Wood industry data analysis management method and system based on machine learning

Abstract

The invention discloses a wood industry data analysis and management method and system based on machine learning, and relates to the field of wood industry data management. When the to-be-managed log is sawn, the coefficient of the plane equation of the sections located on the two sides of the defect and the parameter data during sawing are adjusted, so that the difference value between the strength of the sawn log section and the strength of the log section before sawing is smaller than a preset threshold value; therefore, great influence on the quality of the log in the sawing process is avoided, and the wood processing quality is further guaranteed; according to the method, parameter data of a plurality of use scenes of the wood are clustered, so that a judgment basis is provided for subsequently judging whether the use scene of the defect part of the to-be-managed log is reasonable or not, the defect part of the to-be-managed log is ensured to be applied to the most suitable use scene, and potential safety hazards in the use process are avoided.

Description

Technical Field

[0001] The present invention belongs to the field of wood industry data management, and in particular, relates to a wood industry data analysis management method and system based on machine learning. Background Art

[0002] In the wood industry, sawing of wood is an essential operation; however, some wood has defects, such as knot defects, decay defects, crack defects, etc.; if the sawing position of the defective part or the sawing parameters, such as the cutting speed, are unreasonable during sawing of the wood, it may affect the structural integrity and strength of the wood, and then cause safety hazards in the use of the wood, such as cracks, warping or decay, etc., posing a threat to the life safety of users. Summary of the invention

[0003] In view of the problems in the related technology, the present invention proposes a wood industry data analysis management method and system based on machine learning to overcome the above-mentioned technical problems existing in the existing related technology.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is a wood industry data analysis and management method based on machine learning, comprising the following steps:

[0006] S1. Collect X-ray scanning images at multiple angles at multiple image collection areas on the surface of the log to be managed to obtain a data matrix of the original scanning image to be managed;

[0007] S2, preprocessing the original scanned image data matrix to be managed to obtain a final scanned image data matrix to be managed;

[0008] S3, comparing the final scanned image data matrix to be managed with the standard defect image data to obtain the final scanned image defect type data matrix to be managed; collecting parameter data of several usage scenarios corresponding to each defect type and calculating the corresponding cluster center data to obtain the historical defect scene feature parameter center data matrix;

[0009] S4, collecting plane equation coefficient data of the section when sawing a plurality of test logs to be sawed with single defects, defect edge coordinate data, sawing parameter data and corresponding average strength difference data of the normal parts before and after sawing, and constructing a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model;

[0010] S5. Mapping the initial coefficient data of the plane equations of the two sections when the logs to be managed are sawed, the initial parameter data of sawing, and the defect edge coordinate data according to the knot defect strength difference mapping model, the decay defect strength difference mapping model, and the crack defect strength difference mapping model to obtain the initial strength difference data to be managed;

[0011] S6. Adjust the initial coefficient data of the plane equations of the two sections when sawing the logs to be managed and the initial sawing parameter data according to the initial strength difference data to be managed, and obtain the final section equation coefficient data set and the final sawing parameter data set to be managed; then adjust and replace the usage scenario of the defective part of the logs to be managed.

[0012] Preferably, the S1 comprises the following steps:

[0013] S11, setting a log to be managed and setting the log to be managed to have only a single defect; dividing a plurality of image acquisition areas on the surface of the log to be managed to obtain a current image acquisition area set;

[0014] S12. In conjunction with the current image acquisition area set, an X-ray scanning image acquisition system is used to acquire X-ray scanning images of multiple angles at each image acquisition area on the log to be managed, to obtain a data matrix of the original scanning image to be managed.

[0015] Preferably, S2 comprises the following steps:

[0016] S21, performing grayscale conversion on each original scanned image data in the original scanned image data matrix to be managed, to obtain a scanned image data matrix to be managed after grayscale conversion;

[0017] S22, respectively using a median filter and a Gaussian filter to perform frequency domain filtering operations and space domain filtering operations on each scanned image data in the scanned image data matrix to be managed after grayscale conversion, to obtain a scanned image data matrix to be managed after filtering;

[0018] S23, performing mathematical morphology processing on the filtered scanned image data matrix to be managed to obtain a final scanned image data matrix to be managed.

[0019] Preferably, S3 comprises the following steps:

[0020] S31, setting a number of wood defect types and a number of corresponding wood standard defect images, obtaining a wood defect type set and a wood defect image data matrix; comparing the final scanned image data matrix to be managed with a plurality of wood defect image data corresponding to each wood defect type in the wood defect image data matrix, respectively, and obtaining the corresponding defect type, to obtain a final scanned image defect type data matrix to be managed;

[0021] S32, setting several types of wood usage scenario characteristic parameter types to obtain a wood usage scenario characteristic parameter type set; collecting characteristic parameter data of each wood defect type corresponding to multiple wood usage scenarios in a historical wood defect type set according to the wood usage scenario characteristic parameter type set to obtain a historical defect scene characteristic parameter data matrix set;

[0022] S33, calculating the cluster center data of each historical defect scene characteristic parameter data matrix in the historical defect scene characteristic parameter data matrix set to obtain the historical defect scene characteristic parameter center data matrix.

