Method for evaluating characteristics and modification of catalpa bungei wood based on planting analysis

Abstract

The invention relates to the technical field of catalpa bungei wood modification characteristic evaluation, in particular to a catalpa bungei wood characteristic and modification evaluation method based on planting analysis. If at least any one or more mutagenesis standard planting factors exist in the associated planting factor set, regression decision analysis is performed on the wood characteristic index difference value during modification through a planting termination interval variable of the mutagenesis standard planting factor before modification; determining the variation degree of the mutagenesis standard planting factor when the catalpa bungei wood sample is modified by the target modification method; limiting the accurate evaluation fluctuation amplitude of the planning target characteristic evaluation item according to the variation degree, and adjusting the ideal characteristic evaluation radar map of the catalpa bungei on the basis of the accurate evaluation fluctuation amplitude to obtain the actual characteristic evaluation radar map and the modification characteristic level of the modified catalpa bungei wood sample. The method can accurately analyze whether the planting factors have influence on modification of the catalpa bungei or not and the influence degree, and improves the evaluation accuracy and credibility of the modification characteristics of the catalpa bungei.

Description

Technical Field

[0001] The invention relates to the technical field of evaluation of modified properties of Catalpa ovata wood, and in particular to a method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis. Background Art

[0002] Catalpa ovata is a fast-growing and ecologically adaptable tree species that is widely distributed throughout the world, especially in Asia. Its wood is favored for its light weight, flexibility, corrosion resistance, and easy processing, and is widely used in furniture, construction, handicrafts and other fields. However, the physical and mechanical properties of Catalpa ovata wood are affected to a certain extent by various factors such as the growth environment, planting conditions and tree species selection, resulting in certain limitations in the actual modification and application of wood. With the in-depth study of the characteristics of Catalpa ovata wood, it is hoped that the quality and performance of wood can be improved by optimizing planting management. In addition, in order to improve the application performance of Catalpa ovata wood, wood modification technologies such as heat treatment, chemical modification and physical modification have gradually become the focus of research. These modification technologies can effectively improve the durability, mechanical properties and corrosion resistance of wood and broaden its application fields.

[0003] However, the existing wood property analysis methods mostly rely on traditional laboratory testing methods, such as mechanical property testing, density measurement and durability evaluation, but these methods are usually unable to fully reflect the performance of the modified properties of Catalpa ovata in actual planting and growth; in particular, the existing technology often ignores the impact of the planting environment, the impact of pests and diseases, the age of Catalpa ovata and specifications on the properties of Catalpa ovata and the complex mechanism of action, resulting in the lack of actual representativeness of the evaluation results. Secondly, the modification evaluation methods of Catalpa ovata are relatively single. Although they can improve the mechanical properties and durability of wood to a certain extent, the modification effects and long-term stability of these methods have not been fully evaluated. At the same time, some methods require the collaborative operation of multiple people, which is time-consuming and labor-intensive, with low evaluation efficiency and large modification property evaluation errors. A single modification method may be difficult to fully meet the modification performance requirements of Catalpa ovata under different growth conditions. Summary of the invention

[0004] The invention overcomes the shortcomings of the prior art and provides a method for evaluating the characteristics and modification of catalpa ovata wood based on planting analysis.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] The first aspect of the present invention provides a method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis, comprising the following steps:

[0007] S102: obtaining original internal and external characteristic signals of the wood sample of Catalpa chinensis, calculating the local signal trend of the original internal and external characteristic signals by envelope calculation to obtain internal and external characteristic point cloud fragments, calculating the factor correlation between each internal and external characteristic point cloud fragment and each planting factor in the historical planting system, and obtaining a set of associated planting factors that affect the internal and external characteristics of the wood sample of Catalpa chinensis in the historical planting system;

[0008] S104: Based on big data, multiple standard planting systems for Catalpa ovata are obtained, a first hotspot matrix of internal and external characteristic distribution of Catalpa ovata wood samples under each standard planting factor difference condition in each standard planting system for target modification method is constructed, and a second hotspot matrix of internal and external characteristic distribution of mutation is constructed, and the mutation probability value is calculated and analyzed by combining the first hotspot matrix and the second hotspot matrix to obtain a set of induced mutation standard planting factors;

[0009] S106: If the associated planting factor set contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, a regression decision analysis is performed on the difference of the wood characteristic index during modification through the termination planting interval variable of the mutagenic standard planting factor before modification to obtain a regression decision tree, and the degree of mutation of the mutagenic standard planting factor when the target modification method is used to modify the golden catalpa wood sample is determined based on the regression decision tree;

[0010] S108: By simulating and evaluating the standard modified three-dimensional model of the golden catalpa wood sample, an idealized characteristic evaluation radar chart is obtained, and the accurate evaluation fluctuation range of each target characteristic evaluation item is limited and planned according to the degree of variation. The idealized characteristic evaluation radar chart is adjusted based on the accurate evaluation fluctuation range to obtain the actual characteristic evaluation radar chart of the golden catalpa wood sample after modification and the modified characteristic level.

[0011] More specifically, the step S102 includes the following steps:

[0012] Obtain a sample of Catalpa ovata wood to be evaluated, and use an X-ray detector to perform an X-ray scan of the Catalpa ovata wood sample at a preset time sequence to obtain original internal and external characteristic signals of the Catalpa ovata wood sample at the preset time sequence;

[0013] Extracting the local maximum and the local minimum in the original internal and external characteristic signal, and performing signal interpolation processing based on the local maximum and the local minimum to construct the upper envelope and the lower envelope of the original internal and external characteristic signal;

[0014] Preset an envelope threshold interval, calculate the average values ​​of the upper envelope line and the lower envelope line to obtain an envelope mean value, and if the envelope mean value is within the envelope threshold interval, remove the local signal trend corresponding to the envelope mean value from the original internal and external characteristic signals to obtain new internal and external characteristic signals, repeat the above envelope operation and judgment steps to obtain the remaining new internal and external characteristic signals of the original internal and external characteristic signals and integrate them, and finally obtain N internal and external characteristic point cloud fragments of the golden silk catalpa wood sample;

[0015] Obtaining the planting log of the wood sample of Catalpa ovata, extracting the historical planting system of the wood sample of Catalpa ovata within a preset time period based on the planting log, and defining each system component in the historical planting system as a planting factor;

[0016] Based on the big data network, the benchmark internal and external feature point cloud generated when planting Catalpa ovata wood under the historical planting system is obtained, and the factor correlation coefficient between each internal and external feature point cloud fragment and each planting factor is calculated according to the preset factor correlation critical coefficient of the benchmark internal and external feature point cloud, so as to obtain multiple factor correlation coefficients;

[0017] If the factor correlation coefficient is less than the preset factor correlation critical coefficient, the planting factor corresponding to the factor correlation coefficient is eliminated; if the factor correlation coefficient is greater than the preset factor correlation critical coefficient, the planting factor corresponding to the factor correlation coefficient is retained and marked as a correlated planting factor;

[0018] All the related planting factors were obtained and integrated to obtain a set of related planting factors that affected the internal and external characteristics of Catalpa ovata wood samples in the historical planting system.

