A method and system for evaluating the risk of brittle failure of wood components under wet and cold conditions

Abstract

The application relates to a wood member brittle failure risk assessment method and system under a wet and cold condition. First, environmental parameters of a wood member sample in different wet and cold environments are collected in real time. Then, the wood member sample is subjected to mechanical testing to obtain brittle characteristic parameters in the stress process. Meanwhile, AE signals are collected in real time in the mechanical testing process under different wet and cold environments to obtain signal characteristic parameters of the wood member sample. Subsequently, the obtained environmental, brittle and signal characteristic parameters are processed and a data set is constructed to form a prediction data set. Finally, data in the prediction data set is input into a wood member brittle failure risk assessment model which has been trained, so that a probability value of brittle failure of the wood member in a future preset time period is obtained, thereby realizing accurate assessment of the brittle failure risk of the wood member under a wet and cold environment.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence, and in particular relates to a method and system for assessing the risk of brittle failure of wooden components under wet and cold conditions. Background Technology

[0002] Timber components refer to various parts of buildings or other structures made from wood, widely used in construction, furniture, bridges, and other fields. Performance testing of timber components mainly covers static load, dynamic load, and rack load tests. Static load tests its static load-bearing limit, dynamic load tests its stability during handling, and rack load tests its load-bearing capacity during storage, thus ensuring the safety and reliability of timber components. Traditional timber component design and quality assessment methods are mostly based on conventional environmental conditions, failing to fully consider the special effects of humid and cold environments on its performance. Existing timber component testing technologies mainly focus on static physical performance tests or simple mechanical strength tests, making it difficult to comprehensively reflect the dynamic performance changes of timber components during actual use, especially under complex humid and cold environments and stress conditions, and failing to accurately assess the risk of brittle failure of timber components in humid and cold environments. Summary of the Invention

[0003] Therefore, it is necessary to provide a method and system for assessing the risk of brittle failure of wooden components under humid and cold conditions, which can accurately evaluate the risk of brittle failure of wooden components under humid and cold conditions, in order to address the above-mentioned technical problems.

[0004] Firstly, this application provides a method for assessing the risk of brittle failure of wooden components under wet and cold conditions, including:

[0005] Environmental parameters of the wooden component samples under different humid and cold environments are collected in real time. The environmental parameters include at least one of different temperatures, relative humidity and air velocity.

[0006] Mechanical tests were conducted on wooden component samples to obtain brittle characteristic parameters during the stress process; brittle characteristic parameters include physical property parameters and mechanical property parameters.

[0007] The AE signal of the wooden component is acquired in real time during the mechanical testing process under different humid and cold environments, and the signal characteristic parameters of the wooden component sample are obtained. The signal characteristic parameters include at least one of the following: ring count, energy count, peak frequency, and signal duration.

[0008] The obtained environmental parameters, fragile characteristic parameters, and signal characteristic parameters are processed and a dataset is constructed to obtain the prediction dataset.

[0009] By inputting the predicted dataset into the trained brittle failure risk assessment model for wooden components, the probability value of brittle failure of wooden components within a preset time period is obtained.

[0010] In one embodiment, a mechanical test is performed on a wooden component sample to obtain brittle characteristic parameters during the stress process, including:

[0011] The physical property parameters of the wooden component samples were obtained based on their moisture content, density, bending strength, and modulus of elasticity.

[0012] The mechanical performance parameters of the wooden component samples were obtained by performing dynamic loading simulations on the sample, including the load-bearing time period, maximum load weight, and center of gravity offset.

[0013] The physical and mechanical property parameters were calculated using the following formulas to obtain the brittle characteristic parameters of each wooden component sample:

[0014]

[0015] Where S represents the brittle characteristic parameters of the wooden component sample; ω2, ω3, ω4, ω 5i ω6, ω7, and ω8 represent the weighting coefficients for moisture content, density, bending strength, modulus of elasticity, the i-th type of wood, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; MC0, ρ0, σ0, E0, W0, F0, and G0 represent the reference values ​​for moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; MC, ρ, σ, E, W, F, and G represent the moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset of the wood component sample, respectively; ΔMC, Δρ, Δσ, ΔE, ΔW, ΔF, and ΔG represent the preset deviation thresholds for moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; n represents the total number of wood types; I(X i ) represents the indicator function for the type of wood. If the wood type in the sample is the i-th type, then I(X) i =1, otherwise 0.

[0016] The calculated brittle characteristic parameters of each wooden component sample are standardized to obtain a standardized set of brittle characteristic parameters.

[0017] In one embodiment, the AE signal of the wooden component is acquired in real time during the mechanical testing process under different humid and cold environments to obtain the signal characteristic parameters of the wooden component sample, including:

[0018] Based on the stress conditions of the pretreated wooden component samples in actual use, a variety of mechanical testing schemes were designed; the mechanical testing schemes include different loading rates, load levels, loading methods and loading paths.

[0019] Each mechanical test scheme is tested repeatedly under preset humid and cold environmental conditions to obtain the preset test scheme.

[0020] The wooden component samples were subjected to mechanical loading according to the preset test plan, and the AE signal was collected in real time to obtain the signal parameters of the wooden component samples.

[0021] The acquired AE signal is processed offline using a variety of signal processing methods based on the signal parameters to obtain the final signal parameters. These signal processing methods include filtering, envelope analysis, and wavelet transform.

[0022] Key features are extracted based on the final signal parameters to obtain the signal feature parameters of the wooden component sample. The signal feature parameters include at least one of the following: ring count, energy count, peak frequency, and signal duration. The ring count refers to the number of times the signal exceeds a set threshold. The energy count is the quantification of the signal energy. The peak frequency is the highest frequency in the signal spectrum. The signal duration indicates the duration of the acoustic emission event.

[0023] In one embodiment, after obtaining the signal characteristic parameters of the wooden component sample, the method further includes:

[0024] Abnormal or erroneous data are removed based on the collected signal feature parameters to obtain the processed signal feature parameters.

[0025] Based on the processed signal characteristic parameters and the real-time recorded force and displacement data, the stress-strain curve of the wooden component sample is plotted.