[0023] Preferably, the S33 comprises the following steps:

[0024] S331, constructing a scene defect feature parameter clustering salp population; setting the maximum number of iterations of the scene defect feature parameter clustering salp population to c~ 1 And the current number of iterations is c~ 2 , respectively recorded as the maximum number of iterations of parameter clustering and the current number of iterations of parameter clustering;

[0025] S332, randomly selecting a row of data from each historical defect scene feature parameter data matrix in the historical defect scene feature parameter data matrix set as the initial position of each salp in the scene defect feature parameter clustering salp population, to obtain a first initial position matrix set;

[0026] S333, calculating the Euclidean distance between each row of data of each historical defect scene feature parameter data matrix in the historical defect scene feature parameter data matrix set and the corresponding row in the initial position matrix of the kth salp in the scene defect feature parameter clustering salp population, to obtain a Euclidean distance data matrix;

[0027] Constructing a fitness function of the kth salp in the scene defect feature parameter clustering salp population according to the Euclidean distance data matrix;

[0028] S334, start iteration, and set the current iteration number of the parameter clustering to 1 before iteration; in the first round of iteration, use the fitness function of the kth salp in the scene defect feature parameter clustering salp population to calculate the fitness value of the initial position matrix of each salp in the first initial position matrix set to obtain a first fitness value set; use the maximum fitness value in the first fitness value set and the corresponding initial position matrix of the salp as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each salp in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the parameter clustering and enter the next round of iteration;

[0029] In each other round of iteration, the fitness function of the kth salp in the scene defect feature parameter clustering salp population is used to calculate the fitness value of the position matrix of each salp in the scene defect feature parameter clustering salp population updated in the previous round of iteration to obtain a second fitness value set; the maximum fitness value in the second fitness value set and the corresponding salp position matrix are respectively used as the second global optimal fitness and the second global optimal position; the position matrix of each salp in the scene defect feature parameter clustering salp population updated in the previous round of iteration is updated according to the second global optimal fitness and the second global optimal position; after the update is completed, the current iteration number of the parameter clustering is increased by 1 and the next round of iteration is entered;

[0030] S335, when When , stop the iteration and get the first final global optimal position; otherwise, continue to iterate until So far; taking the first final global optimal position as the central data matrix of the historical defect scene characteristic parameters;

[0031] The salp optimization algorithm searches for the optimal solution by simulating the reproduction, filter feeding and group migration behaviors of salps. It can maintain good performance in complex and changing environments and show excellent robustness. Based on the above advantages, this scheme uses the salp optimization algorithm to iteratively adjust the clustering center of each historical defect scenario feature parameter data matrix in the historical defect scenario feature parameter data matrix set for multiple times, and uses the overall discrete degree of the historical defect scenario feature parameter data matrix set as the fitness function. As the iteration proceeds, the overall discrete degree of the historical defect scenario feature parameter data matrix set becomes smaller and smaller.

[0032] Preferably, S4 includes the following guarantees:

[0033] S41, according to the wood defect type set, a plurality of test logs to be sawn having a single corresponding defect are respectively set, and a plurality of image acquisition areas are divided on the surface of the test logs to be sawn, and then the X-ray scanning image acquisition system in S12 is used to respectively collect corresponding scanning image data at each image acquisition area on each test log to be sawn, and each scanned image data collected is processed in the manner of S21, S22 and S23 to obtain a scanned image data set matrix of the test logs to be sawn;

[0034] S42, when sawing each test log to be sawed, construct a three-dimensional coordinate system for each test log to be sawed, and obtain a test three-dimensional coordinate system matrix; in conjunction with the test three-dimensional coordinate system matrix and according to the test log scan image data set matrix, set a number of coordinate collection points at the defect edge of each test log to be sawed and collect corresponding coordinate data to obtain a test defect edge coordinate data set matrix; and then collect the plane equation coefficients corresponding to the two sections when sawing in conjunction with the test three-dimensional coordinate system matrix to obtain a test section equation coefficient data matrix;

[0035] S43, setting a number of sawing parameter types to obtain a sawing parameter type set; the sawing parameter type set includes a cutter rotation speed and a cutter displacement speed, etc.; collecting parameter data when sawing each test log to be sawed according to the sawing parameter type set to obtain a test sawing parameter data set matrix;

[0036] Then, the average strength difference data of the normal part of each test log to be sawed before and after sawing is collected to obtain the test strength difference average data matrix;

[0037] S44. Construct a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model according to the test defect edge coordinate data set matrix, the test section equation coefficient data matrix, the test sawing parameter data set matrix and the test strength difference average data matrix.

[0038] Preferably, the S44 comprises the following steps:

[0039] S441, constructing a first initial SVM model, a second initial SVM model and a third initial SVM model and setting a first training data ratio, a second training data ratio and a third training data ratio; dividing the data corresponding to the node defect type, the decay defect type and the crack defect type in the test defect edge coordinate data set matrix, the test section equation coefficient data matrix, the test sawing parameter data set matrix and the test strength difference average data matrix according to the first training data ratio, the second training data ratio and the third training data ratio, respectively, to obtain the test defect edge coordinate training data set matrix, the test section equation coefficient training data matrix, the test sawing parameter training data set matrix, the test strength difference average training data matrix, the test defect edge coordinate test data set matrix, the test section equation coefficient test data matrix, the test sawing parameter test data set matrix and the test strength difference average test data matrix;

[0040] S442. Use the data corresponding to the knot defect type, decay defect type, and crack defect type in the test defect edge coordinate training data set matrix, the test section equation coefficient training data matrix, the test sawing parameter training data set matrix, and the test strength difference average training data matrix to train and test the first initial SVM model, the second initial SVM model, and the third initial SVM model respectively; after the training and testing are completed, a knot defect strength difference mapping model, a decay defect strength difference mapping model, and a crack defect strength difference mapping model are obtained.

[0041] Preferably, S5 comprises the following steps:

[0042] S51, constructing a three-dimensional coordinate system of the log to be managed when sawing the log to be managed, and obtaining the three-dimensional coordinate system to be managed; setting a number of coordinate points at the edge of the defect in the log to be managed according to the final defect type data matrix of the scanned image to be managed, and obtaining a defect edge coordinate data set to be managed; randomly setting the initial coefficient data of the plane equations of the two sections when sawing the log to be managed and the initial sawing parameter data set in accordance with the sawing parameter type set, and obtaining the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed;

[0043] S52, determining the defect type of the log to be managed according to the final defect type data matrix of the scanned image to be managed, the first defect type of the log to be managed;

[0044] When the first log defect type to be managed is a knot defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed are input into the knot defect strength difference mapping model for mapping; when the first log defect type to be managed is a decay defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed are input into the decay defect strength difference mapping model for mapping; when the first log defect type to be managed is a crack defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed are input into the crack defect strength difference mapping model for mapping; after the mapping is completed, the initial strength difference data to be managed is obtained.