[0019] More specifically, the step S104 includes the following steps:

[0020] Based on the big data network, several relevant planting cases of Catalpa ovata are obtained, and multiple standard planting systems of Catalpa ovata are extracted through the relevant planting cases, and the modification requirements of Catalpa ovata wood samples are obtained at the same time;

[0021] Obtaining a three-dimensional model of a wood sample of Catalpa ovata, constructing a hotspot base map of the wood sample of Catalpa ovata based on the three-dimensional model, and obtaining a target modification method of the wood sample of Catalpa ovata according to modification requirements;

[0022] Through the planting log, all internal and external modification feature point clouds of the target modification method under each standard planting factor difference condition in each standard planting system and the internal and external modification coordinates of each internal and external modification feature point cloud are obtained;

[0023] Plot all internal and external modification feature point clouds on the hotspot base map to generate an internal and external modification feature distribution hotspot map, and divide the internal and external modification feature distribution hotspot map into M sub-hotspot distributions based on the internal and external modification coordinates, which are defined as a first hotspot matrix;

[0024] Mark the mutated internal and external characteristic point clouds of the target modification method in each first hotspot matrix during the modification process of the golden catalpa wood sample, and obtain the mutated hotspot distribution of each first hotspot area, which is defined as the second hotspot matrix;

[0025] A Bayesian inference algorithm is introduced to calculate the hotspot matrix ratio of the second hotspot matrix to the first hotspot matrix, and the mutation hotspot matrix ratio is obtained. Based on the mutation hotspot matrix ratio, a probability distribution field of mutation hotspots generated during the modification process of the Catalpa chinensis wood sample is constructed by calculation in the Bayesian inference algorithm.

[0026] Based on the probability field, the probability that each standard planting factor in each standard planting system causes the target modification method to modify the internal and external characteristics of the Catalpa ovata wood sample to mutate is calculated to obtain a number of mutation probability values;

[0027] If the mutation probability value is greater than the preset mutation probability value, the standard planting factor corresponding to the mutation probability value is calibrated as the mutagenic standard planting factor to obtain a mutagenic standard planting factor set.

[0028] More specifically, the step S106 includes the following steps:

[0029] If the associated planting factor set that affects the internal and external characteristics of the Catalpa ovata wood sample in the historical planting system contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, the termination planting interval variable of the mutagenic standard planting factor in the preset historical time period before the Catalpa ovata wood sample is modified by the target modification method through the planting log;

[0030] Obtaining the wood property index of the golden catalpa wood sample within a preset historical time period before the target modification method is used to modify the golden catalpa wood sample, which is marked as the starting wood property index, and obtaining the wood property index of the golden catalpa wood sample after the target modification method is used to modify the golden catalpa wood sample, which is marked as the ending wood property index;

[0031] Calculating the index difference between the termination wood property index and the initial wood property index to obtain a wood property index difference, and performing regression analysis on the wood property index difference through the termination planting interval variable;

[0032] During the regression analysis, the mean square error algorithm is introduced to calculate the mean square error of each variable in the termination planting interval variable, and only the termination planting interval variable corresponding to the maximum mean square error is extracted and defined as the optimal planting interval variable. The splitting compliance point of the optimal planting interval variable is created according to the mean square error.

[0033] A threshold value of the number of sample nodes is preset, a regression root node of the wood characteristic index difference is constructed and set as the starting node, and a split operation of the branch subset is performed on the optimal planting interval variable starting from the starting node based on the splitting follow point to obtain the current number of sample nodes of each branch subset;

[0034] If the current number of sample nodes exceeds the sample node number threshold, the splitting operation of the branch subset is stopped, and the above branch subset splitting operation and the determination of the current number of sample nodes are repeated, and finally a regression decision tree of the optimal planting interval variable traversal wood characteristic index difference is obtained;

[0035] All leaf nodes displayed by the regression decision tree are stripped out to obtain the leaf node pattern and the leaf node value of each leaf node. The degree of mutation of the standard planting factor for the target modification method when modifying the golden silk wood sample is determined according to the leaf node pattern and the leaf node value.

[0036] More specifically, the step S108 includes the following steps:

[0037] Obtaining the benchmark modification process parameters of the target modification method, performing standardized modification based on the benchmark modification process parameters, obtaining a standard modified three-dimensional model of the golden silk catalpa wood sample, testing the standard modified three-dimensional model through property simulation, and performing the evaluation of the target property evaluation items of the golden silk catalpa wood sample based on the property evaluation criteria, to obtain an idealized property evaluation radar chart;

[0038] Extract the evaluation fluctuation range of each target characteristic evaluation item for structural mutation caused by modification of Catalpa ovata wood based on the evaluation mechanism, perform mutation processing on the standard modified three-dimensional model based on the degree of mutation, so as to construct a mutation modification three-dimensional model of the target modification method for the modified Catalpa ovata wood sample by the mutagenic standard planting factor;

[0039] Registering the mutated modified three-dimensional model to the standard modified three-dimensional model, calculating the registration misalignment degree between the mutated modified three-dimensional model and the standard modified three-dimensional model, and obtaining the registration misalignment rate;

[0040] Preset the evaluation fluctuation range according to the registration misalignment rate, and limit the evaluation fluctuation range of each target characteristic evaluation item based on the evaluation fluctuation range planning, so as to obtain the accurate evaluation fluctuation range of each target characteristic evaluation item when the modified structure of golden catalpa wood has a degree of abnormality;

[0041] The idealized characteristic evaluation radar chart is adjusted by accurately evaluating the fluctuation amplitude, and finally the actual characteristic evaluation radar chart of the modified Catalpa ovata wood sample is obtained; the area value of the radar region that does not overlap between the actual characteristic evaluation radar chart and the idealized characteristic evaluation radar chart is obtained, and the modified characteristic level of the actual characteristics of the modified Catalpa ovata wood sample compared with the idealized characteristics is determined according to the radar region area value.

[0042] More specifically, in the step S108, the benchmark modification process parameters of the target modification method are obtained, standardized modification is performed based on the benchmark modification process parameters, a standard modified three-dimensional model of the golden silk catalpa wood sample is obtained, the standard modified three-dimensional model is tested by property simulation, and the target property evaluation items of the golden silk catalpa wood sample are evaluated based on the property evaluation criteria to obtain an idealized property evaluation radar chart, which specifically includes the following steps:

[0043] Obtaining a preset modification process flow plan of the target modification method, and obtaining the benchmark modification process parameters of the target modification method for the standardized modification of the Catalpa ovata wood sample through the preset modification process flow plan;

[0044] Based on the benchmark modification process parameters, a standardized modification of the target modification method is performed on the wood sample of Catalpa ovata in the model simulation software to generate a standard modified three-dimensional model of the wood sample of Catalpa ovata;

[0045] A series of modified test signals are written and loaded according to the benchmark modified process parameters, and the series of modified test signals are injected into the standard modified three-dimensional model of the golden silk wood sample through the model simulation software to perform a characteristic simulation test of the golden silk wood sample after standard modification;

[0046] Introduce a deep belief algorithm to obtain target characteristic evaluation items of golden catalpa wood samples according to modification requirements, obtain characteristic evaluation criteria of golden catalpa wood through a big data network, and obtain an evaluation mechanism for each target characteristic evaluation item based on the characteristic evaluation criteria;

[0047] An evaluation model is constructed in the deep belief algorithm based on the evaluation mechanism of each target characteristic evaluation item. The evaluation model is used to evaluate the target characteristic evaluation items of the standard modified three-dimensional model during the characteristic test process, and the characteristic evaluation results of each target characteristic evaluation item of the standard modified Catalpa chinensis wood sample are obtained, which are defined as idealized characteristic evaluation results.

