to enhance the signal characteristics of cellulose and hemicellulose and suppress background interference.

[0026] The fiber component distribution information includes the following cellulose distribution characteristics and hemicellulose distribution characteristics.

[0027] The distribution characteristics of cellulose include: characteristic bands: 1200 nm, 1450 nm (cellulose characteristic bands); characteristic variables: reflectivity peak, reflection area, peak position, etc. of cellulose in the characteristic bands; distribution law: through statistical analysis of multiple sample data, the distribution pattern of cellulose in space is formed.

[0028] The distribution characteristics of hemicellulose include: characteristic bands: 1700 nm, 1930 nm (hemicellulose characteristic bands); characteristic variables: reflectivity peak value, reflection area, etc. of hemicellulose in the characteristic bands; distribution law: the spatial distribution law of hemicellulose is also formed by reflection characteristics.

[0029] The fiber component distribution information is fitted using a multivariate linear regression algorithm. Based on the regression parameter weights obtained from the fitting, the local areas where the fiber components are prone to solidification risk are determined and marked as local structural prone to solidification risk areas: A regression model was established, with the distribution characteristics of cellulose and hemicellulose as input variables to predict their impact on solidification risk: ;in, Represents the solidification risk score of the local area, represents the cellulose characteristic variable, represents the hemicellulose characteristic variable, and is the regression coefficient, Represents random error.

[0030] The local area refers to a specific small area divided by the straw sample through spatial position calibration during the spectrum collection process, which is used to accurately represent the physical position corresponding to the spectral data; and are the regression coefficients in the multiple linear regression model, which respectively represent the relative influence of cellulose characteristic variables and hemicellulose characteristic variables on the solidification risk score, and their values ​​are determined by fitting the experimental data.

[0031] Cellulose characteristic variables are important parameters reflecting the distribution characteristics of cellulose extracted based on spectral reflectance data, including the reflectance peak value, peak area and peak position of cellulose in specific bands (such as 1200 nm and 1450 nm); hemicellulose characteristic variables are important parameters reflecting the distribution characteristics of hemicellulose extracted based on spectral reflectance data, including the reflectance peak value, peak area and peak position of hemicellulose in specific bands (such as 1700 nm and 1930 nm).

[0032] By performing regression calculations on multiple local areas, we can obtain the regression parameter weights (e.g. and values) and analyse the contribution of cellulose and hemicellulose characteristics to solidification risk.

[0033] Based on the regression model, a solidification risk score is calculated for each local area to provide a basis for subsequent regional risk judgment.

[0034] When the curing risk score of a local area is greater than the local curing risk threshold, the local area is marked as a local structural easy-to-curing risk area, indicating that the distribution characteristics of the fiber components in this area may lead to an increased microstructure curing risk. Subsequent analysis is required to confirm whether optimization treatment is needed to avoid adverse effects on the pretreatment process.

[0035] The local solidification risk threshold is a critical scoring value determined through experimental data and statistical analysis. It is used to determine whether there is a risk of solidification in a local area. It is usually set dynamically based on different straw varieties and process conditions.

[0036] Microscopic images of straw raw materials are collected to generate local microstructure maps, and potential solidification feature areas are marked based on feature extraction and classification identification, including: Microscopic images of straw raw materials were collected using microscopic imaging equipment, and the image preprocessing method was used to remove noise and enhance contrast of the microscopic images of straw raw materials: Use microscopic imaging equipment to image the cross section of the straw raw material. The specific operation is as follows: The straw raw material was cut into sample blocks of 5 mm × 5 mm in size, and representative cross sections were selected for imaging. The sample surface was treated with a metal layer (thickness of about 10 nm) to improve the imaging effect. Each sample cross section was imaged from multiple angles to ensure the integrity of the microstructure details in different directions.

[0037] The Gaussian filter algorithm was used to denoise the image. The window size of the Gaussian filter was set to 3×3 to effectively remove the imaging noise while retaining the edge details of the fiber microstructure.

[0038] The histogram equalization method is used to enhance the image contrast and make the fiber edges clearer.

[0039] Through denoising and contrast enhancement processing, clear and high-quality microscopic images are generated, which provides a basis for subsequent edge feature extraction.

[0040] The edge features of the fiber microstructure in the microscopic image of the straw raw material are extracted by edge detection algorithm: The Canny edge detection algorithm is used, which is less sensitive to noise and is suitable for processing fine structures in microscopic images.