[0045] Preferably, the S6 comprises the following steps:

[0046] S61, setting a first intensity difference threshold, a second intensity difference threshold, and a third intensity difference threshold;

[0047] S62, when the first log defect type to be managed is a knot defect type and the initial strength difference data to be managed is greater than or equal to the first strength difference threshold, or when the first log defect type to be managed is a decay defect type and the initial strength difference data to be managed is greater than or equal to the second strength difference threshold, or when the first log defect type to be managed is a crack defect type and the initial strength difference data to be managed is greater than or equal to the third strength difference threshold, adjust the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed until the first log defect type to be managed is greater than or equal to the first strength difference threshold. When the defect type is a knot defect type and the initial strength difference data to be managed is less than the first strength difference threshold, or when the first log defect type to be managed is a decay defect type and the initial strength difference data to be managed is less than the second strength difference threshold, or when the first log defect type to be managed is a crack defect type and the initial strength difference data to be managed is less than the third strength difference threshold, the final section equation coefficient data set to be managed and the final sawing parameter data set to be managed are obtained; otherwise, there is no need to adjust the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed;

[0048] S63, after the adjustment of the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed is completed, sawing operation is performed on the managed logs in coordination with the final section equation coefficient data set to be managed and the final sawing parameter data set to be managed;

[0049] Using the wood usage scenario characteristic parameter type set and collecting usage scenario characteristic parameter data of defective parts of the logs to be managed after processing, to obtain a usage scenario characteristic parameter data set to be managed;

[0050] S64, calculating the Euclidean distance between the usage scenario characteristic parameter data set to be managed and each row of data in the central data matrix of the historical defect scenario characteristic parameter to obtain a first Euclidean distance data set; taking the defect type corresponding to the smallest Euclidean distance data in the first Euclidean distance data set as the second log defect type to be managed;

[0051] When the defect type of the second log to be managed is inconsistent with the defect type of the first log to be managed, the usage scenario of the defective part after the processing of the log to be managed is changed; otherwise, there is no need to change the usage scenario of the defective part after the processing of the log to be managed.

[0052] A wood industry data analysis and management system based on machine learning includes a log scanning image data acquisition module, an image preprocessing module, a log defect type data acquisition module, a scene parameter type setting module, a historical scene parameter acquisition module, a cluster center calculation module, a sawing test data acquisition module, a mapping model construction module, a mapping module, a log sawing data adjustment module and a usage scenario adjustment module.

[0053] The present invention has the following beneficial effects:

[0054] 1. In the present invention, according to the defect types existing inside the log to be managed and the edge range of the defects, the coefficients of the plane equations of the sections located on both sides of the defects when the log to be managed is sawed and the parameter data during sawing are adjusted, so that the difference between the strength of the wood section after sawing and the strength of the wood section before sawing is less than a preset threshold value, thereby avoiding a significant impact on the quality of the log during the sawing process, thereby ensuring the quality of wood processing.

[0055] 2. The present invention clusters the parameter data of several usage scenarios of wood corresponding to different types of wood defects by using the Salp Unica optimization algorithm, which provides a basis for determining whether the usage scenario of the defective part of the log to be managed is reasonable, thereby ensuring that the defective part of the log to be managed is applied to the most appropriate usage scenario and avoiding safety hazards during use.

[0056] 3. In the present invention, by performing grayscale conversion, frequency domain filtering operation, spatial domain filtering operation and mathematical morphology processing on the collected original scanned image data of the logs to be managed, a higher quality data basis is provided for subsequent determination of the defect type of the logs to be managed based on the scanned image data.

[0057] 4. In the present invention, a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model are constructed for different defect types, thereby providing a judgment model for whether the sawing parameters and section equation coefficients are reasonable when sawing logs with a certain defect type.

[0058] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0060] Figure 1 The present invention is a flowchart of a wood industry data analysis and management method based on machine learning. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0062] Embodiment 1

[0063] See also Figure 1 , this embodiment is a wood industry data analysis and management method based on machine learning, comprising the following steps:

[0064] S1. Collect X-ray scanning images at multiple angles at multiple image collection areas on the surface of the log to be managed to obtain a data matrix of the original scanning image to be managed;

[0065] The S1 comprises the following steps:

[0066] S11, setting a log to be managed and setting the log to be managed to have only a single defect; dividing the surface of the log to be managed into multiple image acquisition areas to obtain a current image acquisition area set a 1 ={a 11 ,...,a 1i ,...,a 1a′}, a 1irepresents the i-th image acquisition area divided on the log to be managed, and a′ represents the total number of image acquisition areas divided on the log to be managed;

[0067] S12, using an X-ray scanning image acquisition system to acquire X-ray scanning images of multiple angles at each image acquisition area on the log to be managed in conjunction with the current image acquisition area set, to obtain a matrix a of the original scanned image data to be managed 2 ;as follows,

[0068]

[0069] Among them, a 2ij represents the jth original scanned image data at the i-th image acquisition area on the log to be managed, represents the total number of raw scanned image data collected at each image collection area on the log to be managed;

[0070] S2, preprocessing the original scanned image data matrix to be managed to obtain a final scanned image data matrix to be managed;

[0071] The S2 comprises the following steps:

[0072] S21, performing grayscale conversion on each original scanned image data in the original scanned image data matrix to be managed, to obtain a scanned image data matrix to be managed after grayscale conversion;

[0073] S22, respectively using a median filter and a Gaussian filter to perform frequency domain filtering operations and space domain filtering operations on each scanned image data in the scanned image data matrix to be managed after grayscale conversion, to obtain a scanned image data matrix to be managed after filtering;

[0074] S23, performing mathematical morphological processing on the filtered scanned image data matrix to be managed, to obtain a final scanned image data matrix a to be managed 3 ;

[0075]