[0048] A radar chart framework of the evaluation mechanism is constructed, and the idealized characteristic evaluation result of each target characteristic evaluation item is fitted into the radar chart framework to obtain an idealized characteristic evaluation radar chart.

[0049] The second aspect of the present invention provides a system for evaluating the characteristics and modifications of Catalpa ovata wood based on planting analysis. The system comprises a memory and a processor. The memory stores a program for evaluating the characteristics and modifications of Catalpa ovata wood based on planting analysis. When the program for evaluating the characteristics and modifications of Catalpa ovata wood is executed by the processor, any one of the steps of the method for evaluating the characteristics and modifications of Catalpa ovata wood is implemented.

[0050] The present invention solves the technical defects existing in the background technology, and the beneficial technical effects of the present invention are:

[0051] If the associated planting factor set contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, a regression decision analysis is performed on the difference of the wood characteristic index during modification through the termination planting interval variable of the mutagenic standard planting factor before modification to obtain a regression decision tree, and the degree of mutation of the mutagenic standard planting factor when the target modification method is used to modify the golden catalpa wood sample is determined based on the regression decision tree; an idealized characteristic evaluation radar chart is obtained by simulating and evaluating the standard modified three-dimensional model of the golden catalpa wood sample, and the accurate evaluation fluctuation range of each target characteristic evaluation item is limited and planned according to the degree of mutation; the idealized characteristic evaluation radar chart is adjusted based on the accurate evaluation fluctuation range to obtain the actual characteristic evaluation radar chart of the golden catalpa wood sample after modification and the modified characteristic level. The present invention can accurately analyze whether planting factors have an impact on the modification of Catalpa ovata and the extent of the impact, so that the impact on the variation of Catalpa ovata characteristics can be fully considered to conduct modification evaluation, thereby improving the evaluation accuracy and reliability of the modified characteristics of Catalpa ovata. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0053] Figure 1 The process of evaluating the characteristics and modification of Catalpa ovata wood based on planting analysis is shown. Figure 1 ;

[0054] Figure 2 The process of evaluating the characteristics and modification of Catalpa ovata wood based on planting analysis is shown. Figure 2 ;

[0055] Figure 3 The system framework diagram of a Catalpa ovata wood property and modification evaluation system based on planting analysis is shown. DETAILED DESCRIPTION

[0056] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0058] The first aspect of the present invention provides a method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis, such as Figure 1 As shown, the following steps are included:

[0059] S102: obtaining original internal and external characteristic signals of the wood sample of Catalpa chinensis, calculating the local signal trend of the original internal and external characteristic signals by envelope calculation to obtain internal and external characteristic point cloud fragments, calculating the factor correlation between each internal and external characteristic point cloud fragment and each planting factor in the historical planting system, and obtaining a set of associated planting factors that affect the internal and external characteristics of the wood sample of Catalpa chinensis in the historical planting system;

[0060] S104: Based on big data, multiple standard planting systems for Catalpa ovata are obtained, a first hotspot matrix of internal and external characteristic distribution of Catalpa ovata wood samples under each standard planting factor difference condition in each standard planting system for target modification method is constructed, and a second hotspot matrix of internal and external characteristic distribution of mutation is constructed, and the mutation probability value is calculated and analyzed by combining the first hotspot matrix and the second hotspot matrix to obtain a set of induced mutation standard planting factors;

[0061] S106: If the associated planting factor set contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, a regression decision analysis is performed on the difference of the wood characteristic index during modification through the termination planting interval variable of the mutagenic standard planting factor before modification to obtain a regression decision tree, and the degree of mutation of the mutagenic standard planting factor when the target modification method is used to modify the golden catalpa wood sample is determined based on the regression decision tree;

[0062] S108: By simulating and evaluating the standard modified three-dimensional model of the golden catalpa wood sample, an idealized characteristic evaluation radar chart is obtained, and the accurate evaluation fluctuation range of each target characteristic evaluation item is limited and planned according to the degree of variation. The idealized characteristic evaluation radar chart is adjusted based on the accurate evaluation fluctuation range to obtain the actual characteristic evaluation radar chart of the golden catalpa wood sample after modification and the modified characteristic level.

[0063] More specifically, the step S102 includes the following steps:

[0064] Obtain a sample of Catalpa ovata wood to be evaluated, and use an X-ray detector to perform an X-ray scan of the Catalpa ovata wood sample at a preset time sequence to obtain original internal and external characteristic signals of the Catalpa ovata wood sample at the preset time sequence;

[0065] Extracting the local maximum and the local minimum in the original internal and external characteristic signal, and performing signal interpolation processing based on the local maximum and the local minimum to construct the upper envelope and the lower envelope of the original internal and external characteristic signal;

[0066] Preset an envelope threshold interval, calculate the average values ​​of the upper envelope line and the lower envelope line to obtain an envelope mean value, and if the envelope mean value is within the envelope threshold interval, remove the local signal trend corresponding to the envelope mean value from the original internal and external characteristic signals to obtain new internal and external characteristic signals, repeat the above envelope operation and judgment steps to obtain the remaining new internal and external characteristic signals of the original internal and external characteristic signals and integrate them, and finally obtain N internal and external characteristic point cloud fragments of the golden silk catalpa wood sample;

[0067] Obtaining the planting log of the wood sample of Catalpa ovata, extracting the historical planting system of the wood sample of Catalpa ovata within a preset time period based on the planting log, and defining each system component in the historical planting system as a planting factor;

[0068] Based on the big data network, the benchmark internal and external feature point cloud generated when planting Catalpa chinensis wood under the historical planting system is obtained, and the factor correlation coefficient between each internal and external feature point cloud fragment and each planting factor is calculated according to the preset factor correlation critical coefficient of the benchmark internal and external feature point cloud, so as to obtain multiple factor correlation coefficients;

[0069] If the factor correlation coefficient is less than the preset factor correlation critical coefficient, the planting factor corresponding to the factor correlation coefficient is eliminated; if the factor correlation coefficient is greater than the preset factor correlation critical coefficient, the planting factor corresponding to the factor correlation coefficient is retained and marked as a correlated planting factor;

[0070] All the related planting factors were obtained and integrated to obtain a set of related planting factors that affected the internal and external characteristics of Catalpa ovata wood samples in the historical planting system.