[0041] First, Gaussian smoothing is performed on the preprocessed image, and the smoothing parameters are the same as those in the noise removal step.

[0042] Calculate the gradient magnitude of the smoothed image: ;in, and are the horizontal and vertical gradient values ​​of the pixel, is the gradient amplitude.

[0043] Calculate the gradient direction: ;in, is the gradient direction.

[0044] The non-maximum value of the gradient amplitude is suppressed, and the edge pixels with the local maximum value of the gradient are retained.

[0045] The double threshold segmentation method is used to determine edge pixels. Pixels with edge strength higher than the upper threshold are marked as edges, pixels with edge strength lower than the lower threshold are marked as non-edges, and pixels with strengths between the two are judged by adjacent edge connectivity.

[0046] The output of the Canny algorithm is a binary image, in which white pixels represent the edge positions of the fiber microstructure and black pixels represent the non-edge areas.

[0047] The support vector machine classification algorithm is used to classify and identify the edge features of the fiber microstructure, and the potential solidification feature areas in the microscopic image of the straw raw material are marked according to the classification results: The following fiber edge features are extracted from the binary edge image: Edge density: the number of edge pixels per unit area; Edge length: the cumulative length of the fiber edge; Edge directionality: distribution statistics of edge gradient directions.

[0048] The fiber edge features are combined into a multi-dimensional feature vector as the input of the classification algorithm.

[0049] The support vector machine classification algorithm is trained using the labeled data set, where the positive samples are known solidified areas and the negative samples are normal areas.

[0050] The radial basis kernel function (RBF) is used in the training process to realize nonlinear classification: the fiber edge features are mapped from low-dimensional space to high-dimensional space through this kernel function to enhance the distinction between features, thereby realizing effective classification of potential solidification feature areas. The kernel function parameters are optimized through cross-validation to ensure the accuracy and robustness of the classification model.

[0051] The fiber edge feature vector is input into the trained support vector machine classification algorithm to classify each area in the microscopic image.

[0052] The regions with positive classification results are marked as potential solidified feature regions, and a labeling map is generated.

[0053] Based on the local structure easy solidification risk area and potential solidification characteristic area, the pre-processing risk adjustment area is generated, including: Extract the spatial location data of the local structure prone to solidification risk areas and potential solidification feature areas: The data of the local structural solidification risk area comes from the analysis results of the fiber component distribution information. The result is determined by a multivariate linear regression algorithm and its spatial position data is stored.

[0054] The data of the potential solidification feature area comes from the classification and recognition results of the microscopic image, and the spatial position coordinates of each feature area are marked in the classification results.

[0055] The spatial location data of the two types of areas are stored in the form of three-dimensional coordinates, including the number, starting coordinates, and ending coordinates of each area.

[0056] The spatial location data of the two types of areas are extracted from the corresponding data storage structure respectively; the coordinate data are standardized uniformly, and all coordinate values ​​are uniformly mapped to the three-dimensional spatial layout range of the preprocessing equipment to ensure data consistency.

[0057] The spatial location data of the local structure easy solidification risk area and the potential solidification feature area are combined to determine the minimum bounding box covering the two areas and generate the preprocessing risk adjustment area: The spatial locations of the local structural solidification risk areas and potential solidification feature areas are merged to form a comprehensive area containing all high-risk locations, namely the pretreatment risk adjustment area.

[0058] The union is calculated based on the three-dimensional coordinate bounding box of the region, where each bounding box is defined by a start coordinate and an end coordinate.

[0059] By analyzing the fiber arrangement direction gradient changes in the pre-treatment risk adjustment area, it is evaluated whether the deviation amplitude of the fiber direction arrangement is normal, including: The fiber arrangement direction data in the pre-processed risk adjustment area is extracted, and a two-dimensional distribution map of the fiber arrangement direction is generated based on the fiber arrangement direction data: The fiber arrangement direction data comes from the microscopic image analysis within the pre-processed risk adjustment area. After edge detection and feature extraction, the microscopic image generates relevant data on the fiber arrangement direction and stores it in vector form. Each vector includes three items: the spatial coordinates of the data point, the fiber arrangement direction angle, and the area number.

[0060] The fiber arrangement direction data in three-dimensional space are mapped onto a two-dimensional plane. Specifically, the transverse and longitudinal spatial coordinate information is extracted from each data point, and the height coordinate is ignored and converted into a plane position.