[0076] Among them, a 3ij Indicates a 2ij The final scanned image data to be managed is obtained after grayscale conversion, filtering operation and mathematical morphology processing;

[0077] S3, comparing the final scanned image data matrix to be managed with the standard defect image data to obtain the final scanned image defect type data matrix to be managed; collecting parameter data of several usage scenarios corresponding to each defect type and calculating the corresponding cluster center data to obtain the historical defect scene feature parameter center data matrix;

[0078] The S3 comprises the following steps:

[0079] S31, setting a number of wood defect types and a number of corresponding wood standard defect images to obtain a wood defect type set and a wood defect image data matrix; Respectively represent the knot defect type, decay defect type, crack defect type and non-defect type, and take values ​​of 1, 2, 3, and 4 respectively; compare the final scanned image data matrix to be managed with the multiple wood defect image data corresponding to each wood defect type in the wood defect image data matrix and obtain the corresponding defect type, and obtain the final scanned image defect type data matrix a to be managed 4 ;as follows,

[0080]

[0081] Among them, a 4ij Indicates a 3ij Corresponding image defect type data;

[0082] S32, setting a number of wood use scenario characteristic parameter types, obtaining a wood use scenario characteristic parameter type set b = {b 1 ,...,b i ,...,b b′}, b i represents the set i-th type of wood usage scenario characteristic parameter type, b′ represents the total number of set wood usage scenario characteristic parameter types; the wood usage scenario characteristic parameter type set includes strength requirement, load-bearing degree and decay characteristic requirement, such as making decay-style artworks, etc.; according to the wood usage scenario characteristic parameter type set, the characteristic parameter data of each wood defect type corresponding to multiple wood usage scenarios in the historical wood defect type set is collected to obtain the historical defect scene characteristic parameter data matrix set They respectively represent the historical defect scene characteristic parameter data matrices corresponding to the knot defect type, decay defect type, and crack defect type in the wood defect type set; they are as follows:

[0083]

[0084]

[0085] in, They respectively represent the characteristic parameter data of the jth type of the usage scenario of the i-th wood corresponding to the knot defect type, decay defect type, and crack defect type in the wood defect type set, Indicates the total number of wood corresponding to the knot defect type, decay defect type, and crack defect type in the collected wood defect type set;

[0086] S33, calculating the cluster center data of each historical defect scene characteristic parameter data matrix in the historical defect scene characteristic parameter data matrix set, and obtaining the historical defect scene characteristic parameter center data matrix c; as follows,

[0087]

[0088] Among them, c 1i 、c 2i 、c 3i They respectively represent the characteristic parameter data of the i-th type of the cluster center data set corresponding to the historical defect scene characteristic parameter data matrix corresponding to the knot defect type, decay defect type, and crack defect type in the wood defect type set;

[0089] The S33 comprises the following steps:

[0090] S331. Construct scene defect feature parameter clustering salp population c 1 ' i represents the i-th salp in the salp population clustered by the scene defect feature parameters, represents the size of the scene defect feature parameter clustering salp population; sets the maximum number of iterations of the scene defect feature parameter clustering salp population to And the current number of iterations is are respectively recorded as the maximum iteration number of parameter clustering and the current iteration number of parameter clustering; the search space dimension of the scene defect feature parameter clustering salp population is 3·b′;

[0091] S332, multiple times randomly selecting a row of data from each historical defect scene feature parameter data matrix in the historical defect scene feature parameter data matrix set as the initial position of each salp in the scene defect feature parameter clustering salp population, to obtain a first initial position matrix set d 1k Represents the initial position matrix of the kth salp in the salp population clustered with the scene defect feature parameters; as follows,

[0092]

[0093] Among them, d 1k1j d 1k2j d 1k3j Respectively represent the position component of the initial position of the kth salp in the salp population of the scene defect characteristic parameter clustering in the characteristic parameter data dimension of the jth type of the cluster center data set corresponding to the historical defect scene characteristic parameter data matrix corresponding to the knot defect type, decay defect type, and crack defect type in the wood defect type set;

[0094] S333, calculating the Euclidean distance between each row of data of each historical defect scene feature parameter data matrix in the historical defect scene feature parameter data matrix set and the corresponding row in the initial position matrix of the kth salp in the scene defect feature parameter clustering salp population, and obtaining the Euclidean distance data matrix d k ';as follows,

[0095]

[0096] Among them, d k ' 1i d k ' 2i d k ' 3i Represents the Euclidean distance data between the i-th row data of the 1st, 2nd, and 3rd historical defect scene feature parameter data matrix in the historical defect scene feature parameter data matrix set and the 1st, 2nd, and 3rd row data in the initial position matrix of the kth salp in the scene defect feature parameter clustering salp population; the calculation formulas are as follows,

[0097]

[0098]

[0099] The fitness function of the kth salp in the salp population clustering scene defect feature parameters is constructed according to the Euclidean distance data matrix. as follows,

[0100]

[0101] S334, start iteration, before iteration, set the parameter clustering current iteration number to 1; in the first round of iteration, use the scene defect feature parameter clustering salp in the salp population to obtain the fitness function of the kth salp Calculate the fitness value of the initial position matrix of each salp in the first initial position matrix set to obtain a first fitness value set; use the maximum fitness value in the first fitness value set and the corresponding initial position matrix of the salp as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each salp in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the parameter clustering and enter the next round of iteration;

[0102] In each other iteration, the fitness function of the kth salp in the salp population is clustered using the scene defect feature parameters. Calculate the fitness value of the position matrix of each salp in the scene defect feature parameter clustering salp population updated during the previous iteration to obtain a second fitness value set; use the maximum fitness value in the second fitness value set and the corresponding salp position matrix as the second global optimal fitness and the second global optimal position respectively; update the position matrix of each salp in the scene defect feature parameter clustering salp population updated during the previous iteration according to the second global optimal fitness and the second global optimal position; after the update is completed, add 1 to the current iteration number of the parameter clustering and enter the next iteration;

