Method and system for evaluating carbon emission in drying process of impregnated bamboo bundle

Abstract

The invention discloses a method and a system for evaluating carbon emission in a drying process of a dipped bamboo bunch, and the method comprises the steps: taking key technological parameters (such as average diameter, initial water content, defibering degree, paving thickness and layer number) of the dipped bamboo bunch as input variables (carbon emission influence elements), and taking carbon emission as target output; a pre-trained carbon emission evaluation model is utilized to obtain a carbon emission predicted value in the drying process of the impregnated bamboo bundle, and the carbon emission evaluation model is pre-trained and learned to establish a mapping relation between values of carbon emission influence factors and the carbon emission predicted value in the drying process of the impregnated bamboo bundle. And the recognition and response efficiency of the nonlinear coupling relationship among the complex process parameters is remarkably improved. The problems that a traditional method is lagged in response, poor in adaptability, weak in regulation and control capacity and the like are solved, and the high-order requirements of current green intelligent manufacturing and low-carbon processing production for process perception and accurate regulation and control are difficult to meet.

Description

Technical Field

[0001] This invention relates to the field of carbon emission technology, and in particular to a method and system for assessing carbon emissions during the drying process of resin-impregnated bamboo bundles. Background Technology

[0002] Resin-impregnated bamboo bundles are the basic unit in the preparation of reconstituted bamboo. Their moisture content after drying and the pre-curing characteristics of the resin significantly affect the physical and mechanical properties of the reconstituted bamboo. The preparation process mainly involves the following steps: first, the raw bamboo is mechanically thinned to obtain bamboo bundles with varying morphologies; then, the bamboo bundles undergo preliminary drying and heat treatment to obtain heat-treated bamboo bundles; next, they are impregnated in a phenolic resin solution for a specific time under normal temperature and pressure to allow for full resin absorption; finally, the impregnated bamboo bundles undergo a second drying process. This drying stage is the most energy-intensive part of the entire preparation process, and because the resin is prone to pre-curing during drying, affecting the quality of subsequent hot-pressing bonding, a low-temperature drying process is usually required. This process not only significantly extends the drying cycle but also greatly increases energy consumption, leading to persistently high carbon emissions.

[0003] The drying of resin-impregnated bamboo bundles is a high-energy-consuming process in the preparation of reconstituted bamboo, and the resulting carbon emissions are increasingly attracting widespread attention from the business and academic communities. Currently, existing technologies do not address the relationship between the drying of resin-impregnated bamboo bundles and carbon emissions, making it difficult to accurately capture the real-time evolution of carbon emissions during the drying process.

[0004] The applicant found that the emission factor method, a quantitative assessment method for carbon emissions, is widely used in industrial carbon emission quantitative assessment due to its simplicity and broad applicability, especially for calculating carbon emissions from energy sources such as coal, natural gas, diesel, and electricity. For the drying process of rubble-impregnated bamboo bundles, which is primarily driven by electricity, this method theoretically has good adaptability. However, in practice, the applicant found that energy consumption during the actual drying process of rubble-impregnated bamboo bundles is affected by multiple dynamic factors, including the degree of bamboo bundle loosening, initial moisture content, airflow velocity of the drying medium, laying method, and drying temperature and humidity conditions. These factors work together to cause electricity consumption to exhibit high temporal volatility and nonlinear characteristics. Traditional calculation methods based on a single emission factor cannot accurately reflect the real-time changes in carbon emissions during the drying process, and cannot achieve the technical problem of dynamic coupling analysis between key process parameters of rubble-impregnated bamboo bundles and carbon emissions, exhibiting limitations such as response lag and poor adaptability. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a rapid, accurate method and system for assessing carbon emissions during the drying process of rubberized bamboo bundles that can achieve dynamic coupling analysis between key process parameters and carbon emissions.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: A method for assessing carbon emissions during the drying process of resin-impregnated bamboo bundles includes the following steps: S1. Collect the values ​​of specified carbon emission influencing factors of the resin-impregnated bamboo bundles being evaluated during the drying process; the specified carbon emission influencing factors include at least two or more of the following: number of bamboo bundle loosening times, initial moisture content, number of laying layers, average diameter of bamboo bundles, stacking method, bamboo age, and internode length. S2. The carbon emission influencing factors of the sizing bamboo bundles to be evaluated during the drying process are determined using a pre-trained carbon emission assessment model to obtain the predicted carbon emission values ​​during the drying process of the sizing bamboo bundles. The carbon emission assessment model is pre-trained to establish a mapping relationship between the values ​​of the carbon emission influencing factors and the predicted carbon emission values ​​during the drying process of the sizing bamboo bundles.