[0026] Based on the obtained stress-strain curves, the peak strength point, residual strength point, and elastic modulus of the elastic deformation segment of the curves are determined. Using the peak strength point as the key reference point, a brittleness risk analysis diagram of the wooden component sample is drawn.

[0027] The ideal brittle line is obtained by dividing the brittle risk analysis diagram into straight lines perpendicular to the strain axis and intersecting the peak strength point.

[0028] Based on the brittleness risk analysis diagram, a straight line perpendicular to the stress axis and intersecting the peak strength point is drawn to obtain the predicted brittleness line.

[0029] Based on the brittleness risk analysis diagram, a straight line passing through the peak strength point and with a slope equal to the opposite of the elastic modulus is drawn to obtain the brittleness boundary line.

[0030] Based on the ideal brittleness line, the predicted brittleness line, and the brittleness boundary line, the post-peak strain curve segment in the brittleness risk analysis diagram is used to determine the brittle region.

[0031] Among them, when the post-peak strain curve segment is located between the predicted brittleness line and the brittleness boundary line, the brittle region is a small brittle region.

[0032] When the post-peak strain curve segment lies between the ideal brittle line and the brittle boundary line, the brittle region is a highly brittle region.

[0033] The brittleness index of the wooden component sample was obtained by calculating the brittleness index using formulas based on the small and large brittleness regions.

[0034] In one embodiment, the brittleness index of the wooden component sample is calculated using formulas based on the small brittleness region and the large brittleness region, including:

[0035] When the strain curve segment after the peak is located in the small brittle region:

[0036]

[0037] When the strain curve segment after the peak is located in the brittle region:

[0038]

[0039] Where H represents the brittleness index; K represents the preset brittleness index corresponding to the brittleness boundary; N represents the number of sample points selected on the post-peak strain curve; and ε i and σ i Let ε represent the strain value and stress value of the i-th sample point, respectively. c and σ c These represent the strain and stress values ​​at the peak strength point, respectively, and E represents the elastic modulus.

[0040] In one embodiment, data from the prediction dataset is input into a trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden components within a preset time period in the future, including:

[0041] A dataset is constructed from the brittleness index calculated by the standardized brittleness characteristic parameters and signal characteristic parameters of the environmental parameters and brittleness characteristic parameters to obtain the prediction dataset.

[0042] The weight values ​​of different types of data that cause brittle failure in wooden component samples are calculated by analyzing the data in the prediction dataset.

[0043] The weight values ​​of different types of data are input into the trained brittle failure risk assessment model of wooden components to obtain the probability value of brittle failure of wooden component samples within a preset time period in the future; the risk assessment model includes at least one of support vector machine, random forest and neural network.

[0044] Use the following formula to calculate the weight values ​​for different types of data in the prediction dataset:

[0045]

[0046] Where G represents the weight value of the data, and n represents the type of brittle failure caused by the data; R x m represents the weights of the data in category x. f R represents x The number of non-zero values.

[0047] In one embodiment, the weight values ​​of different types of data are input into a trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden component sample within a preset time period in the future, including:

[0048] Use the following formula to calculate the probability of a wooden component sample undergoing brittle failure within a predetermined time period in the future:

[0049]

[0050] Where C represents the probability value, T represents the mechanical loading period, n represents the transformation coefficient, A represents the correction coefficient, t represents the stability coefficient of the data in the prediction dataset, G represents the weight value corresponding to different types of data in the prediction dataset, f(kT) represents the adjustment function, and k represents a constant.

[0051] The risk of brittle failure in different parts of wooden components is quantitatively assessed based on probability values ​​to obtain the risk level of brittle failure.

[0052] Secondly, this application also provides a risk assessment system for brittle failure of wooden components under wet and cold conditions, the system comprising:

[0053] The data acquisition module is used to collect environmental parameters of the wooden component samples in different humid and cold environments in real time. The environmental parameters include at least one of different temperatures, relative humidity and air flow rates.

[0054] The parameter acquisition module is used to perform mechanical tests on wooden component samples to obtain brittle characteristic parameters during the stress process. The brittle characteristic parameters include physical property parameters and mechanical property parameters. The module also collects AE signals of wooden components during the stress process of mechanical testing under different humid and cold environments in real time to obtain signal characteristic parameters of the wooden component samples. The signal characteristic parameters include at least one of ring count, energy count, peak frequency, and signal duration.

[0055] The risk assessment module is used to process the acquired environmental parameters, brittle characteristic parameters, and signal characteristic parameters and input them into the trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of wooden components within a preset time period in the future.

[0056] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the aforementioned method or system.

[0057] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned method or system.

[0058] The aforementioned method, system, computer equipment, and storage medium for assessing the brittle failure risk of wooden components under humid and cold conditions first collect environmental parameters, including temperature, relative humidity, and air velocity, in real time under different humid and cold environments. Next, mechanical tests are performed on the wooden component samples to obtain brittle characteristic parameters, including physical and mechanical properties, during the stress process. Simultaneously, AE signals are collected in real time during the mechanical testing process under different humid and cold environments, obtaining signal characteristic parameters of the wooden component samples, including ring count, energy count, peak frequency, and signal duration. Subsequently, the acquired environmental, brittle, and signal characteristic parameters are processed to construct a dataset to form a prediction dataset. Finally, the data from the prediction dataset is input into a pre-trained brittle failure risk assessment model for wooden components, thereby obtaining the probability value of brittle failure of the wooden component within a preset time period, thus achieving an accurate assessment of the brittle failure risk of wooden components under humid and cold environments. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 A flowchart of a method for assessing the risk of brittle failure of wooden components under wet and cold conditions, provided in an embodiment of the present invention;

[0061] Figure 2 A flowchart for obtaining brittle characteristic parameters during stress testing of wooden component samples provided in an embodiment of the present invention;

[0062] Figure 3 A flowchart illustrating how to acquire AE signals during mechanical testing of wooden components under different humid and cold environments in real time, and obtain signal characteristic parameters of wooden component samples, is provided in this embodiment of the invention.