[0103] S335, when When , stop the iteration and get the first final global optimal position; otherwise, continue to iterate until So far; taking the first final global optimal position as the central data matrix of the historical defect scene characteristic parameters;

[0104] S4, collecting plane equation coefficient data of the section when sawing a plurality of test logs to be sawed with single defects, defect edge coordinate data, sawing parameter data and corresponding average strength difference data of the normal parts before and after sawing, and constructing a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model;

[0105] The S4 includes the following guarantees:

[0106] S41, according to the wood defect type set, a plurality of test logs to be sawn with a single corresponding defect are respectively set, and a plurality of image acquisition areas are divided on the surface of the test logs to be sawn, and then the X-ray scanning image acquisition system in S12 is used to respectively collect corresponding scanning image data at each image acquisition area on each test log to be sawn, and each scanned image data collected is processed in the manner of S21, S22 and S23 to obtain a scanned image data set matrix of the test logs to be sawn as follows,

[0107]

[0108] in, represents the scanned image dataset of the i-th test log to be sawn corresponding to the knot defect type, decay defect type, and crack defect type obtained by collection and processing, e 1 Indicates the total number of test logs to be sawn corresponding to each wood defect type;

[0109] Respectively The scanned image data corresponding to the j-th image acquisition area in e 2express The total number of scanned image data;

[0110] S42, when sawing each test log to be sawed, construct a three-dimensional coordinate system for each test log to be sawed, and obtain a test three-dimensional coordinate system matrix; cooperate with the test three-dimensional coordinate system matrix and according to the scanned image data set matrix of the test log to be sawed Set several coordinate collection points at the defect edge of each test log to be sawn and collect the corresponding coordinate data to obtain the test defect edge coordinate data set matrix e 1 '; then with the test three-dimensional coordinate system matrix to collect the plane equation coefficients corresponding to the two sections during sawing, the test section equation coefficient data matrix e' is obtained 2 ;e 1 ′、e′ 2 They are as follows:

[0111]

[0112] Among them, e 1 ' 1i 、e 1 ' 2i 、e 1 ' 2i represents the defect edge coordinate data set of the i-th test log to be sawn corresponding to the knot defect type, decay defect type, and crack defect type, respectively, e′ 21i1 , e′ 22i1 , e′ 23i1 The coefficient sets of the first section equation of the i-th test log to be sawn corresponding to the knot defect type, decay defect type, and crack defect type, respectively, e′ 21i2 , e′ 22i2 , e′ 23i3 They represent the coefficient sets of the second section equation of the i-th test log to be sawn corresponding to the knot defect type, decay defect type, and crack defect type respectively; e 1 ' 1i 、e 1 ' 2i 、e 1 ' 3i , e′ 21i1 , e′ 22i1 , e′ 23i1 , e′ 21i2 , e′ 22i2 , e′ 23i3 They are as follows:

[0113]

[0114]

[0115]

[0116] Among them, e 1 ' 1ij1 、e 1 ' 1ij2 、e 1 ' 1ij3 、e 1 ' 2ij1 、e 1 ' 2ij2 、e 1 ' 2ij3 、e 1 ' 3ij1 、e 1 ' 3ij2 、e 1 ' 3ij3 Respectively represent e 1 ' 1i 、e 1 ' 2i 、e 1 ' 3i The 1, 2, and 3-dimensional coordinate data of the j-th defect edge point in Indicates the total number of coordinate collection points set for the defect edge of each test log to be sawn;

[0117] S43, setting a number of sawing parameter types to obtain a sawing parameter type set; the sawing parameter type set includes a cutter rotation speed and a cutter displacement speed, etc.; collecting parameter data when sawing each test log to be sawed according to the sawing parameter type set to obtain a test sawing parameter data set matrix e 3 ';as follows,

[0118]

[0119] Among them, e 3 ' 1i 、e 3 ' 2i 、e 3 ' 2i They respectively represent sawing parameter data sets when sawing the i-th test log to be sawed corresponding to the knot defect type, decay defect type, and crack defect type; e 3 ' 1ij 、e 3 ' 2ij 、e 3 ' 3ij Respectively represent e 3 ' 1i 、e 3 ' 2i 、e3 ' 2i The j-th type of sawing parameter data in;

[0120] Then collect the average strength difference data of the normal part of each test log to be sawed before and after sawing, and obtain the test strength difference average data matrix e′ 4 ;as follows,

[0121]

[0122] Among them, e′ 41i , e′ 42i , e′ 42i They respectively represent the average data of the strength difference of the normal part of the i-th test log to be sawed before and after sawing corresponding to the knot defect type, decay defect type, and crack defect type;

[0123] S44, constructing a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model according to the test defect edge coordinate data set matrix, the test section equation coefficient data matrix, the test sawing parameter data set matrix and the test strength difference average data matrix;

[0124] The S44 comprises the following steps:

[0125] S441, constructing a first initial SVM model, a second initial SVM model and a third initial SVM model and setting a first training data ratio, a second training data ratio and a third training data ratio; dividing the data corresponding to the node defect type, the decay defect type and the crack defect type in the test defect edge coordinate data set matrix, the test section equation coefficient data matrix, the test sawing parameter data set matrix and the test strength difference average data matrix according to the first training data ratio, the second training data ratio and the third training data ratio, respectively, to obtain the test defect edge coordinate training data set matrix, the test section equation coefficient training data matrix, the test sawing parameter training data set matrix, the test strength difference average training data matrix, the test defect edge coordinate test data set matrix, the test section equation coefficient test data matrix, the test sawing parameter test data set matrix and the test strength difference average test data matrix;

[0126] S442, using the test defect edge coordinate training data set matrix, the test section equation coefficient training data set matrix, the test sawing parameter training data set matrix, and the test strength difference average training data matrix, the data corresponding to the knot defect type, the decay defect type, and the crack defect type are used to train and test the first initial SVM model, the second initial SVM model, and the third initial SVM model respectively; after the training and testing are completed, a knot defect strength difference mapping model, a decay defect strength difference mapping model, and a crack defect strength difference mapping model are obtained;