[0007] Preferably, as a further improvement to the above technical solution: The training of the carbon emission assessment model includes: S101. Conduct a drying experiment on the resin-impregnated bamboo bundle samples, and collect the values ​​of the specified carbon emission influencing factors and the corresponding carbon emission label values ​​during the drying process of the resin-impregnated bamboo bundle samples. S102. Construct a dataset of refractory bamboo bundle samples based on the values ​​of carbon emission influencing factors during the drying process and the corresponding carbon emission label values. S103. Construct a carbon emission assessment model and use a sample dataset of resin-impregnated bamboo bundles to train the carbon emission assessment model until the model accuracy meets the requirements.

[0008] The carbon emission label values ​​are the CO2 emissions (CO2eq) of the resin-impregnated bamboo bundles during the entire drying process and the CO2 emissions per unit mass of resin-impregnated bamboo bundles. E CO2 emissions per unit time of resin-impregnated bamboo bundles E 1. The expression for the calculation function is: ; ; ; in, This refers to the total amount of electricity supplied during the entire drying process. Carbon emission factor; m This represents the weight difference of the resin-impregnated bamboo bundles before and after drying. This refers to the drying time of the resin-impregnated bamboo bundles. The CO2 emissions per unit mass of resin-impregnated bamboo bundles are also given. E CO2 emissions per unit time of resin-impregnated bamboo bundles E1. It can explain how input variables (carbon emission influencing factors) affect the carbon emissions during the drying process of resin-impregnated bamboo bundles, causing the carbon emissions to fluctuate. This makes it easier to observe the rate of carbon emissions and the changes in emission peaks under different input variable conditions.

[0009] The carbon emission assessment model constructed in step S103 is a random forest model.

[0010] In step S101, when collecting the values ​​of specified carbon emission influencing factors and corresponding carbon emission label values ​​of the resin-impregnated bamboo bundle samples during the drying process, this includes selecting some carbon emission influencing factors from all carbon emission influencing factors of the resin-impregnated bamboo bundle samples as specified carbon emission influencing factors, thereby obtaining the values ​​of the specified carbon emission influencing factors.

[0011] When selecting a subset of carbon emission influencing factors from all carbon emission influencing factors of the resin-impregnated bamboo bundle sample as designated carbon emission influencing factors, the process includes calculating an importance value for each carbon emission influencing factor among all carbon emission influencing factors of the resin-impregnated bamboo bundle sample, and selecting a subset of carbon emission influencing factors as designated carbon emission influencing factors based on the importance values.

[0012] The function expression for calculating the importance value is: ; in, Let be the importance value of the j-th carbon emission influencing factor, and T be the total number of decision trees in the random forest model; This represents the raw prediction error of the out-of-bag (OOB) data for the t-th decision tree. The out-of-bag (OOB) prediction error of the decision tree after replacing the j-th carbon emission influencing factor; the selection of some carbon emission influencing factors as designated carbon emission influencing factors based on importance value means selecting some carbon emission influencing factors with positive importance values ​​as designated carbon emission influencing factors.

[0013] As a general inventive concept, the present invention also provides a carbon emission assessment system for the drying process of rubberied bamboo bundles, including a microprocessor and a memory interconnected, the microprocessor being programmed or configured to perform the aforementioned carbon emission assessment method for the drying process of rubberied bamboo bundles.

[0014] As a general inventive concept, the present invention also provides a computer-readable storage medium storing a computer program or instructions that are programmed or configured to execute, via a processor, the aforementioned carbon emission assessment method for the drying process of resin-impregnated bamboo bundles.

[0015] As a general inventive concept, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute the aforementioned carbon emission assessment method during the drying process of resin-impregnated bamboo bundles via a processor.