[0061] The fiber direction angle data is directly retained to indicate the specific arrangement direction of the fibers on the plane.

[0062] On a two-dimensional coordinate plane, the plane is divided into several small areas (gridding). The fiber arrangement direction in each grid is represented by arrows. The direction of the arrow corresponds to the angle of the fiber arrangement direction. The color or thickness of the arrow represents the distribution intensity of the fiber direction data. The final generated two-dimensional distribution map presents the spatial distribution of the fiber direction in a visual way for subsequent gradient change analysis.

[0063] Perform gradient analysis on the two-dimensional distribution diagram of the fiber arrangement direction and calculate the gradient changes of the fiber arrangement direction at different spatial positions: The purpose of gradient analysis is to calculate the rate of change of the fiber arrangement direction in a two-dimensional plane to measure the consistency of the fiber direction in adjacent areas. The analysis method determines the size and direction of the direction change by comparing the difference between the fiber direction angle in each grid and the fiber direction angle in its adjacent grid. The gradient change in the horizontal direction indicates the difference in the fiber arrangement direction of adjacent grids in the horizontal direction, and the gradient change in the vertical direction indicates the difference in the fiber arrangement direction of adjacent grids in the vertical direction.

[0064] For each grid in the two-dimensional distribution map, the fiber arrangement direction difference values ​​in the horizontal and vertical directions are calculated one by one; the total gradient change of each grid can be generated by combining the horizontal and vertical differences to generate a comprehensive change value of the grid.

[0065] The gradient change results of all grids (the comprehensive change values ​​of the grids) are stored in the form of a matrix, and each matrix unit corresponds to the gradient change value of a grid; for example, each row of the matrix represents a row of grids in a two-dimensional distribution map, and each column represents the column position of the grid.

[0066] The deviation amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is calculated based on the gradient change of the fiber arrangement direction at different spatial positions: The offset amplitude is an important indicator to measure the consistency of fiber arrangement direction, which indicates the overall change trend of fiber direction in spatial position. The offset amplitude in the region is calculated by statistically analyzing the data of gradient change matrix.

[0067] Average all elements in the gradient change matrix to calculate the overall gradient change: ;in, is the average gradient change within the pretreatment risk-adjusted region, is the total number of grids, Represents the row number of the grid in the two-dimensional distribution map, Indicates the column number of the grid in the two-dimensional distribution map, Indicates that the Line The magnitude of the gradient change in the fiber arrangement direction within the grid of the column.

[0068] The magnitude of the deviation is quantified in terms of standard deviation: ;in, Represents the discreteness of the magnitude of the shift within the pretreatment risk-adjusted region.

[0069] The offset amplitude includes the average gradient change amplitude and the discreteness of the offset amplitude.

[0070] Compare the deviation amplitude of the fiber direction arrangement with the preset normal deviation amplitude range to assess whether the deviation amplitude of the fiber direction arrangement in the pre-treatment risk adjustment area is normal: The average gradient change amplitude within the pre-processing risk adjustment region is compared with its corresponding preset normal range of the offset amplitude; the discreteness of the offset amplitude within the pre-processing risk adjustment region is compared with its corresponding preset normal range of the offset amplitude.

[0071] When the average gradient change amplitude and the discreteness of the offset amplitude in the pretreatment risk adjustment area are both within the corresponding preset offset amplitude normal range, the offset amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is judged to be normal; otherwise, the offset amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is judged to be abnormal.

[0072] Among them, the preset normal range of offset amplitude corresponding to the average gradient change amplitude is a numerical interval set through experiments and statistical analysis, which is used to determine whether the overall change level of fiber direction arrangement is within the process standard; the preset normal range of offset amplitude corresponding to the discreteness of the offset amplitude is a standard for measuring the uniformity of the distribution of fiber direction arrangement changes, and is a stability indicator used to determine whether the local gradient fluctuation meets the process requirements.

[0073] By analyzing the interfacial interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, the asymmetric coupling strength of the interfacial interaction between fiber components is evaluated to see whether it is reasonable, including: Extract the spectral data of cellulose and hemicellulose in the pretreatment risk adjustment area, and combine the molecular structure detection method to generate the interface characterization information of the fiber components: High-resolution near-infrared spectroscopy equipment was used to collect spectra of fiber components (cellulose and hemicellulose) within the pretreatment risk adjustment area. The spectral data included reflection intensities in different wavelength ranges, which corresponded to the characteristic absorption peaks of cellulose and hemicellulose.