[0071] It should be noted that the internal and external characteristics include external wood texture characteristics, external wood color characteristics, internal wood fiber density characteristics and internal wood fiber structure characteristics. The modification of Catalpa ovata wood may cause some of the above internal and external characteristics to change. For example, after chemical modification, its wood fiber density becomes denser. These internal and external characteristics are related to the planting factors when Catalpa ovata is planted. For example, its wood texture depends on the age of the tree and the growth environment of Catalpa ovata. Therefore, before analyzing whether the planting factors have an abnormal effect on the modification of Catalpa ovata, it is necessary to determine the planting factors that are highly correlated with the internal and external characteristics of Catalpa ovata wood before modification. This method first scans the Catalpa ovata wood sample with an X-ray detector. Compared with traditional feature extraction equipment, the X-ray detector can highly express the integrity and timing of the restored feature data points in the form of signals, which better ensures the accuracy of wood features. However, due to the complexity of some wood characteristics, there are certain translation errors in signal analysis, which leads to erroneous results in subsequent correlation calculations. Therefore, this method constructs the upper envelope and lower envelope of the original internal and external characteristic signals by extracting the local maximum and local minimum values ​​in the original internal and external characteristic signals, and then calculates the average values ​​of the upper envelope and the lower envelope to obtain the local signal trend of the original internal and external characteristic signals. A new signal is obtained by removing the local signal trend, so that the complex internal and external characteristic signals are decomposed into a set of intrinsic mode functions. These intrinsic mode functions represent the local oscillation characteristics of the signal and contain more high-frequency components, which effectively help analyze the local characteristics of the complex signal. The modal decomposition can make the processing of complex wood internal and external characteristic signals simpler and more accurate, reduce the feature operation steps, and improve the translation reliability of the feature signal into the feature point cloud.

[0072] It should be noted that the planting system includes the growth environment, growth rate, tree age, tree height, diameter at breast height, planting method, and the scale of impact of pests and diseases. Since the planting of golden catalpa wood samples will inevitably go through a planting system, this method determines the degree of correlation between the two by calculating the factor correlation coefficient between each extracted internal and external feature point cloud and the planting factor; among them, if the factor correlation coefficient is less than the preset factor correlation critical coefficient, it means that a certain planting factor in the historical planting system does not affect a certain internal and external feature, and there is no connection with the internal and external feature, so the planting factor corresponding to the factor correlation coefficient is eliminated; on the contrary, it means that a certain planting factor in the historical planting system causes a certain internal and external feature to undergo a phased change, and there is an inevitable correlation between the two, so the planting factor is retained and marked. This method can calculate the planting factors that are correlated with the internal and external characteristics of golden catalpa wood, which provides an accurate basis for determining whether the subsequent planting factors have a mutation effect on the modification of golden catalpa wood, and effectively improves the accuracy of golden catalpa evaluation under planting analysis.

[0073] More specifically, the step S104 includes the following steps:

[0074] Based on the big data network, several relevant planting cases of Catalpa ovata are obtained, and multiple standard planting systems of Catalpa ovata are extracted through the relevant planting cases, and the modification requirements of Catalpa ovata wood samples are obtained at the same time;

[0075] Obtaining a three-dimensional model of a wood sample of Catalpa ovata, constructing a hotspot base map of the wood sample of Catalpa ovata based on the three-dimensional model, and obtaining a target modification method of the wood sample of Catalpa ovata according to modification requirements;

[0076] Through the planting log, all internal and external modification feature point clouds of the target modification method under each standard planting factor difference condition in each standard planting system and the internal and external modification coordinates of each internal and external modification feature point cloud are obtained;

[0077] Plot all internal and external modification feature point clouds on the hotspot base map to generate an internal and external modification feature distribution hotspot map, and divide the internal and external modification feature distribution hotspot map into M sub-hotspot distributions based on the internal and external modification coordinates, which are defined as a first hotspot matrix;

[0078] Mark the mutated internal and external characteristic point clouds of the target modification method in each first hotspot matrix during the modification process of the golden catalpa wood sample, and obtain the mutated hotspot distribution of each first hotspot area, which is defined as the second hotspot matrix;

[0079] A Bayesian inference algorithm is introduced to calculate the hotspot matrix ratio of the second hotspot matrix to the first hotspot matrix, and the mutation hotspot matrix ratio is obtained. Based on the mutation hotspot matrix ratio, a probability distribution field of mutation hotspots generated during the modification process of the Catalpa chinensis wood sample is constructed by calculation in the Bayesian inference algorithm.

[0080] Based on the probability field, the probability that each standard planting factor in each standard planting system causes the target modification method to modify the internal and external characteristics of the Catalpa ovata wood sample to mutate is calculated to obtain a number of mutation probability values;

[0081] If the mutation probability value is greater than the preset mutation probability value, the standard planting factor corresponding to the mutation probability value is calibrated as the mutagenic standard planting factor to obtain a mutagenic standard planting factor set.

[0082] It should be noted that due to the different planting systems, some internal and external characteristics of Catalpa ovata wood have modification quality differences, which may cause local changes or mutations in Catalpa ovata wood due to modification. Therefore, it is necessary to determine the planting factors corresponding to the internal and external characteristics of the wood that may cause mutations. In this regard, this method is based on the target modification method. When the Catalpa ovata wood sample is in each standard planting system, all the internal and external modification feature point clouds and the internal and external modification coordinates of each internal and external modification feature point cloud are placed under each standard planting factor difference condition. A hotspot distribution map of the modification changes of internal and external characteristics is drawn when the Catalpa ovata wood sample is modified by the target modification method. In order to facilitate further calculations and reduce calculation errors and steps, it is decomposed into M sub-hotspot distributions. The internal and external modification feature distributions displayed by these sub-hotspot distributions will form a global hotspot matrix that expresses whether the modification is normal or not, that is, the first hotspot matrix; then at each first hotspot The matrix marks the mutated internal and external characteristic point clouds that mutate during the modification process of the target modification method on the golden silk catalpa wood sample. The expression of the mutated internal and external characteristic point clouds in the global hotspot matrix reflects the random distribution of the internal and external characteristics that mutate under the modification, that is, the second hotspot matrix; therefore, based on the random distribution characteristics of the second hotspot matrix in the first hotspot matrix, a probability distribution field expressing the relative probability of the two can be calculated in the Bayesian inference algorithm, so as to visualize the probability that each standard planting factor in each standard planting system causes the target modification method to mutate the internal and external characteristics of the golden silk catalpa wood sample. Among them, if the mutation probability value is greater than the preset mutation probability value, it means that the internal and external characteristics of the wood produced under the planting factor have a greater probability of characteristic mutation during the modification process, and the mutation is an evaluation basis for the subsequent characteristics of the wood after the golden silk catalpa modification, so the standard planting factor corresponding to the mutation probability value is calibrated as the mutation standard planting factor. This method can accurately calculate and locate the mutagenic planting factors corresponding to the internal and external characteristics of the wood that may cause mutations during the modification of Catalpa ovata wood, and can provide an accurate evaluation and analysis indicator for the evaluation of the characteristics of Catalpa ovata after modification, so as to fully consider the influence of Catalpa ovata planting factors on the accuracy of its evaluation.