[0127] S5. Mapping the initial coefficient data of the plane equations of the two sections when the logs to be managed are sawed, the initial parameter data of sawing, and the defect edge coordinate data according to the knot defect strength difference mapping model, the decay defect strength difference mapping model, and the crack defect strength difference mapping model to obtain the initial strength difference data to be managed;

[0128] The S5 comprises the following steps:

[0129] S51, constructing a three-dimensional coordinate system of the log to be managed when sawing the log to be managed, and obtaining the three-dimensional coordinate system to be managed; setting a number of coordinate points at the edge of the defect in the log to be managed according to the final defect type data matrix of the scanned image to be managed, and obtaining a coordinate data set of the defect edge to be managed as follows,

[0130]

[0131] in, The 1-, 2-, and 3-dimensional data of the i-th coordinate point set at the edge of the defect in the log to be managed respectively represent the data; the initial coefficient data of the plane equations of the two sections when sawing the log to be managed and the initial sawing parameter data are randomly set in conjunction with the sawing parameter type set to obtain the coefficient data set of the initial section equation to be managed And the initial sawing parameter data set to be managed represent the x-variable coefficient, y-variable coefficient, z-variable coefficient and constant of the plane equation of the first section when the log to be managed is sawed, respectively, respectively represent the x-variable coefficient, y-variable coefficient, z-variable coefficient and constant of the plane equation of the second section when the log to be managed is sawed; represents the initial parameter data of sawing of the i-th type when sawing the log to be managed;

[0132] S52, determining the defect type of the log to be managed according to the final defect type data matrix of the scanned image to be managed, the first defect type of the log to be managed;

[0133] When the first log defect type to be managed is a knot defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed, and the initial sawing parameter data set to be managed are input into the knot defect strength difference mapping model for mapping; when the first log defect type to be managed is a decay defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed, and the initial sawing parameter data set to be managed are input into the decay defect strength difference mapping model for mapping; when the first log defect type to be managed is a crack defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed, and the initial sawing parameter data set to be managed are input into the crack defect strength difference mapping model for mapping; after the mapping is completed, the initial strength difference data to be managed is obtained;

[0134] S6. Adjust the initial coefficient data of the plane equations of the two sections when sawing the logs to be managed and the initial sawing parameter data according to the initial strength difference data to be managed, so as to obtain a final section equation coefficient data set and a final sawing parameter data set to be managed; and then adjust and replace the usage scenario of the defective part of the logs to be managed;

[0135] The S6 comprises the following steps:

[0136] S61, setting a first intensity difference threshold, a second intensity difference threshold, and a third intensity difference threshold;

[0137] S62, when the first log defect type to be managed is a knot defect type and the initial strength difference data to be managed is greater than or equal to the first strength difference threshold, or when the first log defect type to be managed is a decay defect type and the initial strength difference data to be managed is greater than or equal to the second strength difference threshold, or when the first log defect type to be managed is a crack defect type and the initial strength difference data to be managed is greater than or equal to the third strength difference threshold, adjust the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed until the first log defect type to be managed is greater than or equal to the first strength difference threshold. When the defect type is a knot defect type and the initial strength difference data to be managed is less than the first strength difference threshold, or when the first log defect type to be managed is a decay defect type and the initial strength difference data to be managed is less than the second strength difference threshold, or when the first log defect type to be managed is a crack defect type and the initial strength difference data to be managed is less than the third strength difference threshold, the final section equation coefficient data set to be managed and the final sawing parameter data set to be managed are obtained; otherwise, there is no need to adjust the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed;

[0138] S63, after the adjustment of the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed is completed, sawing operation is performed on the managed logs in coordination with the final section equation coefficient data set to be managed and the final sawing parameter data set to be managed;

[0139] The scene feature parameter type set of the wood is combined with the scene feature parameter data of the defective part of the log to be managed after processing to obtain the scene feature parameter data set to be managed f = {f 1 ,...,f i ,...,f b′}, f i Indicates parameter data of the i-th type of usage scenario after the logs to be managed are processed;

[0140] S64, calculating the Euclidean distance between the usage scenario characteristic parameter data set to be managed and each row of data in the central data matrix of the historical defect scenario characteristic parameter to obtain a first Euclidean distance data set; taking the defect type corresponding to the smallest Euclidean distance data in the first Euclidean distance data set as the second log defect type to be managed;

[0141] When the defect type of the second log to be managed is inconsistent with the defect type of the first log to be managed, the usage scenario of the defective part after the processing of the log to be managed is changed; otherwise, there is no need to change the usage scenario of the defective part after the processing of the log to be managed.

[0142] Embodiment 2

[0143] The present embodiment discloses a wood industry data analysis and management system based on machine learning, the system can implement the method of the above embodiment, including a log scanning image data acquisition module to be managed, an image preprocessing module, a log defect type data acquisition module to be managed, a scene parameter type setting module, a historical scene parameter acquisition module, a cluster center calculation module, a sawing test data acquisition module, a mapping model construction module, a mapping module, a log sawing data adjustment module to be managed, and a usage scene adjustment module;

[0144] The log scan image data acquisition module to be managed is used to acquire X-ray scan images at multiple angles at multiple image acquisition areas on the surface of the log to be managed to obtain a matrix of original scan image data to be managed;

[0145] The image preprocessing module is used to perform grayscale conversion, frequency domain filtering operation, space domain filtering operation and mathematical morphology processing on the original scanned image data matrix to be managed, so as to obtain the final scanned image data matrix to be managed;

[0146] The module for acquiring defect type data of logs to be managed is used to compare the final scanned image data matrix to be managed with the standard defect image data to obtain the final scanned image defect type data matrix to be managed;

[0147] The scenario parameter type setting module is used to set a number of wood usage scenario characteristic parameter types to obtain a wood usage scenario characteristic parameter type set;