[0074] The molecular vibration frequency analysis method was used to deduce the molecular interaction characteristics of cellulose and hemicellulose at the interface through spectral data. The interface characteristic parameters obtained by analysis included hydrogen bond strength, intermolecular force change value and chemical shift.

[0075] The spectral data are converted into interface characterization information through molecular structure detection. The interface characterization information includes the interaction force between molecules, adsorption energy distribution and chemical environment change parameters.

[0076] Preprocess the interface characterization information and extract interface interaction variables by combining chemical feature analysis methods: The interface characterization information is normalized to convert the values ​​from different sources into the same dimensional range.

[0077] From the normalized interface representation information, the following interface interaction variables are extracted: Intermolecular interaction strength variable: measures the interaction strength between cellulose and hemicellulose at the interface; Chemical shift variables: reflect the changes in the chemical environment between molecules at the interface; Molecular adsorption variable: represents the adsorption capacity of interface molecules.

[0078] A high-dimensional characteristic matrix of interface interaction variables was constructed, and the coupling degree calculation method was used to decompose the high-dimensional characteristic matrix to obtain the coupling coefficient distribution of the interface interaction between cellulose and hemicellulose: Construct a high-dimensional feature matrix: organize the interface interaction variables into a matrix structure, where the rows of the matrix represent different spatial positions and the columns represent different variable types.

[0079] The elements of the high-dimensional feature matrix are defined as: ;in, Represents the high-dimensional feature matrix Line The elements of the column, Indicates The spatial position corresponding to The value of an interface interaction variable.

[0080] The sparse regularized decomposition method is used to decompose the high-dimensional feature matrix and extract the coupling coefficient distribution of the interface interaction between cellulose and hemicellulose. The decomposed high-dimensional feature matrix is ​​expressed as: ;in, Indicates The spatial position and The correlation strength of the feature dimension (used to reflect the contribution of the interface interaction variable at that position on a specific dimension), Indicates The feature dimension and The correlation strength of the interface interaction variables (used to reflect the influence weight of the feature dimension between different interaction variables).

[0081] The coupling coefficient distribution is the result obtained after decomposing the high-dimensional feature matrix, which specifically includes the correlation strength between the spatial position and the feature dimension and the correlation strength between the feature dimension and the interface interaction variable.

[0082] Based on the positive and negative differences in the coupling coefficient distribution, the asymmetric coupling strength of the fiber component interface interaction is calculated: The difference value of the forward and reverse interaction strength is extracted from the coupling coefficient distribution, and the forward and reverse difference is defined as: ;in, represents the difference value of the strength of positive and negative interactions, Indicates the pre-treatment risk adjustment region The spatial position is The strength of association on the positive interaction dimension, Indicates the pre-treatment risk adjustment region The spatial position is The strength of the association on the reverse interaction dimension, represents the total number of spatial positions, The number of the positive interaction dimension. A number representing the reverse interaction dimension.

[0083] The asymmetric coupling strength represents the overall difference in forward and reverse interactions in the entire region, that is, the asymmetric coupling strength is the ratio of the sum of the difference values ​​of the forward and reverse interaction strengths of all interface interaction variables to the number of interface interaction variables.

[0084] Compare the asymmetric coupling strength with the reasonable range of coupling strength to determine whether the asymmetric coupling strength of the fiber component interface interaction in the pretreatment risk adjustment area is reasonable: A reasonable range of coupling strength is set. The reasonable range of coupling strength is a numerical interval determined by experimental data statistics and process analysis. It is used to determine the balance and stability of the interface interaction of fiber components. The upper and lower limits of the reasonable range correspond to the minimum stable value and the maximum allowable deviation of the interface interaction, respectively, to ensure that the interface function meets the requirements of the pretreatment process.

[0085] Determine whether the asymmetric coupling strength is within a reasonable range of coupling strength: When the asymmetric coupling strength is not within the reasonable range of coupling strength, it is determined that the asymmetric coupling strength of the fiber component interface interaction in the pretreatment risk adjustment area is unreasonable; this indicates that there are significant positive and negative differences in the interface interaction between cellulose and hemicellulose, which may lead to functional imbalance of the interface interaction or reduced reaction efficiency.