[0083] More specifically, the step S106 includes the following steps:

[0084] If the associated planting factor set that affects the internal and external characteristics of the Catalpa ovata wood sample in the historical planting system contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, the termination planting interval variable of the mutagenic standard planting factor in the preset historical time period before the Catalpa ovata wood sample is modified by the target modification method through the planting log;

[0085] Obtaining the wood property index of the golden catalpa wood sample within a preset historical time period before the target modification method is used to modify the golden catalpa wood sample, which is marked as the starting wood property index, and obtaining the wood property index of the golden catalpa wood sample after the target modification method is used to modify the golden catalpa wood sample, which is marked as the ending wood property index;

[0086] Calculating the index difference between the termination wood property index and the initial wood property index to obtain a wood property index difference, and performing regression analysis on the wood property index difference through the termination planting interval variable;

[0087] During the regression analysis, the mean square error algorithm is introduced to calculate the mean square error of each variable in the termination planting interval variable, and only the termination planting interval variable corresponding to the maximum mean square error is extracted and defined as the optimal planting interval variable. The splitting compliance point of the optimal planting interval variable is created according to the mean square error.

[0088] A threshold value of the number of sample nodes is preset, a regression root node of the wood characteristic index difference is constructed and set as the starting node, and a split operation of the branch subset is performed on the optimal planting interval variable starting from the starting node based on the splitting follow point to obtain the current number of sample nodes of each branch subset;

[0089] If the current number of sample nodes exceeds the sample node number threshold, the splitting operation of the branch subset is stopped, and the above branch subset splitting operation and the determination of the current number of sample nodes are repeated, and finally a regression decision tree of the optimal planting interval variable traversal wood characteristic index difference is obtained;

[0090] All leaf nodes displayed by the regression decision tree are stripped out to obtain the leaf node pattern and the leaf node value of each leaf node. The degree of mutation of the standard planting factor for the target modification method when modifying the golden silk wood sample is determined according to the leaf node pattern and the leaf node value.

[0091] It should be noted that if the associated planting factor set that affects the internal and external characteristics of the Catalpa chinensis wood samples in the historical planting system contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, it means that the internal and external characteristics of the Catalpa chinensis wood samples under the historical planting system may undergo local mutations during the modification process of the target modification method, that is, the actual modification deviates from the ideal modification. If the actual characteristics of the modified Catalpa chinensis wood are to be accurately evaluated, it is necessary to further clarify the degree of influence of the mutagenic planting factor on the characteristics of the modified wood. Since the planting factors have changes in the planting interval, for example, the age of the golden catalpa will gradually increase or the wood fiber will gradually become denser with age, this method is based on the difference in wood characteristic index between the terminal wood characteristic index and the initial wood characteristic index of the golden catalpa wood sample after the target modification method, to regress the terminal planting interval variable of the mutagenic standard planting factor in the preset historical time period before the target modification method is used to modify the golden catalpa wood sample, so that the degree of influence of the planting interval variable of the mutagenic standard planting factor on the characteristic variable of the wood characteristics during modification can be regressed. For the regression analysis process, this method uses the splitting compliance point created by the optimal planting interval variable of the terminal planting interval variable as the splitting standard, and starts to split the branch subset of the optimal planting interval variable from the regression root node of the wood characteristic index difference, which can make the characteristic variable of the wood characteristics during modification more refined and regressed to the corresponding planting interval variable, thereby making the calculation of the degree of mutation of the mutagenic standard planting factor for the golden catalpa wood sample modified by the target modification method more accurate and reliable. This method can accurately calculate the degree of mutation of the standard planting factor for the target modification method when modifying the Catalpa ovata wood sample. The degree of mutation can make the evaluation results of Catalpa ovata modification under the influence of planting factors more credible. Compared with the traditional method that does not consider the mutation conditions of the planting factors, the evaluation accuracy and reliability of the modified characteristics of Catalpa ovata are improved, which is helpful to the subsequent modification stability of Catalpa ovata.

[0092] More specifically, the step S108 is as follows: Figure 2 As shown, the specific steps include:

[0093] S202: Obtaining a benchmark modification process parameter of a target modification method, performing standardized modification based on the benchmark modification process parameter, obtaining a standard modified three-dimensional model of a Catalpa ovata wood sample, testing the standard modified three-dimensional model through a property simulation, and performing an evaluation of a target property evaluation item of the Catalpa ovata wood sample based on a property evaluation criterion, to obtain an idealized property evaluation radar chart;

[0094] S204: extracting the evaluation fluctuation range of each target characteristic evaluation item for structural mutation caused by modification of Catalpa ovata wood based on the evaluation mechanism, performing mutation processing on the standard modified three-dimensional model based on the degree of mutation, so as to construct a mutation modification three-dimensional model of the target modification method for the modified Catalpa ovata wood sample by the mutagenic standard planting factor;

[0095] S206: registering the abnormal modified three-dimensional model to the standard modified three-dimensional model, calculating the registration misalignment degree between the abnormal modified three-dimensional model and the standard modified three-dimensional model, and obtaining the registration misalignment rate;

[0096] S208: Preset an evaluation fluctuation range according to the registration misalignment rate, and limit the evaluation fluctuation range of each target characteristic evaluation item based on the evaluation fluctuation range planning, so as to obtain an accurate evaluation fluctuation range of each target characteristic evaluation item when the modified structure of golden catalpa wood has a degree of abnormality;

[0097] S210: The idealized characteristic evaluation radar chart is adjusted by accurately evaluating the fluctuation amplitude, and finally an actual characteristic evaluation radar chart of the modified Catalpa ovata wood sample is obtained, and the area value of the radar region that does not overlap between the actual characteristic evaluation radar chart and the idealized characteristic evaluation radar chart is obtained, and the modified characteristic level of the actual characteristic of the modified Catalpa ovata wood sample compared with the idealized characteristic is determined according to the radar region area value.

[0098] It should be noted that when the mutation degree of the standard planting factor for the target modification method is determined, the wood sample can be modified and its characteristics can be tested. Since the mutation degree is generated during the standard modification process of the wood sample, it is necessary to first build a standard modified three-dimensional model of the wood sample based on the benchmark modification process parameters of the target modification method, and then perform mutation processing on the standard modified three-dimensional model according to the mutation degree, so as to build a mutation modification three-dimensional model of the standard planting factor for the target modification method. From the evaluation mechanism, it can be known that the evaluation of each target characteristic evaluation item for the modification of golden catalpa wood will produce a fluctuation range with the structural mutation. For example, if the golden catalpa wood is modified and produces a one-centimeter mutation, its characteristic evaluation result will fluctuate by a corresponding one or two points. There is a modification difference in structural mutation between the mutated modified 3D model and the standard modified 3D model. Therefore, this method is based on the evaluation fluctuation range preset by the registration misalignment rate between the mutated modified 3D model and the standard modified 3D model to perform The one-step planning limits the accurate assessment fluctuation range of each target characteristic evaluation item when the modified structure of Catalpa ovata wood undergoes a mutation. The accurate assessment fluctuation range is to adjust the characteristic evaluation of the idealized modified Catalpa ovata wood sample to the actual characteristic evaluation of the modified change under the condition of the mutation range, so as to achieve the effect of accurately updating the modified characteristic evaluation of Catalpa ovata wood based on the influence of planting factors in planting analysis, save the real-time adjustment calculation steps of the modified characteristic evaluation results based on the planting analysis results in the traditional method, and improve the evaluation efficiency and the accuracy of the evaluation results.