[0063] Figure 4 This is a flowchart illustrating the steps following the acquisition of signal characteristic parameters of a wooden component sample, as provided in an embodiment of the present invention.

[0064] Figure 5 The present invention provides a structural block diagram of a risk assessment system for brittle failure of wooden components under wet and cold conditions. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] Next, the implementation environment of the embodiments of this application will be described. Exemplarily, this implementation environment includes environmental monitoring simulation hardware, mechanical performance testing hardware, data acquisition hardware, and data processing equipment.

[0067] The environmental monitoring simulation hardware and mechanical performance testing hardware are connected to the data acquisition hardware to transmit the collected environmental parameters and mechanical performance data. The data acquisition hardware is connected to the data processing equipment to analyze and process the integrated data. At the same time, the data processing equipment can provide feedback control to the environmental monitoring simulation hardware and mechanical performance testing hardware.

[0068] The environmental monitoring simulation hardware includes a high and low temperature humidity test chamber, which can accurately simulate different temperature and humidity combinations in the risk assessment method for brittle failure of wooden components under humid and cold conditions, providing diverse environmental conditions for the testing of wooden components. Simultaneously, a temperature and humidity recorder records environmental data in real time with high precision, such as temperature ±0.1℃ and humidity ±2%RH, ensuring that environmental parameters are accurately captured throughout the test. The combined hardware provides a reliable environmental simulation and monitoring foundation for assessing the risk of brittle failure of wooden components in humid and cold environments.

[0069] In the assessment of the risk of brittle failure of wooden components under humid and cold conditions, the mechanical performance testing hardware includes a universal testing machine that can perform various tests on wooden components, such as tensile, compression, and bending tests, to accurately measure key indicators such as strength and stiffness in humid and cold environments. An impact testing machine simulates the impacts during handling and transportation to evaluate the impact resistance of wooden components. A dynamic mechanical analyzer can also analyze the dynamic mechanical properties at different frequencies, temperatures, and humidity levels, providing a comprehensive understanding of the mechanical performance of wooden components under humid and cold conditions, thus providing strong support for assessing the risk of brittle failure.

[0070] In the risk assessment of brittle failure of wooden components under humid and cold conditions, high-performance data acquisition cards can simultaneously acquire data from multiple sensors at high speed and high precision, converting analog signals into digital signals. The accompanying computer can run sophisticated assessment software to process and deeply analyze massive amounts of experimental data, ensuring the accuracy and reliability of the assessment method.

[0071] The data processing equipment, equipped with a multi-core high-performance processor and a computer as its core, efficiently organizes and analyzes large amounts of data obtained from various tests, such as mechanical property data and microstructural change data of wooden components under different temperatures and humidity conditions, when assessing the risk of brittle failure of wooden components under humid and cold conditions. Combined with professional data processing software, it enables the visualization of data, intuitively presenting the correlation between various factors and the risk of brittle failure of wooden components in humid and cold environments, providing strong support for accurate assessment.

[0072] The application scenarios of the embodiments of this application will be described in conjunction with the above implementation environment.

[0073] This application provides a method and system for assessing the risk of brittle failure of wooden components under humid and cold conditions. First, different humid and cold conditions are simulated using a high and low temperature humidity test chamber, and environmental data is monitored in real time using a temperature and humidity recorder. Next, equipment such as a universal testing machine and an impact testing machine are used to conduct tensile, compression, and impact mechanical property tests on the wooden components to obtain data such as strength and stiffness. Finally, by integrating various data and applying professional algorithms and models, the risk of brittle failure of the wooden components under humid and cold conditions is comprehensively assessed. Exemplarily, the method and system for assessing the risk of brittle failure of wooden components under humid and cold conditions provided in this application can be applied to at least one scenario, including but not limited to the following.

[0074] First, this method and system for assessing the risk of brittle failure of wooden components under humid and cold conditions is applied to construction sites. Environmental monitoring simulation hardware can be installed at construction sites to monitor environmental parameters such as temperature and humidity in real time. The monitored data is then fed back to the assessment system to simulate the actual humid and cold environment in which the wooden components are located. Portable wood hardness testers, tensile testing machines, and other mechanical performance testing hardware can be used to test key components of the wooden components. For example, when constructing a wooden house, strength and toughness tests can be performed on major wooden components such as beams and columns to assess their mechanical properties under the current humid and cold environment. Data acquisition hardware collects the data from the environmental monitoring simulation hardware and the mechanical performance testing hardware, and then transmits it to data processing equipment. The data processing equipment analyzes the data to predict the risk of brittle failure of wooden components due to the humid and cold environment during construction and subsequent use.

[0075] Secondly, the method and system for assessing the risk of brittle failure of wooden components under humid and cold conditions are applied in timber processing plants. Environmental monitoring simulation hardware is installed in the raw material storage areas and processing workshops of the timber processing plant to simulate different humid and cold environmental conditions. For example, when processing and producing wooden components for outdoor construction, the environmental monitoring simulation hardware is controlled to make the environment in the storage area and processing workshop approximate the outdoor humid and cold environment, thereby monitoring the performance changes of the wood under this environment. Mechanical performance testing hardware is used to test the wood at each stage of wood processing, such as before and after sawing and planing. Data acquisition hardware collects data from environmental monitoring and mechanical performance testing and transmits it to data processing equipment. The data processing equipment performs comprehensive analysis of the data and, based on the assessment method, determines the risk of brittle failure of the wood in a humid and cold environment after processing into wooden components. The plant can optimize its processing technology based on the analysis results.

[0076] In one embodiment, such as Figure 1 As shown, a method for assessing the risk of brittle failure of wooden components under wet and cold conditions is provided, which may include the following steps:

[0077] Step S101: Real-time acquisition of environmental parameters of the wooden component sample under different humid and cold environments. The environmental parameters include at least one of different temperatures, relative humidity and air flow rate.