[0086] When the asymmetric coupling strength is within a reasonable range of coupling strength, it is determined that the asymmetric coupling strength of the fiber component interface interaction in the pretreatment risk adjustment region is reasonable; this indicates that the interface interaction is stable and meets the process requirements of the pretreatment risk adjustment region.

[0087] Based on the evaluation results of the deviation amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs to be immediately optimized, including: Abnormal deviation amplitude indicates abnormal distribution of fiber direction in local area, which may lead to fiber stress concentration or loose structure in the treatment area, thus inducing curing effect or affecting the efficiency and uniformity of subsequent treatment (such as enzymatic hydrolysis); unreasonable asymmetric coupling strength of interface interaction means that there is functional imbalance in the interaction between cellulose and hemicellulose at the local interface, which may lead to uneven response of fiber components to chemical reagents or thermal and humid environment during pretreatment, further aggravating the risk of local structural curing.

[0088] When the offset amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is normal and the asymmetric coupling strength of the fiber component interface interaction is reasonable, it is determined that the pretreatment risk adjustment area does not need immediate parameter optimization treatment, indicating that the arrangement stability and interface interaction performance of cellulose and hemicellulose in the local structure meet the pretreatment process requirements, and no immediate parameter optimization treatment is required under the current process conditions.

[0089] When the offset amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is abnormal, or the asymmetric coupling strength of the fiber component interface interaction is unreasonable, it is determined that the pretreatment risk adjustment area needs to be immediately optimized. This indicates that the fiber microstructure in this area has abnormal arrangement, or the interface interaction performance between cellulose and hemicellulose has not reached the expected equilibrium state, which may lead to local curing or decreased pretreatment effect. Therefore, it is determined that this area needs to be immediately optimized.

[0090] Parameter optimization is aimed at the abnormal fiber direction arrangement or unreasonable fiber component interface interaction in the pretreatment risk adjustment area. By adjusting the process parameters, the treatment effect of the local area is restored to ensure the stability and efficiency of the overall pretreatment process. Parameter optimization includes: Adjust humidity parameters: increase or decrease the humidity level in the pretreatment risk adjustment area to make the structural softening degree of cellulose and hemicellulose uniform; deploy precision humidification devices in areas with abnormal humidity, and perform local spray humidification in areas with insufficient humidity; for areas with excessively high humidity, increase the wind speed of ventilation equipment to reduce local humidity.

[0091] Adjust temperature parameters: By adjusting the temperature distribution in the pretreatment risk adjustment area, the uniformity of the interface reaction of cellulose and hemicellulose can be promoted and the solidification risk of the local structure can be reduced; in areas with insufficient temperature, local heating equipment such as steam injection or heating rods can be used to increase the regional temperature; in areas with excessively high temperatures, the heat source output can be reduced or the wind speed of the cooling fan can be increased to balance the regional temperature.

[0092] Adjust the concentration of chemical reagents: optimize the local concentration distribution of chemical reagents in the pretreatment risk adjustment area to ensure stable reaction conditions for the interface interaction between cellulose and hemicellulose; in areas with insufficient reagent concentration, increase the local injection amount of chemical reagents and adjust the injection angle to cover the target area; in areas with excessively high reagent concentration, dilute the chemical reagents or reduce the injection time to improve local uniformity.

[0093] Optimize reaction time: By extending or shortening the pretreatment time, the stability of the fiber direction arrangement can be improved and the reasonable state of interface interaction can be restored; for areas where the reaction time needs to be extended, the equipment residence time or the number of cycles can be increased; for areas where the reaction time needs to be shortened, the equipment operating speed can be reduced or the material processing time can be shortened to avoid fiber damage caused by over-treatment.

[0094] Optimize mechanical pressure: adjust the mechanical pressure distribution, improve the uniformity of fiber direction arrangement, and prevent local abnormalities caused by excessive or insufficient pressure; in areas with insufficient pressure, increase the local pressure of the compression equipment; in areas with excessive pressure, reduce the compression strength or adjust the material distribution to ensure uniform mechanical action.

[0095] Example 2: The difference between Example 2 of the present invention and Example 1 is that this example introduces an intelligent management system for efficient utilization of straw feed resources.