[0016] The main innovation of this invention is as follows: The applicant has found through long-term practice that the main factors affecting carbon emissions during the drying process of phenolic resin-impregnated bamboo bundles include the following: (1) Bamboo bundles need to be dried before and after impregnation, resulting in high carbon emissions due to the two drying processes; (2) The presence of bamboo accelerates the curing reaction of PF resin. To reduce the pre-curing of resin during the drying process, only low-temperature drying methods can be used. Although lowering the temperature is beneficial for controlling the resin state, it also prolongs the drying time and increases the carbon load of the process; (3) Mechanical loosening of bamboo increases the specific surface area and pore structure of bamboo bundles, thereby improving the water absorption capacity of bamboo bundles during the phenolic resin impregnation process, resulting in higher free water and bound water content. The higher initial moisture content requires a longer drying time to achieve internal moisture migration and equalization, which in turn exacerbates energy consumption and emissions; (4) In industrial production, multi-layer paving, bundling and stacking are often used, and the fiber bundles between bamboo bundles are easily intertwined and entangled, which hinders moisture migration and heat conduction channels, resulting in decreased drying efficiency and increased energy consumption; (5) After the resin-impregnated bamboo bundles are dried, they need to reach a suitable moisture content and a uniform moisture content distribution.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention discloses a method for assessing carbon emissions during the drying process of sizing bamboo bundles. Key process parameters of sizing bamboo bundles (such as average diameter, initial moisture content, degree of loosening, and thickness and number of layers) are used as input variables (carbon emission influencing factors), with carbon emissions as the target output. A pre-trained carbon emission assessment model is used to obtain predicted carbon emissions during the drying process of sizing bamboo bundles. The pre-trained carbon emission assessment model establishes a mapping relationship between the values ​​of carbon emission influencing factors and the predicted carbon emissions during the drying process of sizing bamboo bundles, significantly improving the efficiency of identifying and responding to the nonlinear coupling relationships between complex process parameters. This approach addresses the technical challenge of traditional carbon emission assessment methods for resin-impregnated bamboo bundles, which rely heavily on static process parameter settings and quantitative energy consumption estimation. These methods only provide a result-based assessment after the drying process is complete and cannot achieve dynamic coupling analysis between key process parameters and carbon emissions. In particular, when faced with multi-dimensional dynamic variables such as the average diameter, initial moisture content, degree of loosening, paving thickness, and number of layers of resin-impregnated bamboo bundles, traditional methods suffer from slow response, poor adaptability, and weak control capabilities, making it difficult to meet the advanced requirements of current green intelligent manufacturing and low-carbon processing for process perception and precise control. Attached Figure Description

[0018] Figure 1This is a simplified flowchart of the carbon emission assessment method for the drying process of resin-impregnated bamboo bundles according to the present invention.

[0019] Figure 2 This is a detailed flowchart of the carbon emission assessment method for the drying process of resin-impregnated bamboo bundles according to the present invention.

[0020] Figure 3 This is a graph showing the importance values ​​of the factors affecting carbon emissions in Example 1.

[0021] Figure 4 This is the carbon emission change curve of the unit mass and time during the drying process of the resin-impregnated bamboo bundles when laying 3 layers in Example 1.

[0022] Figure 5 This is the carbon emission change curve of the resin-impregnated bamboo bundles per unit mass and time during the drying process when laying 9 layers in Example 1.

[0023] Figure 6 This is the carbon emission change curve of the resin-impregnated bamboo bundles per unit mass and time during the drying process when 15 layers are laid in Example 1.

[0024] Figure 7 The curves show the changes in carbon emissions as a function of the mass loss of the resin-impregnated bamboo bundles when paving 3 layers in Example 1.

[0025] Figure 8 This is a curve showing the change of carbon emissions with the mass loss of the resin-impregnated bamboo bundles when 9 layers are laid in Example 1, based on the measured and predicted values.

[0026] Figure 9 This is a curve showing the change in carbon emissions as a function of the mass loss of the resin-impregnated bamboo bundles when 15 layers are laid in Example 1, compared to the predicted values.

[0027] Figure 10 This is the carbon emission change curve of the resin-impregnated bamboo bundles during the drying process at an initial moisture content of 30% in Example 2.

[0028] Figure 11 This is the carbon emission change curve of the resin-impregnated bamboo bundles during the drying process at an initial moisture content of 40% in Example 2.

[0029] Figure 12 This is the carbon emission change curve of the bamboo bundles soaked in resin during the drying process at an initial moisture content of 50% in Example 2.

[0030] Figure 13 This is the curve showing the change of carbon emissions with the measured and predicted values ​​of the resin-impregnated bamboo bundles at an initial moisture content of 30% in Example 2.

[0031] Figure 14 This is the curve showing the change of carbon emissions with the measured and predicted values ​​of the resin-impregnated bamboo bundles at an initial moisture content of 40% in Example 2.

[0032] Figure 15 This is the curve showing the change of carbon emissions with the measured and predicted values ​​of the resin-impregnated bamboo bundles at an initial moisture content of 50% in Example 2.

[0033] Figure 16 The graph shows the carbon emission changes per unit mass and time during the drying process of the resin-impregnated bamboo bundles in Example 3, when the bamboo bundles are loosened once.

[0034] Figure 17 The graph shows the carbon emission changes per unit mass and time during the drying process of the resin-impregnated bamboo bundles in Example 3, when the bundles are loosened twice.

[0035] Figure 18 The graph shows the carbon emission changes per unit mass and time during the drying process of the resin-impregnated bamboo bundles in Example 3, when the bundles were loosened three times.

[0036] Figure 19 This is a graph showing the changes in carbon emissions of Example 3 as a function of the number of times the resin-impregnated bamboo bundles are loosened, compared to the measured and predicted values. Detailed Implementation

[0037] The present invention will be further described in detail below. Unless otherwise specified, the instruments or materials used in the present invention are commercially available.