[0099] It should be noted that, in addition, the target characteristic evaluation items include mechanical strength, corrosion resistance, weather resistance and dimensional stability. In order to more intuitively and completely display the characteristic evaluation results and avoid the adjustment errors and adjustment errors of the target characteristic evaluation items due to the accurate assessment of the fluctuation range, this method centrally draws the evaluation results of all target characteristic evaluation items in the form of a radar chart, so that the adjustment of the accurate assessment of the fluctuation range is faster and more unified, further optimizes the evaluation rate, and improves the accuracy of the evaluation results; at the same time, the actual characteristics of the modified golden silk catalpa wood sample compared with the idealized characteristics are displayed with non-overlapping radar area values. The non-overlapping radar area is the evaluation gap between the actual characteristic evaluation results and the idealized characteristic evaluation results. According to the modified characteristic level, the actual modification performance and modification potential of golden silk catalpa can be known, which can provide an improvement basis for the modification of golden silk catalpa.

[0100] More specifically, in the step S108, the benchmark modification process parameters of the target modification method are obtained, standardized modification is performed based on the benchmark modification process parameters, a standard modified three-dimensional model of the golden silk catalpa wood sample is obtained, the standard modified three-dimensional model is tested by property simulation, and the target property evaluation items of the golden silk catalpa wood sample are evaluated based on the property evaluation criteria to obtain an idealized property evaluation radar chart, which specifically includes the following steps:

[0101] Obtaining a preset modification process flow plan of the target modification method, and obtaining the benchmark modification process parameters of the target modification method for the standardized modification of the Catalpa ovata wood sample through the preset modification process flow plan;

[0102] Based on the benchmark modification process parameters, a standardized modification of the target modification method is performed on the wood sample of Catalpa ovata in the model simulation software to generate a standard modified three-dimensional model of the wood sample of Catalpa ovata;

[0103] A series of modified test signals are written and loaded according to the benchmark modified process parameters, and the series of modified test signals are injected into the standard modified three-dimensional model of the golden silk wood sample through the model simulation software to perform a characteristic simulation test of the golden silk wood sample after standard modification;

[0104] Introduce a deep belief algorithm to obtain target characteristic evaluation items of golden catalpa wood samples according to modification requirements, obtain characteristic evaluation criteria of golden catalpa wood through a big data network, and obtain an evaluation mechanism for each target characteristic evaluation item based on the characteristic evaluation criteria;

[0105] An evaluation model is constructed in the deep belief algorithm based on the evaluation mechanism of each target characteristic evaluation item. The evaluation model is used to evaluate the target characteristic evaluation items of the standard modified three-dimensional model during the characteristic test process, and the characteristic evaluation results of each target characteristic evaluation item of the standard modified Catalpa chinensis wood sample are obtained, which are defined as idealized characteristic evaluation results.

[0106] A radar chart framework of the evaluation mechanism is constructed, and the idealized characteristic evaluation result of each target characteristic evaluation item is fitted into the radar chart framework to obtain an idealized characteristic evaluation radar chart.

[0107] It should be noted that, since the actual characteristic evaluation of the modified changes under the condition of the variation amplitude is based on the adjustment of the characteristic evaluation of the idealized modification by accurately evaluating the fluctuation amplitude, this method can be used to draw an idealized evaluation benchmark under the standard modification of the golden silk catalpa wood sample for the subsequent adjustment calculation of the actual evaluation results based on the degree of variation, aiming to ensure the rationality of the evaluation adjustment when the golden silk catalpa standard is modified and the modified variation is modified, which greatly improves the accuracy and credibility of the evaluation results of the modified characteristics adjusted based on the degree of variation. In addition, the introduced radar chart architecture can realize the visualization of the evaluation results of the target characteristic evaluation items, making the adjustment of the evaluation results of each target characteristic evaluation item more accurate and unified, reducing the adjustment error of the accurate evaluation of the fluctuation amplitude, and having high reliability.

[0108] In addition, the method for evaluating the characteristics and modification of Catalpa ovata wood based on planting analysis also includes the following steps:

[0109] Obtaining the use requirements of Catalpa ovata, and extracting the modified characteristic score required to be achieved by using Catalpa ovata through the use requirements, which is defined as the expected modified characteristic score value;

[0110] Based on the planting log, the target modification method is used to obtain the actual modification characteristic scores of Catalpa ovata wood under different planting phenotypic characteristics, and the actual planting phenotypic characteristics of different Catalpa ovata wood varieties at different planting times are simultaneously obtained based on big data;

[0111] Presetting an allowable drift threshold interval of the modified characteristic score, calculating the difference between each actual modified characteristic score value and the expected modified characteristic score value one by one, and obtaining a plurality of score deviation values;

[0112] If the score deviation value is within the allowable drift threshold range, a graph node of the actual modified characteristic score is constructed based on the score deviation value, and the similarity between each graph node is calculated to obtain a similarity matrix of the actual modified characteristic scores of the characteristics of Catalpa ovata at different planting times;

[0113] A spectral clustering algorithm is introduced, and the actual planting phenotypic characteristics are decomposed and clustered by performing the decomposition and clustering of the similarity matrix in the spectral clustering algorithm, and finally the actual planting phenotypic characteristics of the target modification method for different golden catalpa wood varieties at different planting times are obtained, and the actual modification characteristics are scored within the allowable range, and are marked as qualified actual planting phenotypic characteristics;

[0114] Acquire the actual planting phenotypic characteristics of each Catalpa chinensis wood variety in the Catalpa chinensis planting area, and construct a comparison library of the planting phenotypic characteristics of Catalpa chinensis based on one or more of the qualified actual planting phenotypic characteristics;

[0115] If the degree of agreement between the actual planting phenotypic characteristics and any qualified actual planting phenotypic characteristics in the planting phenotypic characteristics comparison library is greater than the preset agreement, the planting area where the actual planting phenotypic characteristics are located is marked and defined as the target golden catalpa planting area, and a distribution map of the target golden catalpa planting area is generated;

[0116] The target Catalpa ovata planting area distribution map is uploaded to the Catalpa ovata collection equipment terminal to quickly locate and collect Catalpa ovata wood varieties that meet the use requirements.