[0096] Figure 2 A structural schematic diagram of an intelligent management system for efficient utilization of straw feed resources of the present invention is given, an intelligent management system for efficient utilization of straw feed resources, including a spectral component analysis module, a microscopic image recognition module, an adjustment area generation module, a fiber deviation evaluation module, an interface interaction evaluation module and a parameter optimization judgment module.

[0097] Spectral component analysis module: Spectral component analysis of straw raw materials is performed to generate fiber component distribution information, and the fiber component distribution information is fitted based on a multivariate linear regression algorithm to determine the local structure solidification risk area.

[0098] Microscopic image recognition module: Microscopic images of straw raw materials are collected to generate local microstructure maps, and potential solidification feature areas are marked based on feature extraction and classification.

[0099] Adjustment area generation module: Generates pre-processing risk adjustment areas based on local structure easy-to-solidify risk areas and potential solidification feature areas.

[0100] Fiber deviation assessment module: By analyzing the fiber arrangement direction gradient changes in the pre-treatment risk adjustment area, it is assessed whether the deviation amplitude of the fiber direction arrangement is normal.

[0101] Interface interaction assessment module: By analyzing the interface interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, it is evaluated whether the asymmetric coupling strength of the interface interaction between fiber components is reasonable.

[0102] Parameter optimization judgment module: Based on the evaluation results of the offset amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs to be immediately optimized.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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. An intelligent management method for efficient utilization of straw feed resources, characterized in that: The steps include: Spectral component analysis of straw raw materials is performed to generate fiber component distribution information, and the fiber component distribution information is fitted and processed based on a multivariate linear regression algorithm to determine the local structure solidification risk area; Microscopic images of straw raw materials are collected to generate local microstructure maps, and potential solidification feature areas are marked based on feature extraction and classification identification; Generate pre-treatment risk adjustment areas based on local structural solidification risk areas and potential solidification feature areas; By analyzing the fiber alignment gradient changes in the pre-treatment risk adjustment area, it is assessed whether the deviation amplitude of the fiber alignment is normal; By analyzing the interface interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, the asymmetric coupling strength of the interface interaction between fiber components is evaluated to see whether it is reasonable. Based on the evaluation results of the deviation amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs immediate parameter optimization.

2. The intelligent management method for efficient utilization of straw feed resources according to claim 1, characterized in that: The fiber component distribution information is generated by spectral component analysis of straw raw materials. The fiber component distribution information is fitted and processed based on the multivariate linear regression algorithm to determine the local structure solidification risk area, including: The spectral characteristics of the straw raw material are collected by near infrared spectroscopy equipment to obtain spectral reflectance data including cellulose and hemicellulose; Extract the distribution characteristics of cellulose and hemicellulose based on the spectral reflectance data to generate fiber component distribution information; The fiber component distribution information was fitted using a multivariate linear regression algorithm. Based on the regression parameter weights obtained from the fitting, local areas where the fiber components had a risk of easy solidification were determined and marked as local structural risk areas of easy solidification.

3. The intelligent management method for efficient utilization of straw feed resources according to claim 2, characterized in that: Microscopic images of straw raw materials are collected to generate local microstructure maps, and potential solidification feature areas are marked based on feature extraction and classification identification, including: Microscopic images of straw raw materials are collected by using microscopic imaging equipment, and the microscopic images of straw raw materials are denoised and contrast enhanced by using image preprocessing methods. The edge features of fiber microstructure in the microscopic image of straw raw material are extracted by edge detection algorithm; The edge features of the fiber microstructure were classified and identified using the support vector machine classification algorithm, and the potential solidification feature areas in the microscopic images of the straw raw materials were marked according to the classification results.

4. The intelligent management method for efficient utilization of straw feed resources according to claim 3, characterized in that: Based on the local structure easy solidification risk area and potential solidification characteristic area, the pre-processing risk adjustment area is generated, including: Extract the spatial location data of the local structure prone to solidification risk areas and potential solidification feature areas; The spatial location data of the local structure prone to solidification risk area and the potential solidification feature area are combined to calculate the minimum bounding box covering the two areas and generate the preprocessing risk adjustment area.