[0038] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0039] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0040] In this invention, unless otherwise explicitly specified and limited, the terms "connected," "linked," "fixed," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0041] Example 1: like Figure 1 and Figure 2 As shown in this embodiment, a method for assessing carbon emissions during the drying process of resin-impregnated bamboo bundles includes the following steps: S1. Collect the values ​​of specified carbon emission influencing factors of the resin-impregnated bamboo bundles being evaluated during the drying process; the specified carbon emission influencing factors include at least two or more of the following: number of bamboo bundle loosening times, initial moisture content, number of laying layers, average diameter of bamboo bundles, stacking method, bamboo age, and internode length. S2. The carbon emission influencing factors of the sizing bamboo bundles to be evaluated during the drying process are determined using a pre-trained carbon emission assessment model to obtain the predicted carbon emission values ​​during the drying process of the sizing bamboo bundles. The carbon emission assessment model is pre-trained to establish a mapping relationship between the values ​​of the carbon emission influencing factors and the predicted carbon emission values ​​during the drying process of the sizing bamboo bundles.

[0042] This invention discloses a method for assessing carbon emissions during the drying process of sizing bamboo bundles. Key process parameters of sizing bamboo bundles (such as average diameter, initial moisture content, degree of loosening, and thickness and number of layers) are used as input variables (carbon emission influencing factors), with carbon emissions as the target output. A pre-trained carbon emission assessment model is used to obtain predicted carbon emissions during the drying process of sizing bamboo bundles. The pre-trained carbon emission assessment model establishes a mapping relationship between the values ​​of carbon emission influencing factors and the predicted carbon emissions during the drying process of sizing bamboo bundles, significantly improving the efficiency of identifying and responding to the nonlinear coupling relationships between complex process parameters. This approach addresses the technical challenge of traditional carbon emission assessment methods for resin-impregnated bamboo bundles, which rely heavily on static process parameter settings and quantitative energy consumption estimation. These methods only provide a result-based assessment after the drying process is complete and cannot achieve dynamic coupling analysis between key process parameters and carbon emissions. In particular, when faced with multi-dimensional dynamic variables such as the average diameter, initial moisture content, degree of loosening, paving thickness, and number of layers of resin-impregnated bamboo bundles, traditional methods suffer from slow response, poor adaptability, and weak control capabilities, making it difficult to meet the advanced requirements of current green intelligent manufacturing and low-carbon processing for process perception and precise control.

[0043] This invention utilizes a pre-trained carbon emission assessment model to obtain predicted carbon emissions during the drying process of resin-impregnated bamboo bundles. The pre-trained model establishes a mapping relationship between the values ​​of influencing factors and predicted carbon emissions during the drying process. Through continuous learning and iterative optimization during pre-training, the model can accurately adapt to the fluctuating carbon emission behavior of resin-impregnated bamboo bundles under different parameter conditions. It exhibits excellent robustness and prediction accuracy, particularly in handling parameter changes during the multi-parameter linkage of the bamboo bundle drying process, overcoming the adaptation bottleneck of traditional static methods in the complex manufacturing environment of resin-impregnated bamboo bundle drying. More importantly, it achieves a fundamental shift in carbon emission monitoring during bamboo bundle drying from "post-event statistics" to "process prediction," providing solid technical support and a theoretical foundation for promoting the digital transformation and low-carbon optimization of the bamboo drying process. In addition, the model has strong trainability and self-learning ability. It can continuously update the model and optimize its performance based on the actual production data collected, ensuring that it maintains a high level of accuracy and stability in prediction under changing working conditions, and significantly improving the engineering practicality and long-term operating efficiency of the system.

[0044] In step S2, the training of the carbon emission assessment model includes: S101. Conduct a drying experiment on the resin-impregnated bamboo bundle samples, and collect the values ​​of the specified carbon emission influencing factors and the corresponding carbon emission label values ​​during the drying process of the resin-impregnated bamboo bundle samples. S102. Construct a dataset of refractory bamboo bundle samples based on the values ​​of carbon emission influencing factors during the drying process and the corresponding carbon emission label values. S103. Construct a carbon emission assessment model and use a sample dataset of resin-impregnated bamboo bundles to train the carbon emission assessment model until the model accuracy meets the requirements.

[0045] In this embodiment, step S101 specifically includes the following steps: A101. Dilute the phenolic resin with distilled water to a mass fraction of 20% and impregnate the heat-treated bamboo bundles with the resin. Then, immerse the heat-treated bamboo bundles in the phenolic resin solution, impregnate for 10 min under normal pressure, and let them stand for 12 h to drain the resin, thus obtaining the resin-impregnated bamboo bundles.