[0117] It should be noted that for different usage scenarios or requirements of Catalpa ovata, there are corresponding regulations on the modified characteristic scoring standards to meet the usage requirements. However, the traditional characteristic screening method has a lot of calculations and steps for the actual planting phenotypic characteristics screening of different Catalpa ovata varieties at different planting times, so there are large errors, which makes the actual modified characteristic scores of the actual planting phenotypic characteristics screened out under the target modification method unable to meet the expected modified characteristic scores, resulting in errors in the comparison and collection of Catalpa ovata variety characteristics. In this regard, the present method can use the actual modification characteristic score whose score deviation value is within the allowable drift threshold interval as the clustering benchmark through clustering, and perform clustering operations on the actual planting phenotypic characteristics of different golden catalpa varieties at different planting times to meet the use requirements, so as to obtain qualified actual planting phenotypic characteristics that meet the use requirements of golden catalpa, and then perform feature comparison on each golden catalpa variety in the golden catalpa planting area based on these qualified actual planting phenotypic characteristics, so as to quickly obtain the location of the golden catalpa varieties that can meet the use requirements in the current golden catalpa planting area, and provide accurate and reliable navigation and positioning data for the staff to quickly obtain modified golden catalpa wood samples, save the collection time of modified golden catalpa wood samples, improve the collection efficiency, and at the same time improve the accuracy of golden catalpa wood modification and sample collection, avoid the tedious steps of traditional manual feature analysis, estimation and screening one by one, and meet the modification requirements of golden catalpa to the greatest extent, with high economic benefits.

[0118] The second aspect of the present invention provides a system for evaluating the characteristics and modification of Catalpa ovata wood based on planting analysis, such as Figure 3 As shown, the system for evaluating the characteristics and modification of Catalpa ovata wood includes a memory 31 and a processor 32. The memory 31 stores a program for evaluating the characteristics and modification of Catalpa ovata wood based on planting analysis. When the program for evaluating the characteristics and modification of Catalpa ovata wood is executed by the processor 32, any one of the steps of the method for evaluating the characteristics and modification of Catalpa ovata wood is implemented.

[0119] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis, characterized in that: The following steps are involved: S102: obtaining original internal and external characteristic signals of the wood sample of Catalpa chinensis, calculating the local signal trend of the original internal and external characteristic signals by envelope calculation to obtain internal and external characteristic point cloud fragments, calculating the factor correlation between each internal and external characteristic point cloud fragment and each planting factor in the historical planting system, and obtaining a set of associated planting factors that affect the internal and external characteristics of the wood sample of Catalpa chinensis in the historical planting system; S104: Based on big data, multiple standard planting systems for Catalpa ovata are obtained, a first hotspot matrix of internal and external characteristic distribution of Catalpa ovata wood samples under each standard planting factor difference condition in each standard planting system for target modification method is constructed, and a second hotspot matrix of internal and external characteristic distribution of mutation is constructed, and the mutation probability value is calculated and analyzed by combining the first hotspot matrix and the second hotspot matrix to obtain a set of induced mutation standard planting factors; S106: If the associated planting factor set contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, a regression decision analysis is performed on the difference of the wood characteristic index during modification through the termination planting interval variable of the mutagenic standard planting factor before modification to obtain a regression decision tree, and the degree of mutation of the mutagenic standard planting factor when the target modification method is used to modify the golden catalpa wood sample is determined based on the regression decision tree; S108: By simulating and evaluating the standard modified three-dimensional model of the golden catalpa wood sample, an idealized characteristic evaluation radar chart is obtained, and the accurate evaluation fluctuation range of each target characteristic evaluation item is limited and planned according to the degree of variation. The idealized characteristic evaluation radar chart is adjusted based on the accurate evaluation fluctuation range to obtain the actual characteristic evaluation radar chart of the golden catalpa wood sample after modification and the modified characteristic level.

2. The method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis according to claim 1, characterized in that: The step S102 specifically includes the following steps: Obtain a sample of Catalpa ovata wood to be evaluated, and use an X-ray detector to perform an X-ray scan of the Catalpa ovata wood sample at a preset time sequence to obtain original internal and external characteristic signals of the Catalpa ovata wood sample at the preset time sequence; Extracting the local maximum and the local minimum in the original internal and external characteristic signal, and performing signal interpolation processing based on the local maximum and the local minimum to construct the upper envelope and the lower envelope of the original internal and external characteristic signal; Preset an envelope threshold interval, calculate the average values ​​of the upper envelope line and the lower envelope line to obtain an envelope mean value, and if the envelope mean value is within the envelope threshold interval, remove the local signal trend corresponding to the envelope mean value from the original internal and external characteristic signals to obtain new internal and external characteristic signals, repeat the above envelope operation and judgment steps to obtain the remaining new internal and external characteristic signals of the original internal and external characteristic signals and integrate them, and finally obtain N internal and external characteristic point cloud fragments of the golden silk catalpa wood sample; Obtaining the planting log of the wood sample of Catalpa ovata, extracting the historical planting system of the wood sample of Catalpa ovata within a preset time period based on the planting log, and defining each system component in the historical planting system as a planting factor; Based on the big data network, the benchmark internal and external feature point cloud generated when planting Catalpa ovata wood under the historical planting system is obtained, and the factor correlation coefficient between each internal and external feature point cloud fragment and each planting factor is calculated according to the preset factor correlation critical coefficient of the benchmark internal and external feature point cloud, so as to obtain multiple factor correlation coefficients; If the factor correlation coefficient is less than the preset factor correlation critical coefficient, the planting factor corresponding to the factor correlation coefficient is eliminated; if the factor correlation coefficient is greater than the preset factor correlation critical coefficient, the planting factor corresponding to the factor correlation coefficient is retained and marked as a correlated planting factor; All the related planting factors were obtained and integrated to obtain a set of related planting factors that affected the internal and external characteristics of Catalpa ovata wood samples in the historical planting system.

3. The method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis according to claim 1, characterized in that: The step S104 specifically includes the following steps: Based on the big data network, several relevant planting cases of Catalpa ovata are obtained, and multiple standard planting systems of Catalpa ovata are extracted through the relevant planting cases, and the modification requirements of Catalpa ovata wood samples are obtained at the same time; Obtaining a three-dimensional model of a wood sample of Catalpa ovata, constructing a hotspot base map of the wood sample of Catalpa ovata based on the three-dimensional model, and obtaining a target modification method of the wood sample of Catalpa ovata according to modification requirements; Through the planting log, all internal and external modification feature point clouds of the target modification method under each standard planting factor difference condition in each standard planting system and the internal and external modification coordinates of each internal and external modification feature point cloud are obtained; Plot all internal and external modification feature point clouds on the hotspot base map to generate an internal and external modification feature distribution hotspot map, and divide the internal and external modification feature distribution hotspot map into M sub-hotspot distributions based on the internal and external modification coordinates, which are defined as a first hotspot matrix; Mark the mutated internal and external characteristic point clouds of the target modification method in each first hotspot matrix during the modification process of the golden catalpa wood sample, and obtain the mutated hotspot distribution of each first hotspot area, which is defined as the second hotspot matrix; A Bayesian inference algorithm is introduced to calculate the hotspot matrix ratio of the second hotspot matrix to the first hotspot matrix, and the mutation hotspot matrix ratio is obtained. Based on the mutation hotspot matrix ratio, a probability distribution field of mutation hotspots generated during the modification process of the Catalpa chinensis wood sample is constructed by calculation in the Bayesian inference algorithm. Based on the probability field, the probability that each standard planting factor in each standard planting system causes the target modification method to modify the internal and external characteristics of the Catalpa ovata wood sample to mutate is calculated to obtain a number of mutation probability values; If the mutation probability value is greater than the preset mutation probability value, the standard planting factor corresponding to the mutation probability value is calibrated as the mutagenic standard planting factor to obtain a mutagenic standard planting factor set.