[0078] Specifically, real-time monitoring of the environment in which the wooden component samples are located can be achieved using specialized sensor equipment. For temperature acquisition, high-precision thermometers can measure temperature values ​​at different times to ensure the capture of temperature changes in humid and cold environments. Relative humidity can be measured using humidity sensors to determine the proportion of water vapor in the environment, with an accuracy of ±3% relative humidity. Air velocity monitoring utilizes specialized anemometers to measure the speed of airflow around the wooden components, ranging from near-stationary 0 m / s to higher velocities that may be caused by ventilation equipment or natural wind. Real-time acquisition of at least one environmental parameter provides crucial data support for subsequent comprehensive analysis of the performance changes of wooden components under different humid and cold environments.

[0079] Step S102: Perform mechanical tests on the wooden component sample to obtain brittle characteristic parameters during the stress process; the brittle characteristic parameters include physical property parameters and mechanical property parameters.

[0080] Specifically, various types of mechanical tests on wooden component samples yield a series of brittle characteristic parameters, encompassing both physical properties and mechanical performance parameters. Among physical properties, moisture content significantly impacts the internal structure of wood; for example, high moisture content may make wood more prone to deformation and decay under stress, thus affecting its brittleness. Density reflects the compactness and material properties of wood; woods of different densities exhibit varying resistance to external forces. Regarding mechanical performance parameters, by simulating loading processes in real-world applications, the response of wooden components under different loads is measured. For instance, the load-bearing time reflects the stability of the wooden component under sustained stress, the maximum load capacity directly reflects its ultimate load-bearing capacity, and the center of gravity shift reveals, to some extent, the equilibrium characteristics of the wooden component under stress, providing a comprehensive and accurate description of the brittle characteristics of the wooden component during stress.

[0081] Step S103: Real-time acquisition of AE signals during the mechanical testing of wooden components under different humid and cold environments to obtain signal characteristic parameters of the wooden component samples; the signal characteristic parameters include at least one of ring count, energy count, peak frequency, and signal duration.

[0082] Acoustic emission (AE) signals were acquired in real time during mechanical stress testing of wooden component samples under simulated different humid and cold environments. Among these, the ring count reflects the frequency of acoustic emission events, i.e., the number of times the signal exceeds a set threshold; a higher number of ring counts may indicate more active microcrack generation and propagation within the wooden component. The energy count quantifies the signal energy; a high energy count indicates a stronger acoustic emission event, potentially indicating severe damage or stress concentration in the wooden component structure. The peak frequency, as the highest frequency in the signal spectrum, helps determine the type and nature of the acoustic emission source; different frequency characteristics are closely related to changes in the microstructure and stress patterns within the wood. The signal duration visually represents the duration of the acoustic emission event; a longer duration may suggest continued crack propagation or a complex stress release process. By acquiring and analyzing at least one signal characteristic parameter, including ring count, energy count, peak frequency, and signal duration, insights can be gained into the internal structural changes and potential brittleness risks of wooden components under humid and cold stress conditions.

[0083] Step S104: Based on the obtained environmental parameters, fragile characteristic parameters and signal characteristic parameters, process them and construct a dataset to obtain a prediction dataset.

[0084] For the acquired environmental parameters, data such as temperature, relative humidity, and air velocity need to be normalized to adjust their numerical range to a unified standard scale. The conversion formula is determined based on the actual measured minimum and maximum temperatures. Regarding brittle characteristic parameters, both physical properties such as moisture content and density, and mechanical properties such as bending strength and maximum load-bearing capacity, must be standardized to eliminate the influence of dimensions. Moisture content can be represented by the ratio of the difference to the standard moisture content value; mechanical property parameters can be quantified based on their relative position within the common performance range of similar wood components. Signal characteristic parameters such as ring count and energy count require data cleaning to remove outliers that may be caused by equipment noise or accidental interference. For example, a reasonable ring count threshold can be set, and data points above or below this threshold within a certain range are considered outliers and discarded. Then, the processed environmental parameters, brittle characteristic parameters, and signal characteristic parameters are combined and arranged according to certain rules to construct a data row containing multi-dimensional information for each wood component sample. By integrating data from numerous wooden component samples to form a prediction dataset, we can provide data support for accurately predicting the probability of brittle failure of wooden components within a predetermined time period.

[0085] Step S105: Input the data from the prediction dataset into the trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden components within a preset time period in the future.

[0086] Specifically, processed and integrated data from the prediction dataset can be input into a pre-trained risk assessment model for brittle failure of wooden components, trained using extensive experimental data and complex algorithms. This model yields the probability of brittle failure of the wooden components within a predetermined timeframe. The brittle failure risk assessment model can be built using machine learning algorithms such as support vector machines, random forests, or deep learning. For environmental parameters, the model can quantify the weight of each parameter in the brittle failure process by incorporating existing knowledge and training experience. For brittle characteristic parameters such as low bending strength and high moisture content, the model references historical failure cases of wooden components with similar parameter combinations to further analyze their correlation with failure risk. After calculation and inference, the model ultimately outputs a probability value between 0 and 1, representing the probability of brittle failure of the wooden component within the predetermined timeframe. Based on this probability value, relevant personnel can take targeted measures.

[0087] The aforementioned method for assessing the risk of brittle failure of wooden components under humid and cold conditions first collects environmental parameters, including temperature, relative humidity, and air velocity, in real time under different humid and cold environments. Next, mechanical tests are performed on the wooden component samples to obtain brittle characteristic parameters, including physical and mechanical properties, during the stress process. Simultaneously, AE signals are collected in real time during the mechanical testing process under different humid and cold environments, obtaining signal characteristic parameters of the wooden component samples, including ring count, energy count, peak frequency, and signal duration. Subsequently, the acquired environmental, brittle, and signal characteristic parameters are processed to construct a dataset to form a prediction dataset. Finally, the data from the prediction dataset is input into a pre-trained brittle failure risk assessment model for wooden components, thereby obtaining the probability value of brittle failure of the wooden component within a preset time period, thus achieving an accurate assessment of the brittle failure risk of wooden components under humid and cold environments.

[0088] In one embodiment, such as Figure 2 As shown, mechanical testing of wooden component samples to obtain brittle characteristic parameters during stress can include the following steps:

[0089] Step S201: Obtain the physical property parameters of the wooden component sample based on its moisture content, density, bending strength, and modulus of elasticity.