5. The intelligent management method for efficient utilization of straw feed resources according to claim 4, characterized in that: By analyzing the fiber arrangement direction gradient changes in the pre-treatment risk adjustment area, it is evaluated whether the deviation amplitude of the fiber direction arrangement is normal, including: Extracting fiber arrangement direction data in the pre-processing risk adjustment area, and generating a two-dimensional distribution map of the fiber arrangement direction based on the fiber arrangement direction data; Perform gradient analysis on the two-dimensional distribution map of fiber arrangement direction to calculate the gradient change of fiber arrangement direction at different spatial positions; The deviation amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is calculated based on the gradient change of the fiber arrangement direction at different spatial positions, and the deviation amplitude includes the average gradient change amplitude and the discreteness of the deviation amplitude; The deviation amplitude of the fiber direction arrangement is compared with the preset normal range of the deviation amplitude to evaluate whether the deviation amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is normal.

6. The intelligent management method for efficient utilization of straw feed resources according to claim 5, characterized in that: The method for obtaining the discreteness of the average gradient change amplitude and the offset amplitude is specifically as follows: Average gradient change: ;in, is the average gradient change within the pretreatment risk-adjusted region, is the total number of grids, Represents the row number of the grid in the two-dimensional distribution map, Indicates the column number of the grid in the two-dimensional distribution map, Indicates that the Line The magnitude of the gradient change in the fiber arrangement direction within the grid of the column; Discreteness of offset amplitude: ;in, Represents the discreteness of the magnitude of the shift within the pretreatment risk-adjusted region.

7. The intelligent management method for efficient utilization of straw feed resources according to claim 6, characterized in that: By analyzing the interfacial interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, the asymmetric coupling strength of the interfacial interaction between fiber components is evaluated to see whether it is reasonable, including: Extract the spectral data of cellulose and hemicellulose in the pretreatment risk adjustment area, and generate the interface characterization information of fiber components by combining molecular structure detection methods; Preprocess the interface characterization information and extract interface interaction variables by combining chemical feature analysis methods; A high-dimensional feature matrix of interface interaction variables is constructed, and the high-dimensional feature matrix is ​​decomposed by a coupling degree calculation method to obtain the coupling coefficient distribution of the interface interaction between cellulose and hemicellulose. The coupling coefficient distribution includes the correlation strength between the spatial position and the feature dimension, and the correlation strength between the feature dimension and the interface interaction variable. Based on the positive and negative differences in the coupling coefficient distribution, the asymmetric coupling strength of the fiber component interface interaction is calculated; The asymmetric coupling strength is compared with the reasonable range of coupling strength to determine whether the asymmetric coupling strength of the fiber component interface interaction in the pretreatment risk adjustment area is reasonable.

8. The intelligent management method for efficient utilization of straw feed resources according to claim 7, characterized in that: Based on the evaluation results of the deviation amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs to be immediately optimized, including: When the offset amplitude of the fiber direction arrangement in the pretreatment risk adjustment area is normal and the asymmetric coupling strength of the fiber component interface interaction is reasonable, it is determined that the pretreatment risk adjustment area does not need to be immediately optimized; otherwise, it is determined that the pretreatment risk adjustment area needs to be immediately optimized.

9. An intelligent management system for efficient utilization of straw feed resources, used to implement the intelligent management method for efficient utilization of straw feed resources according to any one of claims 1 to 8, characterized in that: It includes a spectral component analysis module, a microscopic image recognition module, an adjustment area generation module, a fiber offset evaluation module, an interface interaction evaluation module, and a parameter optimization judgment module; Spectral component analysis module: Spectral component analysis of straw raw materials is performed to generate fiber component distribution information, and the fiber component distribution information is processed based on a multivariate linear regression algorithm to determine the local structure solidification risk area; Microscopic image recognition module: collect microscopic images of straw raw materials to generate local microstructure maps, and mark potential solidification feature areas based on feature extraction and classification identification; Adjustment area generation module: Generates pre-processing risk adjustment areas based on local structure easy-to-solidify risk areas and potential solidification feature areas; Fiber deviation assessment module: By analyzing the fiber arrangement direction gradient change in the pre-treatment risk adjustment area, it is assessed whether the deviation amplitude of the fiber direction arrangement is normal; Interface interaction assessment module: By analyzing the interface interaction between cellulose and hemicellulose in the pretreatment risk adjustment area, it is evaluated whether the asymmetric coupling strength of the fiber component interface interaction is reasonable; Parameter optimization judgment module: Based on the evaluation results of the offset amplitude of the fiber direction arrangement and the asymmetric coupling strength of the fiber component interface interaction, it is judged whether the pretreatment risk adjustment area needs to be immediately optimized.

Images