[0148] The historical scene parameter collection module is used to collect parameter data of several usage scenes corresponding to each defect type according to the wood usage scene characteristic parameter type set to obtain a historical defect scene characteristic parameter data matrix set;

[0149] The cluster center calculation module is used to calculate the cluster center data of each historical defect scene characteristic parameter data matrix in the historical defect scene characteristic parameter data matrix set to obtain the historical defect scene characteristic parameter center data matrix;

[0150] The sawing test data acquisition module is used to collect plane equation coefficient data of the section when sawing a plurality of single defective test logs to be sawed, defect edge coordinate data, sawing parameter data and corresponding average strength difference data of the normal part before and after sawing, and obtain a test defect edge coordinate data set matrix, a test section equation coefficient data matrix, a test sawing parameter data set matrix and a test strength difference average data matrix;

[0151] The mapping model construction module is used to construct a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model by using a test defect edge coordinate data set matrix, a test section equation coefficient data matrix, a test sawing parameter data set matrix and a test strength difference average data matrix;

[0152] The mapping module is used to map the initial coefficient data of the plane equations of the two sections when the logs to be managed are sawed, the initial parameter data of sawing, and the defect edge coordinate data according to the knot defect strength difference mapping model, the decay defect strength difference mapping model, and the crack defect strength difference mapping model, so as to obtain the initial strength difference data to be managed;

[0153] The log sawing data adjustment module to be managed is used to adjust the initial coefficient data of the plane equations of the two sections when the log to be managed is sawed and the initial sawing parameter data according to the initial strength difference data to be managed, so as to obtain the final section equation coefficient data set to be managed and the final sawing parameter data set to be managed;

[0154] The usage scenario adjustment module is used to adjust and replace the usage scenario of the defective part of the log to be managed in coordination with the central data matrix of historical defect scenario characteristic parameters.

[0155] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0156] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A data analysis and management method for the wood industry based on machine learning, characterized in that: The following steps are involved: S1. Collect X-ray scanning images at multiple angles at multiple image collection areas on the surface of the log to be managed to obtain a data matrix of the original scanning image to be managed; S2, preprocessing the original scanned image data matrix to be managed to obtain a final scanned image data matrix to be managed; S3, comparing the final scanned image data matrix to be managed with the standard defect image data to obtain the final scanned image defect type data matrix to be managed; collecting parameter data of several usage scenarios corresponding to each defect type and calculating the corresponding cluster center data to obtain the historical defect scene feature parameter center data matrix; S4, collecting plane equation coefficient data of the section when sawing a plurality of test logs to be sawed with single defects, defect edge coordinate data, sawing parameter data and corresponding average strength difference data of the normal parts before and after sawing, and constructing a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model; S5. Mapping the initial coefficient data of the plane equations of the two sections when the logs to be managed are sawed, the initial parameter data of sawing, and the defect edge coordinate data according to the knot defect strength difference mapping model, the decay defect strength difference mapping model, and the crack defect strength difference mapping model to obtain the initial strength difference data to be managed; S6. Adjust the initial coefficient data of the plane equations of the two sections when sawing the logs to be managed and the initial sawing parameter data according to the initial strength difference data to be managed, so as to obtain a final section equation coefficient data set to be managed and a final sawing parameter data set to be managed; Then adjust and replace the usage scenarios of the defective parts of the logs to be managed.

2. The method for wood industry data analysis and management based on machine learning according to claim 1, characterized in that: The S1 comprises the following steps: S11, setting a log to be managed and setting the log to be managed to have only a single defect; dividing the surface of the log to be managed into multiple image acquisition areas to obtain a current image acquisition area set; S12. In conjunction with the current image acquisition area set, an X-ray scanning image acquisition system is used to acquire X-ray scanning images of multiple angles at each image acquisition area on the log to be managed, to obtain a data matrix of the original scanning image to be managed.

3. The method for wood industry data analysis and management based on machine learning according to claim 2 is characterized in that: The S2 comprises the following steps: S21, performing grayscale conversion on each original scanned image data in the original scanned image data matrix to be managed, to obtain a scanned image data matrix to be managed after grayscale conversion; S22, respectively using a median filter and a Gaussian filter to perform frequency domain filtering operations and space domain filtering operations on each scanned image data in the scanned image data matrix to be managed after grayscale conversion, to obtain a scanned image data matrix to be managed after filtering; S23, performing mathematical morphology processing on the filtered scanned image data matrix to be managed to obtain a final scanned image data matrix to be managed.

4. The method for wood industry data analysis and management based on machine learning according to claim 3 is characterized in that: The S3 comprises the following steps: S31, respectively comparing the final scanned image data matrix to be managed with a plurality of corresponding wood standard defect image data and obtaining corresponding defect types to obtain a final scanned image defect type data matrix to be managed; S32, collecting characteristic parameter data of multiple wood usage scenarios corresponding to each wood defect type in the historical wood defect type set, and obtaining a historical defect scene characteristic parameter data matrix set; S33, calculating the cluster center data of each historical defect scene characteristic parameter data matrix in the historical defect scene characteristic parameter data matrix set to obtain the historical defect scene characteristic parameter center data matrix.