[0090] The process involves measuring the initial moisture content of wooden component samples at multiple key locations according to standard testing methods and calculating the average value to obtain the moisture content of the wooden component samples. The density of the wooden component samples is then measured using the drainage method or a professional density meter. The wooden component samples are then subjected to a bending load gradually applied at a constant loading rate according to standard three-point or four-point bending test methods until the sample fails, with force and displacement data recorded in real time to obtain the bending strength of the wooden component samples. Finally, the elastic modulus of the wooden component samples is tested, and the corresponding force and displacement data are recorded to calculate the elastic modulus of the wooden component samples.

[0091] Step S202: Based on the load-bearing time period, maximum load-bearing weight, and center of gravity offset under dynamic loading simulation of the wooden component sample, the mechanical performance parameters of the wooden component sample are obtained.

[0092] The process involves simulating load-bearing on wooden component samples at different center-of-gravity positions using a dynamic loading mode, recording relevant data to obtain stress data. This stress data includes force, displacement, and time data. Based on the stress data, the duration of different load levels is recorded to obtain the load-bearing time period. The weight of the load on the wooden component sample is gradually increased until the sample reaches its maximum load-bearing capacity or shows obvious signs of failure; the load weight at this point is recorded to obtain the maximum load-bearing weight. Based on the deformation of the wooden component sample under different loads and motion states, causing a shift in the center of gravity, the data on the change in the center of gravity position is recorded to obtain the center of gravity shift.

[0093] Step S203: Calculate the physical property parameters and mechanical property parameters using the following formulas to obtain the brittle characteristic parameters of each wooden component sample:

[0094]

[0095] Where S represents the brittle characteristic parameters of the wooden component sample; ω2, ω3, ω4, ω 5i ω6, ω7, and ω8 represent the weighting coefficients for moisture content, density, bending strength, modulus of elasticity, the i-th type of wood, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; MC0, ρ0, σ0, E0, W0, F0, and G0 represent the reference values ​​for moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; MC, ρ, σ, E, W, F, and G represent the moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset of the wood component sample, respectively; ΔMC, Δρ, Δσ, ΔE, ΔW, ΔF, and ΔG represent the preset deviation thresholds for moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; n represents the total number of wood types; I(X i ) represents the indicator function for the type of wood. If the wood type in the sample is the i-th type, then I(X) i =1, otherwise 0.

[0096] Step S204: Standardize the calculated brittle characteristic parameters of each wooden component sample to obtain a standardized set of brittle characteristic parameters.

[0097] In evaluating the brittle characteristic parameters of wooden components, the physical properties of the wooden component samples were first measured at multiple key locations according to standard testing methods. Next, the mechanical properties of the wooden component samples were obtained by simulating dynamic loading under different center-of-gravity positions. Then, specific formulas were used to calculate each parameter, where each parameter corresponds to different weighting coefficients and involves factors such as reference values, deviation thresholds, and wood species indicator functions, to derive the brittle characteristic parameters for each wooden component sample. Finally, the calculated brittle characteristic parameters were standardized to obtain a standardized set of brittle characteristic parameters, providing a unified and standardized data foundation for subsequent analysis and evaluation.

[0098] In one embodiment, such as Figure 3 As shown, real-time acquisition of AE signals during the mechanical testing of wooden components under different humid and cold environments to obtain signal characteristic parameters of the wooden component samples can include the following steps:

[0099] Step S301: Based on the stress conditions of the pre-treated wooden component samples in actual use, design a variety of mechanical testing schemes; the mechanical testing schemes include different loading rates, load levels, loading methods and loading paths.

[0100] Step S302: Each mechanical test scheme is tested repeatedly under preset humid and cold environmental conditions to obtain the preset test scheme.

[0101] Step S303: Apply mechanical loading to the wooden component sample according to the preset test plan and collect AE signals in real time to obtain the signal parameters of the wooden component sample.

[0102] Step S304: The acquired AE signal is processed offline using a variety of signal processing methods based on the signal parameters to obtain the final signal parameters; the various signal processing methods include filtering, envelope analysis, and wavelet transform.

[0103] Step S305: Extract key features based on the final signal parameters to obtain the signal feature parameters of the wooden component sample; the signal feature parameters include at least one of ring count, energy count, peak frequency, and signal duration; the ring count refers to the number of times the signal exceeds a set threshold; the energy count is the quantification of the signal energy; the peak frequency is the highest frequency in the signal spectrum; and the signal duration indicates the duration of the acoustic emission event.

[0104] When extracting signal characteristic parameters from wooden components, multiple mechanical test schemes covering different loading rates, load levels, loading methods, and loading paths are first designed based on the stress conditions of the pre-processed wooden component samples in actual use. Then, for each designed mechanical test scheme, multiple repeated tests are conducted under pre-set humid and cold environmental conditions to determine the final preset test scheme. Subsequently, mechanical loading operations are performed on the wooden component samples according to this preset test scheme, and AE signals are simultaneously acquired in real time to obtain the signal parameters of the wooden component samples. Based on the signal parameters, various signal processing methods such as filtering, envelope analysis, and wavelet transform are used to process the acquired AE signals offline, thereby obtaining the final processed signal parameters. Based on the obtained final signal parameters, key features such as ring count, energy count, peak frequency, and signal duration are extracted to obtain the signal characteristic parameters of the wooden component samples. The obtained signal characteristic parameters can effectively reflect the internal structural changes and potential damage of the wooden components, providing a crucial basis for accurately evaluating the performance and reliability of wooden components under humid and cold conditions.

[0105] In one embodiment, such as Figure 4 As shown, after obtaining the signal characteristic parameters of the wooden component sample, the following steps may also be included:

[0106] Step S401: Based on the collected signal feature parameters, abnormal or erroneous data are removed to obtain the processed signal feature parameters.

[0107] Step S402: Based on the processed signal characteristic parameters and the real-time recorded force and displacement data, the stress-strain curve of the wooden component sample is plotted.