[0046] A102. The resin-impregnated bamboo bundles are laid out in a forced-air drying oven for drying. Record and calculate the average diameter, initial moisture content (0% ~ 100%), laying thickness (6 ~ 100 mm) or number of layers (1 ~ 15 layers), number of loosenings (1 ~ 3 times) or laying method (bundled or unbundled), bamboo age (3 ~ 5 years), and inter-bamboo length (10 ~ 20 cm) of the resin-impregnated bamboo bundles until they reach a constant weight. The formula for calculating the average diameter AD of the resin-impregnated bamboo bundles is shown below. The calculated average diameter ranges for the three loosening levels are 0.89 ~ 1.6 mm, 0.51 ~ 0.89 mm, and 0.30 ~ 0.51 mm, respectively.

[0047] ; in, The diameter of the fiber bundle, measured by Image-Pro Plus, is in mm; T represents the number of fiber bundles in the cross section, in pcs.

[0048] In step S101, the carbon emission label values ​​are the CO2 emissions (CO2eq) of the resin-impregnated bamboo bundles during the entire drying process and the CO2 emissions per unit mass of resin-impregnated bamboo bundles. E CO2 emissions per unit time of resin-impregnated bamboo bundles E 1. The expression for the calculation function is: ; ; ; in, The total electricity (kWh) supplied during the entire drying process. Carbon emission factor (kgCO2 / kwh); m The weight difference (kg) of the resin-impregnated bamboo bundles before and after drying. The drying time (h) for the resin-impregnated bamboo bundles.

[0049] In this embodiment, in step S101, the power consumption data during the drying process is collected in real time, the power consumption (kWh) during the drying process is recorded, and the mass change of the rubberized bamboo bundles is continuously recorded during the drying process until the rubberized bamboo bundles are dried to a constant weight. The carbon footprint of the rubberized bamboo bundles during the drying process is evaluated using the emission factor method.

[0050] In this embodiment, when collecting the values ​​of specified carbon emission influencing factors and corresponding carbon emission label values ​​of the resin-impregnated bamboo bundle samples during the drying process in step S101, it includes selecting some carbon emission influencing factors from all carbon emission influencing factors of the resin-impregnated bamboo bundle samples as specified carbon emission influencing factors, thereby obtaining the values ​​of the specified carbon emission influencing factors.

[0051] In this embodiment, step S101, when selecting some carbon emission influencing factors from all carbon emission influencing factors of the resin-impregnated bamboo bundle sample as designated carbon emission influencing factors, includes calculating the importance value for each carbon emission influencing factor among all carbon emission influencing factors of the resin-impregnated bamboo bundle sample, and selecting some carbon emission influencing factors as designated carbon emission influencing factors based on the importance values. The functional expression for calculating the importance value is: ; in, Let be the importance value of the j-th carbon emission influencing factor, and T be the total number of decision trees in the random forest model; This represents the raw prediction error of the out-of-bag (OOB) data for the t-th decision tree. The out-of-bag (OOB) prediction error of the decision tree after replacing the j-th carbon emission influencing factor; the selection of some carbon emission influencing factors as designated carbon emission influencing factors based on importance value means selecting some carbon emission influencing factors with positive importance values ​​as designated carbon emission influencing factors.

[0052] In this embodiment, step S103, constructing a carbon emission assessment model includes: denoising and normalizing the data of carbon emission influencing factors of resin-impregnated bamboo bundles (average diameter, initial moisture content, degree of loosening, and parameters such as paving thickness and number of layers), and selecting the Random Forest Regression model as the carbon emission assessment model.

[0053] Selected carbon emission influencing factors are designated as valid input variables, and the carbon emissions from the drying process are used as output variables. In this embodiment, the importance values ​​of the carbon emission influencing factors are as follows: Figure 3 As shown, the age of the bamboo bundles and the length between bamboo bundles have negative effects on carbon emissions, indicating that these two parameters have little impact on the carbon emissions during the bamboo bundle drying process and are therefore invalid input variables.

[0054] In this embodiment, the 270 datasets collected during the drying process of the resin-impregnated bamboo bundles were divided into three subsets: training set, validation set, and test set, which account for 70%, 15%, and 15% of the total data, respectively.

[0055] The parameters of the PSO-RF prediction model are configured as follows: the maximum number of iterations is set to 30, the population size is set to 15, the inertia weight is set to 0.6, and the individual and social learning factors are both set to 1.7 to obtain the carbon emission prediction value.

[0056] The parameters for the RF prediction model are configured as follows: the number of decision trees is set to 100, and the minimum number of samples for each leaf node is set to 3, to obtain the carbon emission prediction value.