4. The method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis according to claim 1, characterized in that: The step S106 specifically includes the following steps: If the associated planting factor set that affects the internal and external characteristics of the Catalpa ovata wood sample in the historical planting system contains at least one or more mutagenic standard planting factors in the mutagenic standard planting factor set, the termination planting interval variable of the mutagenic standard planting factor in the preset historical time period before the Catalpa ovata wood sample is modified by the target modification method through the planting log; Obtaining the wood property index of the golden catalpa wood sample within a preset historical time period before the target modification method is used to modify the golden catalpa wood sample, which is marked as the starting wood property index, and obtaining the wood property index of the golden catalpa wood sample after the target modification method is used to modify the golden catalpa wood sample, which is marked as the ending wood property index; Calculating the index difference between the termination wood property index and the initial wood property index to obtain a wood property index difference, and performing regression analysis on the wood property index difference through the termination planting interval variable; During the regression analysis, the mean square error algorithm is introduced to calculate the mean square error of each variable in the termination planting interval variable, and only the termination planting interval variable corresponding to the maximum mean square error is extracted and defined as the optimal planting interval variable. The splitting compliance point of the optimal planting interval variable is created according to the mean square error. A threshold value of the number of sample nodes is preset, a regression root node of the wood characteristic index difference is constructed and set as the starting node, and a split operation of the branch subset is performed on the optimal planting interval variable starting from the starting node based on the splitting follow point to obtain the current number of sample nodes of each branch subset; If the current number of sample nodes exceeds the sample node number threshold, the splitting operation of the branch subset is stopped, and the above branch subset splitting operation and the determination of the current number of sample nodes are repeated, and finally a regression decision tree of the optimal planting interval variable traversal wood characteristic index difference is obtained; All leaf nodes displayed by the regression decision tree are stripped out to obtain the leaf node pattern and the leaf node value of each leaf node. The degree of mutation of the standard planting factor for the target modification method when modifying the golden silk wood sample is determined according to the leaf node pattern and the leaf node value.

5. The method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis according to claim 1, characterized in that: The step S108 specifically includes the following steps: Obtaining the benchmark modification process parameters of the target modification method, performing standardized modification based on the benchmark modification process parameters, obtaining a standard modified three-dimensional model of the golden silk catalpa wood sample, testing the standard modified three-dimensional model through property simulation, and performing the evaluation of the target property evaluation items of the golden silk catalpa wood sample based on the property evaluation criteria, to obtain an idealized property evaluation radar chart; Extract the evaluation fluctuation range of each target characteristic evaluation item for structural mutation caused by modification of Catalpa ovata wood based on the evaluation mechanism, perform mutation processing on the standard modified three-dimensional model based on the degree of mutation, so as to construct a mutation modification three-dimensional model of the target modification method for the modified Catalpa ovata wood sample by the mutagenic standard planting factor; Registering the mutated modified three-dimensional model to the standard modified three-dimensional model, calculating the registration misalignment degree between the mutated modified three-dimensional model and the standard modified three-dimensional model, and obtaining the registration misalignment rate; Preset the evaluation fluctuation range according to the registration misalignment rate, and limit the evaluation fluctuation range of each target characteristic evaluation item based on the evaluation fluctuation range planning, so as to obtain the accurate evaluation fluctuation range of each target characteristic evaluation item when the modified structure of golden catalpa wood has a degree of abnormality; The idealized characteristic evaluation radar chart is adjusted by accurately evaluating the fluctuation amplitude, and finally the actual characteristic evaluation radar chart of the modified Catalpa ovata wood sample is obtained; the area value of the radar region that does not overlap between the actual characteristic evaluation radar chart and the idealized characteristic evaluation radar chart is obtained, and the modified characteristic level of the actual characteristics of the modified Catalpa ovata wood sample compared with the idealized characteristics is determined according to the radar region area value.

6. The method for evaluating the properties and modification of Catalpa ovata wood based on planting analysis according to claim 5, characterized in that: In the step S108, the benchmark modification process parameters of the target modification method are obtained, standardized modification is performed based on the benchmark modification process parameters, a standard modified three-dimensional model of the Catalpa ovata wood sample is obtained, the standard modified three-dimensional model is tested by property simulation, and the target property evaluation items of the Catalpa ovata wood sample are evaluated based on the property evaluation criteria to obtain an idealized property evaluation radar chart, which specifically includes the following steps: Obtaining a preset modification process flow plan of the target modification method, and obtaining the benchmark modification process parameters of the target modification method for the standardized modification of the Catalpa ovata wood sample through the preset modification process flow plan; Based on the benchmark modification process parameters, a standardized modification of the target modification method is performed on the wood sample of Catalpa ovata in the model simulation software to generate a standard modified three-dimensional model of the wood sample of Catalpa ovata; A series of modified test signals are written and loaded according to the benchmark modified process parameters, and the series of modified test signals are injected into the standard modified three-dimensional model of the golden silk wood sample through the model simulation software to perform a characteristic simulation test of the golden silk wood sample after standard modification; Introduce a deep belief algorithm to obtain target characteristic evaluation items of Catalpa ovata wood samples according to modification requirements, obtain the characteristic evaluation criteria of Catalpa ovata wood through a big data network, and obtain the evaluation mechanism of each target characteristic evaluation item based on the characteristic evaluation criteria; An evaluation model is constructed in the deep belief algorithm based on the evaluation mechanism of each target characteristic evaluation item. The evaluation model is used to evaluate the target characteristic evaluation items of the standard modified three-dimensional model during the characteristic test process, and the characteristic evaluation results of each target characteristic evaluation item of the standard modified Catalpa chinensis wood sample are obtained, which are defined as idealized characteristic evaluation results. A radar chart framework of the evaluation mechanism is constructed, and the idealized characteristic evaluation result of each target characteristic evaluation item is fitted into the radar chart framework to obtain an idealized characteristic evaluation radar chart.

7. A system for evaluating the characteristics and modification of Catalpa ovata wood based on planting analysis, characterized in that: The system for evaluating the characteristics and modifications of Catalpa ovata wood includes a memory and a processor. The memory stores a program for evaluating the characteristics and modifications of Catalpa ovata wood based on planting analysis. When the program for evaluating the characteristics and modifications of Catalpa ovata wood is executed by the processor, the steps of the method for evaluating the characteristics and modifications of Catalpa ovata wood as described in any one of claims 1 to 6 are implemented.

Images