[0108] Step S403: Based on the obtained stress-strain curve, determine the peak strength point, residual strength point, and elastic modulus of the elastic deformation segment of the curve, and use the peak strength point as the key reference point to draw the brittleness risk analysis diagram of the wooden component sample.

[0109] A thorough analysis of the acquired stress-strain curves was conducted. The point on the curve where the stress reaches its maximum value was identified as the peak strength point, representing the maximum stress the wooden component can withstand under load. The residual strength point corresponds to the strength the wooden component retains after a certain degree of deformation. The elastic modulus was calculated using the slope of the curve in the elastic deformation segment. Using the peak strength point as the core reference, combined with other key data points and curve characteristics, a brittleness risk analysis diagram of the wooden component sample was created. This diagram comprehensively displays information related to the brittleness of the wooden component.

[0110] Step S404: Based on the brittleness risk analysis diagram, divide the line perpendicular to the strain axis and intersecting the peak strength point to obtain the ideal brittleness line.

[0111] Step S405: Based on the brittleness risk analysis diagram, divide the line perpendicular to the stress axis and intersecting the peak strength point to obtain the predicted brittleness line.

[0112] Step S406: Based on the brittleness risk analysis diagram, divide the line passing through the peak strength point and with a slope equal to the opposite of the elastic modulus to obtain the brittleness boundary line.

[0113] Step S407: Based on the ideal brittleness line, the predicted brittleness line, and the brittleness boundary line, the region of the strain curve segment after the peak in the brittleness risk analysis diagram is determined to obtain the brittle region.

[0114] Among them, when the post-peak strain curve segment is located between the predicted brittleness line and the brittleness boundary line, the brittle region is a small brittle region.

[0115] When the post-peak strain curve segment lies between the ideal brittle line and the brittle boundary line, the brittle region is a highly brittle region.

[0116] Step S408: The brittleness index of the wooden component sample is obtained by calculating the brittleness index based on the formula for the small brittleness region and the large brittleness region respectively.

[0117] This embodiment first removes abnormal or erroneous data from the collected signal feature parameters to obtain processed signal feature parameters. Next, the processed signal feature parameters are combined with real-time recorded force and displacement data to plot the stress-strain curve of the wooden component sample. Then, based on the plotted stress-strain curve, the peak strength point, residual strength point, and elastic modulus of the elastic deformation segment are accurately determined. Using the peak strength point as a key reference point, a brittleness risk analysis diagram of the wooden component sample is plotted. Based on the brittleness risk analysis diagram, the ideal brittleness line, the predicted brittleness line, and the brittleness boundary line are delineated. Then, based on the ideal brittleness line, the predicted brittleness line, and the brittleness boundary line, the post-peak strain curve segment in the brittleness risk analysis diagram is regionally determined to obtain small brittleness regions and large brittleness regions. Finally, based on the small brittleness regions and large brittleness regions, specific formulas are used to calculate and obtain the brittleness index of the wooden component sample.

[0118] In one embodiment, the brittleness index of the wooden component sample is calculated using formulas based on the small brittleness region and the large brittleness region, including:

[0119] When the strain curve segment after the peak is located in the small brittle region:

[0120]

[0121] When the strain curve segment after the peak is located in the brittle region:

[0122]

[0123] Where H represents the brittleness index; K represents the preset brittleness index corresponding to the brittleness boundary; N represents the number of sample points selected on the post-peak strain curve; and ε i and σ i Let ε represent the strain value and stress value of the i-th sample point, respectively. c and σ c These represent the strain and stress values ​​at the peak strength point, respectively, and E represents the elastic modulus.

[0124] When assessing the brittleness of wooden components, different formulas are used to accurately calculate the brittleness index based on the region of the post-peak strain curve segment. The brittleness index is a quantitative indicator for measuring the brittleness of wooden components. The preset brittleness index, representing the brittleness boundary, is a key reference value derived from extensive experimental data and theoretical analysis, reflecting the critical brittleness level of a wooden component approaching the brittle transition under specific conditions. The brittleness index comprehensively reflects the brittle characteristics of wooden components, providing a quantitative basis for assessing their reliability in humid and cold environments.

[0125] In one embodiment, inputting data from the prediction dataset into a trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden components within a preset time period may include the following steps:

[0126] Step S501: Construct a dataset by combining the brittleness index calculated from the standardized brittleness characteristic parameters and signal characteristic parameters of the environmental parameters and brittleness characteristic parameters to obtain a prediction dataset.

[0127] Step S502: Calculate the data in the prediction dataset to obtain the weight values ​​of different types of data that cause brittle failure of wooden component samples.

[0128] Step S503: Input the weight values ​​of different types of data into the trained brittle failure risk assessment model of wooden components to obtain the probability value of brittle failure of wooden component samples within a preset time period in the future; the risk assessment model includes at least one of support vector machine, random forest and neural network.

[0129] Use the following formula to calculate the weight values ​​for different types of data in the prediction dataset:

[0130]

[0131] Where G represents the weight value of the data, and n represents the type of brittle failure caused by the data; R x m represents the weights of the data in category x. f R represents x The number of non-zero values.

[0132] In assessing the risk of brittle failure in wooden components, the collected environmental parameters, standardized brittleness characteristic parameters, and brittleness index calculated from signal characteristic parameters are first integrated to construct a prediction dataset. Next, a formula is used to determine the weight values ​​of different types of data that could cause brittle failure in the wooden component samples. Finally, the calculated weight values ​​of different types of data are input into a pre-trained brittle failure risk assessment model for wooden components. The model then calculates and outputs the probability value of brittle failure of the wooden component samples within a preset time period, thus effectively assessing the risk of brittle failure in wooden components under humid and cold conditions.

[0133] In one embodiment, the weight values ​​of different types of data are input into a trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden component sample within a preset time period in the future. This may include the following steps:

[0134] Use the following formula to calculate the probability of a wooden component sample undergoing brittle failure within a predetermined time period in the future:

[0135]

[0136] Where C represents the probability value, T represents the mechanical loading period, n represents the transformation coefficient, A represents the correction coefficient, t represents the stability coefficient of the data in the prediction dataset, G represents the weight value corresponding to different types of data in the prediction dataset, f(kT) represents the adjustment function, and k represents a constant.