[0057] In step S103, ensuring the carbon emission assessment model meets the accuracy requirements includes the following steps: B101. Three key indicators are used to evaluate the performance of the model: coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). The error between the predicted carbon emissions and the actual carbon emissions is calculated using the formula shown below.

[0058]

[0059]

[0060] In the formula: n represents the total amount of data; This represents the average of the predicted carbon emissions. Let be the predicted carbon emission value of the i-th carbon emission influencing factor; Let be the actual carbon emission value of the i-th carbon emission influencing factor.

[0061] B102. If the R² value is greater than 0.90, the RMSE value is less than 1, and the MAE value is less than 1, it indicates that the model has excellent predictive ability; otherwise, adjust the maximum number of iterations and the number of decision trees in step S103.

[0062] In the above process, the main parameters that have a significant impact on carbon emissions during the drying process of sizing bamboo bundles are obtained, and the accurate detection and prediction of carbon emissions during the drying process of sizing bamboo bundles are achieved.

[0063] Depend on Figure 4 It was found that when three layers were laid, the resin-impregnated bamboo bundles, with an average diameter ranging from 0.89 to 1.6 mm and an initial moisture content of 50%, were loosened once without bundling. The carbon emissions per unit mass of the dried resin-impregnated bamboo bundles gradually increased with the extension of drying time, reaching a range of 13.2 kgCO2 / kg. The carbon emission rate per unit drying time showed a trend of first increasing and then decreasing, with the peak carbon emission occurring at 10 h. The drying time to constant mass was 40 h.

[0064] Depend on Figure 5 It can be seen that when 9 layers are laid, the carbon emissions generated by drying a unit mass of resin-impregnated bamboo bundles are reduced by only 5.68 kgCO2 / kg compared to 3 layers. The carbon emission rate fluctuates over drying time, with a peak emission at 16 h. The drying time to a constant mass is 48 h.

[0065] Depend on Figure 6It can be seen that when 15 layers are laid, the carbon emissions generated by the drying of a unit mass of resin-impregnated bamboo bundles gradually increase, reaching a range of 13.6 kgCO2 / kg. The carbon emission rate per unit drying time also shows a trend of first increasing and then decreasing, with the peak carbon emission occurring at 36 h. The drying time to a constant mass is 100 h.

[0066] Depend on Figure 4 , Figure 5 , Figure 6 It can be seen that as the number of paving layers increases, the peak carbon emission also delays, and the overall drying time is extended, leading to an increase in carbon emissions.

[0067] Figure 7 In the middle, R 2 =0.996, RMSE=0.046, MAE=0.183, Figure 8 In the middle, R 2 =0.997, RMSE=0.046, MAE=0.171, Figure 9 In the middle, Importance=1.809, R 2 =0.986, RMSE=0.307, MAE=0.365, and the significance value of the number of paving layers reached 1.809, indicating that the number of paving layers has a significant impact on the carbon emissions of the drying process of sizing bamboo bundles. 2 All values ​​are greater than 0.99, while MSE and MAE are relatively small, both below 0.5, indicating that the carbon emission prediction values ​​have high accuracy.

[0068] Example 2: A method for assessing carbon emissions during the drying process of resin-impregnated bamboo bundles is largely the same as in Example 1, except that step S101 in this example specifically includes the following steps: A101. First, dilute the phenolic resin with distilled water to a mass fraction of 20% and impregnate the heat-treated bamboo bundles with the resin. Then, immerse the heat-treated bamboo bundles in the phenolic resin solution, soak them for 10 minutes under normal pressure, and let them age for 12 hours to drain the resin, thus obtaining the resin-impregnated bamboo bundles.

[0069] A102. The resin-impregnated bamboo bundles were laid in a forced-air drying oven for drying. Initial moisture contents were recorded at 30%, 40%, and 50%, with 9 layers, one loosening, and no bundling, until the bamboo bundles reached constant weight. The calculated average diameter range was 0.89 ~ 1.6 mm. Real-time data on energy consumption during the drying process was collected and recorded (kWh).

[0070] Depend on Figure 10It can be seen that when the initial moisture content is 30%, and 9 layers are laid, the carbon emissions generated by drying the unbundled, un-tied bamboo bundles with an average diameter ranging from 0.89 to 1.6 mm gradually increase, reaching a range of 5.2 kg CO2 / kg. The carbon emission rate per unit drying time shows a trend of first increasing, then decreasing, and then slowly increasing to equilibrium, with the peak carbon emission occurring at 16 hours.

[0071] Depend on Figure 11 It can be seen that when the initial moisture content is 40%, the carbon emissions generated by drying a unit mass of resin-impregnated bamboo bundles are relatively uniform, with the process emissions ranging from 1.4 to 4.5 kgCO2 / kg. The carbon emission rate per unit drying time shows a fluctuating trend, with the peak carbon emission occurring at 16 h.