5. The method for wood industry data analysis and management based on machine learning according to claim 4 is characterized in that: The S33 comprises the following steps: S331, constructing a scene defect feature parameter clustering salp population; setting the maximum number of iterations of the scene defect feature parameter clustering salp population to c~1 and the current number of iterations to c~2, which are recorded as the maximum number of iterations of parameter clustering and the current number of iterations of parameter clustering respectively; S332, randomly selecting a row of data from each historical defect scene feature parameter data matrix in the historical defect scene feature parameter data matrix set as the initial position of each salp in the scene defect feature parameter clustering salp population, to obtain a first initial position matrix set; S333, calculating the Euclidean distance between each row of data of each historical defect scene feature parameter data matrix in the historical defect scene feature parameter data matrix set and the corresponding row in the initial position matrix of the kth salp in the scene defect feature parameter clustering salp population, to obtain a Euclidean distance data matrix; Constructing a fitness function of the kth salp in the scene defect feature parameter clustering salp population according to the Euclidean distance data matrix; S334, start iteration; in each round of iteration, use the fitness function of the kth salp in the scene defect feature parameter clustering salp population to calculate the fitness value of the position matrix of each salp in the scene defect feature parameter clustering salp population updated in the previous round of iteration, and update the position matrix of each salp in the scene defect feature parameter clustering salp population updated in the previous round of iteration; S335. When c~2≥c~1, stop iteration and obtain the first final global optimal position; otherwise, continue iteration until c~2≥c~1; use the first final global optimal position as the central data matrix of historical defect scene feature parameters.

6. The method for wood industry data analysis and management based on machine learning according to claim 5, characterized in that: The S4 includes the following guarantees: S41, respectively setting a plurality of test logs to be sawn with a single corresponding defect according to the wood defect type set and collecting the scanning image data at each corresponding image collection area, and processing each collected scanning image data in the manner of S21, S22 and S23 to obtain a scanning image data set matrix of the test logs to be sawn; S42, constructing a three-dimensional coordinate system for each test log to be sawn, and obtaining a test three-dimensional coordinate system matrix; In conjunction with the test three-dimensional coordinate system matrix and according to the scanned image data set matrix of the test log to be sawn, a number of coordinate collection points are set at the defect edge of each test log to be sawn and corresponding coordinate data are collected to obtain a test defect edge coordinate data set matrix; Then, the plane equation coefficients corresponding to the two sections during sawing are collected in conjunction with the test three-dimensional coordinate system matrix to obtain the test section equation coefficient data matrix; S43, setting a number of sawing parameter types to obtain a sawing parameter type set; the sawing parameter type set includes a cutter rotation speed and a cutter displacement speed, etc.; Collect parameter data when sawing each test log to be sawed according to the sawing parameter type set to obtain a test sawing parameter data set matrix; Then, the average strength difference data of the normal part of each test log to be sawed before and after sawing is collected to obtain the test strength difference average data matrix; S44. Construct a knot defect strength difference mapping model, a decay defect strength difference mapping model and a crack defect strength difference mapping model according to the test defect edge coordinate data set matrix, the test section equation coefficient data matrix, the test sawing parameter data set matrix and the test strength difference average data matrix.

7. The method for wood industry data analysis and management based on machine learning according to claim 6 is characterized in that: The knot defect strength difference mapping model, the decay defect strength difference mapping model and the crack defect strength difference mapping model all adopt the SVM model.

8. The method for wood industry data analysis and management based on machine learning according to claim 7 is characterized in that: The S5 comprises the following steps: S51, constructing a three-dimensional coordinate system of the log to be managed when sawing the log to be managed, and obtaining the three-dimensional coordinate system to be managed; setting a number of coordinate points at the edge of the defect in the log to be managed according to the final defect type data matrix of the scanned image to be managed, and obtaining a defect edge coordinate data set to be managed; randomly setting the initial coefficient data of the plane equations of the two sections when sawing the log to be managed and the initial sawing parameter data set in accordance with the sawing parameter type set, and obtaining the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed; S52, determining the defect type of the log to be managed according to the final defect type data matrix of the scanned image to be managed, the first defect type of the log to be managed; When the first log defect type to be managed is a knot defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed are input into the knot defect strength difference mapping model for mapping; when the first log defect type to be managed is a decay defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed are input into the decay defect strength difference mapping model for mapping; when the first log defect type to be managed is a crack defect type, the defect edge coordinate data set to be managed, the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed are input into the crack defect strength difference mapping model for mapping; after the mapping is completed, the initial strength difference data to be managed is obtained.

9. The method for wood industry data analysis and management based on machine learning according to claim 8, characterized in that: The S6 comprises the following steps: S61, setting a first intensity difference threshold, a second intensity difference threshold, and a third intensity difference threshold; S62, when the first log defect type to be managed is a knot defect type and the initial strength difference data to be managed is greater than or equal to the first strength difference threshold, or when the first log defect type to be managed is a decay defect type and the initial strength difference data to be managed is greater than or equal to the second strength difference threshold, or when the first log defect type to be managed is a crack defect type and the initial strength difference data to be managed is greater than or equal to the third strength difference threshold, adjust the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed until the first log defect type to be managed is greater than or equal to the first strength difference threshold. When the defect type is a knot defect type and the initial strength difference data to be managed is less than the first strength difference threshold, or when the first log defect type to be managed is a decay defect type and the initial strength difference data to be managed is less than the second strength difference threshold, or when the first log defect type to be managed is a crack defect type and the initial strength difference data to be managed is less than the third strength difference threshold, the final section equation coefficient data set to be managed and the final sawing parameter data set to be managed are obtained; otherwise, there is no need to adjust the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed; S63, after the adjustment of the initial section equation coefficient data set to be managed and the initial sawing parameter data set to be managed is completed, sawing operation is performed on the managed logs in coordination with the final section equation coefficient data set to be managed and the final sawing parameter data set to be managed; Collect usage scenario characteristic parameter data of defective parts of the logs to be managed after processing, and obtain a usage scenario characteristic parameter data set to be managed; S64, calculating the Euclidean distance between the usage scenario characteristic parameter data set to be managed and each row of data in the central data matrix of the historical defect scenario characteristic parameter to obtain a first Euclidean distance data set; taking the defect type corresponding to the smallest Euclidean distance data in the first Euclidean distance data set as the second log defect type to be managed; When the defect type of the second log to be managed is inconsistent with the defect type of the first log to be managed, the usage scenario of the defective part after the processing of the log to be managed is changed; otherwise, there is no need to change the usage scenario of the defective part after the processing of the log to be managed.

10. A system for implementing the wood industry data analysis and management method based on machine learning as described in any one of claims 1 to 9.

Images