[0137] The risk of brittle failure in different parts of wooden components is quantitatively assessed based on probability values ​​to obtain the risk level of brittle failure.

[0138] The mechanical loading cycle describes the stress cycle time of a wooden component during actual use. The length of this cycle affects the structural stability of the wooden component; a longer loading cycle may accelerate the accumulation of damage in its internal structure, thereby increasing the risk of brittle failure. The transition coefficient measures the ease with which a wooden component transitions to a brittle failure mode under different conditions. It comprehensively considers the influence of wood characteristics and environmental factors on the brittle transition. A larger value indicates that, under given conditions, the wooden component is more likely to transition from a relatively stable state to a brittle failure state. The adjustment function flexibly adjusts the combination of various parameters according to specific assessment needs and data characteristics to optimize the accuracy of probability calculations. After obtaining the probability values, the brittle failure risk of different parts of the wooden component is quantitatively assessed based on these probabilities. By dividing the wooden component into multiple key parts, and combining the stress and strain conditions of each part with its importance in the overall structure, the brittle failure risk level of each part is determined based on the probability value. For example, for the main load-bearing parts that support cargo, if the probability value is high, its risk level is determined to be high risk; while for some secondary support parts, even if the probability value is relatively low, it is still within a certain risk range and may be determined to be medium risk. Quantitative assessment can reveal the safety status of different parts of wooden components, providing a scientific basis for taking targeted maintenance, replacement, or reinforcement measures.

[0139] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0140] In one embodiment, such as Figure 5 As shown, this application also provides a system for assessing the risk of brittle failure of wooden components under wet and cold conditions. The system may include:

[0141] The data acquisition module 601 is used to collect environmental parameters of the wooden component sample under different humid and cold environments in real time. The environmental parameters include at least one of different temperatures, relative humidity and air flow rate.

[0142] The parameter acquisition module 602 is used to perform mechanical tests on wooden component samples to obtain brittle characteristic parameters during the stress process; the brittle characteristic parameters include physical property parameters and mechanical property parameters; the module also collects AE signals of the wooden component during the stress process of mechanical testing under different humid and cold environments in real time to obtain signal characteristic parameters of the wooden component sample; the signal characteristic parameters include at least one of ring count, energy count, peak frequency, and signal duration.

[0143] The risk assessment module 603 is used to process the acquired environmental parameters, brittle characteristic parameters and signal characteristic parameters and input them into the trained brittle failure risk assessment model of wooden components to obtain the probability value of brittle failure of wooden components within a preset time period in the future.

[0144] The aforementioned risk assessment system for brittle failure of wooden components under humid and cold conditions mainly consists of three important modules: a data acquisition module, a parameter acquisition module, and a risk assessment module. The data acquisition module acquires relevant environmental parameters in different humid and cold environments where the wooden component samples are located, covering at least one element such as different temperatures, relative humidity, and air velocity. The parameter acquisition module conducts mechanical tests on the wooden component samples to obtain their brittle characteristic parameters during stress, including physical property parameters and mechanical performance parameters. It also collects the AE signals of the wooden components during mechanical testing under different humid and cold environments in real time, and extracts at least one signal characteristic parameter of the wooden component samples, such as ring count, energy count, peak frequency, and signal duration. The risk assessment module processes the acquired environmental parameters, brittle characteristic parameters, and signal characteristic parameters, and then inputs the processed data into a pre-trained risk assessment model for brittle failure of wooden components. Finally, it calculates the probability value of brittle failure of the wooden component within a preset time period, thereby achieving an accurate assessment of the risk of brittle failure of wooden components under humid and cold conditions.

[0145] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the aforementioned method or system for assessing the risk of brittle failure of wooden components under wet and cold conditions.

[0146] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the embodiments of the methods or systems described above.

[0147] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0148] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for assessing the risk of brittle failure of wooden components under wet and cold conditions, characterized in that, The method includes: Real-time acquisition of environmental parameters of wooden component samples under different humid and cold environments, including at least one of different temperatures, relative humidity and air velocity; Mechanical tests were conducted on wooden component samples to obtain brittle characteristic parameters during the stress process; the brittle characteristic parameters include physical property parameters and mechanical property parameters; Real-time acquisition of AE signals during mechanical testing of wooden components under different humid and cold environments yields signal characteristic parameters of the wooden component samples; the signal characteristic parameters include at least one of ring count, energy count, peak frequency, and signal duration. The obtained environmental parameters, fragility characteristic parameters, and signal characteristic parameters are processed and a dataset is constructed to obtain a prediction dataset; The predicted dataset is input into the trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden components within a preset time period in the future.

2. The method according to claim 1, characterized in that, The mechanical testing of the wooden component samples to obtain brittle characteristic parameters during the stress process includes: The physical property parameters of the wooden component samples were obtained based on their moisture content, density, bending strength, and modulus of elasticity. The mechanical performance parameters of the wooden component samples were obtained by performing dynamic loading simulation on the sample, including the load-bearing time period, maximum load-bearing weight, and center of gravity offset. The brittle characteristic parameters of each wooden component sample are obtained by calculating the physical property parameters and the mechanical property parameters using the following formula: Where S represents the brittle characteristic parameters of the wooden component sample; ω2, ω3, ω4, ω 5i ω6, ω7, and ω8 represent the weighting coefficients for moisture content, density, bending strength, modulus of elasticity, the i-th type of wood, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; MC0, ρ0, σ0, E0, W0, F0, and G0 represent the reference values ​​for moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; MC, ρ, σ, E, W, F, and G represent the moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset of the wood component sample, respectively; ΔMC, Δρ, Δσ, ΔE, ΔW, ΔF, and ΔG represent the preset deviation thresholds for moisture content, density, bending strength, modulus of elasticity, maximum load-bearing weight, load-bearing time period, and center of gravity offset, respectively; n represents the total number of wood types; I(X i ) represents the indicator function for the type of wood. If the wood type in the sample is the i-th type, then I(X) i ) = 1, otherwise 0; The calculated brittle characteristic parameters of each wooden component sample are standardized to obtain a standardized set of brittle characteristic parameters.