[0072] Depend on Figure 12 It can be seen that when the initial moisture content is 50%, the carbon emissions generated by drying a unit mass of resin-impregnated bamboo bundles gradually increase to 5.04 kgCO2 / kg. The carbon emission rate per unit drying time also shows a trend of first increasing and then decreasing, with the peak carbon emission occurring at 24 h.

[0073] Depend on Figure 10 , Figure 11 and Figure 12 It can be seen that as the water content increases, the peak carbon emissions are also delayed.

[0074] Figure 13 In the middle, Importance=2.982, R 2 =0.997, RMSE=0.063, MAE=0.209, Figure 14 In the middle, Importance=2.982, R 2 =0.989, RMSE=0.308, MAE=0.365, Figure 15 In the middle, Importance=2.982, R 2 With values ​​of 0.994, RMSE = 0.395, and MAE = 0.499, the initial moisture content has a significant impact on carbon emissions during the drying process of the resin-impregnated bamboo bundles, indicating a high critical value of 2.982. In this embodiment, R... 2 All values ​​are greater than 0.98, while MSE and MAE are relatively small, both below 0.5, indicating that the carbon emission prediction values ​​have high accuracy.

[0075] Example 3: A method for assessing carbon emissions during the drying process of resin-impregnated bamboo bundles is largely the same as in Example 1, except that step S101 in this example specifically includes the following steps: A101. Dilute the phenolic resin with distilled water to a mass fraction of 20% and impregnate the heat-treated bamboo bundles with the resin. Then, immerse the heat-treated bamboo bundles in the phenolic resin solution, impregnate for 10 min under normal pressure, and let them stand for 12 h to drain the resin, thus obtaining the resin-impregnated bamboo bundles.

[0076] A102. The resin-impregnated bamboo bundles were laid in a forced-air drying oven for drying treatment. The initial moisture content was recorded as follows: 50%; 15 layers; 1, 2, and 3 layers of thinning; and unbundled laying. The resin-impregnated bamboo bundles were dried to constant weight. The calculated average diameters for thinning 1, 2, and 3 layers were 0.89 ~ 1.6 mm, 0.51 ~ 0.89 mm, and 0.30 ~ 0.51 mm, respectively.

[0077] Depend on Figure 16 It can be seen that when the bamboo bundles are laid out once with an initial moisture content of 50% and are not bundled, with average diameters ranging from 0.89 to 1.6 mm, 0.51 to 0.89 mm, and 0.30 to 0.51 mm respectively, the carbon emissions generated per unit mass of dried bamboo bundles first increase and then tend to stabilize. The carbon emission rate per unit drying time shows a trend of first increasing, then decreasing, and finally increasing again.

[0078] Depend on Figure 17 It can be seen that when the bamboo bundles are dried twice, the carbon emissions per unit mass of resin-impregnated bamboo bundles are reduced compared to when dried once. The carbon emission rate per unit drying time shows a trend of first increasing, then decreasing, and then slowly increasing again.

[0079] Depend on Figure 18 It can be seen that when the bamboo bundles are dried three times, the carbon emissions per unit mass of resin-impregnated bamboo bundles increase rapidly at first and then rise slowly. The carbon emission rate per unit drying time also shows a trend of increasing rapidly at first and then slowly.

[0080] Depend on Figure 16 , 17 As shown in Figures 1 and 18, the peak carbon emissions remain unchanged at 36 h as the dispersal increases.

[0081] Figure 19 In the middle, R 2 =0.998, RMSE=0.185, MAE=0.319, R 2 The value is greater than 0.99, the MSE and MAE are both less than 0.4, the importance value of the number of relocations is 1.182, and the carbon emission prediction value has high accuracy.

[0082] As a general inventive concept, the present invention also provides a carbon emission assessment system for the drying process of rubberized bamboo bundles, including a microprocessor and a memory interconnected thereto, the microprocessor being programmed or configured to execute the carbon emission assessment methods for the drying process of rubberized bamboo bundles in the foregoing embodiments.

[0083] As a general inventive concept, the present invention also provides a computer-readable storage medium storing a computer program or instructions that are programmed or configured to execute, via a processor, the carbon emission assessment method for the drying process of the resin-impregnated bamboo bundles in the foregoing embodiments.

[0084] As a general inventive concept, the present invention also provides a computer program product, including a computer program or instructions, which are programmed or configured to execute, via a processor, the carbon emission assessment method for the drying process of the sizing bamboo bundles described in the foregoing embodiments.

[0085] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The present invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce implementations of the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] While the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the invention. Any person skilled in the art can make many possible variations and modifications to the technical solutions of the present invention, or modify them into equivalent embodiments, without departing from the scope of the present invention. Therefore, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention, without departing from the scope of the present invention, should fall within the protection scope of the present invention.