3. The method according to claim 1, characterized in that, The method involves real-time acquisition of the AE signal during the mechanical testing of wooden components under different humid and cold environments to obtain the signal characteristic parameters of the wooden component samples, including: Based on the stress conditions of the pretreated wooden component samples in actual use, a variety of mechanical testing schemes were designed; the mechanical testing schemes include different loading rates, load levels, loading methods and loading paths; Each of the aforementioned mechanical test schemes is tested repeatedly under preset humid and cold environmental conditions to obtain the preset test scheme; The wooden component sample was subjected to mechanical loading according to the preset test plan, and the AE signal was collected in real time to obtain the signal parameters of the wooden component sample. The acquired AE signal is processed offline using a variety of signal processing methods based on the signal parameters to obtain the final signal parameters; the various signal processing methods include filtering, envelope analysis, and wavelet transform; Key features are extracted based on the final signal parameters to obtain signal feature parameters of the wooden component sample; the signal feature parameters include at least one of ring count, energy count, peak frequency, and signal duration; the ring count refers to the number of times the signal exceeds a set threshold; the energy count is the quantification of signal energy; the peak frequency is the highest frequency in the signal spectrum; and the signal duration indicates the duration of the acoustic emission event.

4. The method according to claim 3, characterized in that, After obtaining the signal characteristic parameters of the wooden component sample, the process further includes: Based on the collected signal feature parameters, abnormal or erroneous data are removed to obtain processed signal feature parameters; Based on the processed signal characteristic parameters and the real-time recorded force and displacement data, the stress-strain curve of the wooden component sample is plotted. Based on the obtained stress-strain curve, the peak strength point, residual strength point, and elastic modulus of the elastic deformation segment of the curve are determined, and the brittleness risk analysis diagram of the wooden component sample is drawn with the peak strength point as the key reference point. Based on the brittleness risk analysis diagram, a straight line perpendicular to the strain axis and intersecting the peak strength point is drawn to obtain the ideal brittleness line; Based on the brittleness risk analysis diagram, a straight line perpendicular to the stress axis and intersecting the peak strength point is drawn to obtain the predicted brittleness line; Based on the brittleness risk analysis diagram, a straight line passing through the peak strength point and with a slope equal to the opposite of the elastic modulus is drawn to obtain the brittleness boundary line. Based on the ideal brittleness line, the predicted brittleness line, and the brittleness boundary line, the post-peak strain curve segment in the brittleness risk analysis diagram is used to determine the brittle region; Wherein, when the post-peak strain curve segment is located between the predicted brittleness line and the brittleness boundary line, the brittle region is a small brittle region; When the post-peak strain curve segment is located between the ideal brittleness line and the brittleness boundary line, the brittle region is a highly brittle region. The brittleness index of the wooden component sample is obtained by calculating the brittleness index using the formula based on the small brittleness region and the large brittleness region respectively.

5. The method according to claim 4, characterized in that, The brittleness index of the wooden component sample is calculated using formulas based on the small and large brittle regions, including: When the post-peak strain curve segment is located in a small brittle region: When the post-peak strain curve segment is located in the brittle region: Wherein, H represents the brittleness index; K represents the preset brittleness index corresponding to the brittleness boundary; N represents the number of sample points selected on the post-peak strain curve; ε i and σ i Let ε represent the strain value and stress value of the i-th sample point, respectively. c and σ c These represent the strain and stress values ​​at the peak strength point, respectively, and E represents the elastic modulus.

6. The method according to claim 1, characterized in that, The step of inputting the data from the predicted dataset into the trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden components within a preset time period includes: A dataset is constructed from the environmental parameters, the standardized brittle characteristic parameters in the brittle characteristic parameter set, and the brittle index calculated from the signal characteristic parameters to obtain a prediction dataset; The weight values ​​of different types of data that cause brittle failure in wooden component samples are calculated from the data in the prediction dataset. The weight values ​​of different types of data are input into the trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden component sample within a preset time period in the future; the risk assessment model includes at least one of support vector machine, random forest and neural network; Use the following formula to calculate the weight values ​​for different types of data in the prediction dataset: Where G represents the weight value of the data, and n represents the type of brittle failure caused by the data; R x m represents the weights of the data in category x. f R represents x The number of non-zero values.

7. The method according to claim 6, characterized in that, The step of inputting the weight values ​​of different types of data into the trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of the wooden component sample within a preset time period includes: Use the following formula to calculate the probability of a wooden component sample undergoing brittle failure within a predetermined time period in the future: Where C represents the probability value, T represents the mechanical loading period, n represents the transformation coefficient, A represents the correction coefficient, t represents the stability coefficient of the data in the prediction dataset, G represents the weight value corresponding to different types of data in the prediction dataset, f(kT) represents the adjustment function, and k represents a constant. Based on the probability values, the risk of brittle failure in different parts of the wooden component is quantitatively assessed to obtain the risk level of brittle failure.

8. A system for assessing the risk of brittle failure of wooden components under wet and cold conditions, characterized in that, The system includes: The data acquisition module is used to collect environmental parameters of the wooden component samples under different humid and cold environments in real time. The environmental parameters include at least one of different temperatures, relative humidity and air flow rate. The parameter acquisition module is used to perform mechanical tests on wooden component samples to obtain brittle characteristic parameters during the stress process; the brittle characteristic parameters include physical property parameters and mechanical property parameters; the module also collects AE signals of the wooden component during the stress process of mechanical testing under different humid and cold environments in real time to obtain signal characteristic parameters of the wooden component sample; the signal characteristic parameters include at least one of ring count, energy count, peak frequency, and signal duration. The risk assessment module is used to process the acquired environmental parameters, brittle characteristic parameters, and signal characteristic parameters and input them into the trained brittle failure risk assessment model for wooden components to obtain the probability value of brittle failure of wooden components within a preset time period in the future.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method or system according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method or system according to any one of claims 1 to 8.

Images