Claims

1. A method for assessing carbon emissions during the drying process of resin-impregnated bamboo bundles, characterized in that: Includes the following steps: S1. Collect the values ​​of specified carbon emission influencing factors of the resin-impregnated bamboo bundles being evaluated during the drying process; the specified carbon emission influencing factors include at least two or more of the following: number of bamboo bundle loosening times, initial moisture content, number of laying layers, average diameter of bamboo bundles, stacking method, bamboo age, and internode length. S2. The carbon emission influencing factors of the sizing bamboo bundles to be evaluated during the drying process are determined using a pre-trained carbon emission assessment model to obtain the predicted carbon emission values ​​during the drying process of the sizing bamboo bundles. The carbon emission assessment model is pre-trained to establish a mapping relationship between the values ​​of the carbon emission influencing factors and the predicted carbon emission values ​​during the drying process of the sizing bamboo bundles.

2. The carbon emission assessment method during the drying process of resin-impregnated bamboo bundles according to claim 1, characterized in that: The training of the carbon emission assessment model includes: S101. Conduct a drying experiment on the resin-impregnated bamboo bundle samples, and collect the values ​​of the specified carbon emission influencing factors and the corresponding carbon emission label values ​​during the drying process of the resin-impregnated bamboo bundle samples. S102. Construct a dataset of refractory bamboo bundle samples based on the values ​​of carbon emission influencing factors during the drying process and the corresponding carbon emission label values. S103. Construct a carbon emission assessment model and use a sample dataset of resin-impregnated bamboo bundles to train the carbon emission assessment model until the model accuracy meets the requirements.

3. The carbon emission assessment method during the drying process of resin-impregnated bamboo bundles according to claim 2, characterized in that: The carbon emission label values ​​are the CO2 emissions (CO2eq) of the resin-impregnated bamboo bundles during the entire drying process and the CO2 emissions per unit mass of resin-impregnated bamboo bundles. E CO2 emissions per unit time of resin-impregnated bamboo bundles E 1. The expression for the calculation function is: ； ； ； in, This refers to the total amount of electricity supplied during the entire drying process. Carbon emission factor; m This represents the weight difference of the resin-impregnated bamboo bundles before and after drying. This refers to the drying time of the resin-impregnated bamboo bundles.

4. The carbon emission assessment method during the drying process of resin-impregnated bamboo bundles according to claim 2, characterized in that: The carbon emission assessment model constructed in step S103 is a random forest model.

5. The carbon emission assessment method during the drying process of resin-impregnated bamboo bundles according to claim 2, characterized in that: In step S101, when collecting the values ​​of specified carbon emission influencing factors and corresponding carbon emission label values ​​of the resin-impregnated bamboo bundle samples during the drying process, this includes selecting some carbon emission influencing factors from all carbon emission influencing factors of the resin-impregnated bamboo bundle samples as specified carbon emission influencing factors, thereby obtaining the values ​​of the specified carbon emission influencing factors.

6. The carbon emission assessment method during the drying process of resin-impregnated bamboo bundles according to claim 5, characterized in that: When selecting a subset of carbon emission influencing factors from all carbon emission influencing factors of the resin-impregnated bamboo bundle sample as designated carbon emission influencing factors, the process includes calculating an importance value for each carbon emission influencing factor among all carbon emission influencing factors of the resin-impregnated bamboo bundle sample, and selecting a subset of carbon emission influencing factors as designated carbon emission influencing factors based on the importance values.

7. The carbon emission assessment method during the drying process of resin-impregnated bamboo bundles according to claim 6, characterized in that: The function expression for calculating the importance value is: ； in, Let be the importance value of the j-th carbon emission influencing factor, and T be the total number of decision trees in the random forest model; This represents the raw prediction error of the out-of-bag data for the t-th decision tree. The out-of-bag prediction error of the decision tree after replacing the j-th carbon emission influencing factor; the selection of some carbon emission influencing factors as designated carbon emission influencing factors based on importance value means selecting some carbon emission influencing factors with positive importance values ​​as designated carbon emission influencing factors.

8. A carbon emission assessment system for the drying process of resin-impregnated bamboo bundles, comprising a microprocessor and a memory interconnected, characterized in that, The microprocessor is programmed or configured to perform the carbon emission assessment method during the drying process of the resin-impregnated bamboo bundles as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the carbon emission assessment method for the drying process of the resin-impregnated bamboo bundles as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, The computer program or instructions are programmed or configured to execute, via a processor, the carbon emission assessment method for the drying process of the resin-impregnated bamboo bundles as described in any one of claims 1 to 7.

Images