A method for predicting chloride ion concentration in concrete based on deep learning

Abstract

The present invention relates to the technical field of chloride ion concentration prediction, and discloses a method for predicting the chloride ion concentration of concrete based on deep learning. The chloride ion concentration of concrete is predicted by a deep learning model, which not only improves the accuracy and reliability of the prediction, but also optimizes the training process of the model by calculating the prediction uncertainty and dynamically adjusting the learning rate. By evaluating the prediction uncertainty, the prediction error of the model under specific conditions can be discovered in a timely manner, and the learning rate can be adjusted accordingly to ensure that the model can maintain optimal performance and stability at different training stages. By calculating the mean and standard deviation of environmental parameters, a correction factor is generated and the predicted value is adjusted. This correction method based on environmental parameters not only takes into account the influence of the external environment on the chloride ion concentration of concrete, but also improves the robustness and adaptability of the prediction results. A more accurate and reliable chloride ion concentration prediction result is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of chloride ion concentration prediction, and in particular to a method for predicting concrete chloride ion concentration based on deep learning. Background Art

[0002] Concrete is one of the most commonly used building materials in modern construction, and its durability is directly related to the safety and service life of building structures. Chloride ion corrosion is one of the main causes of premature failure of concrete structures. Chloride ions, primarily derived from environmental factors such as sea salt and deicing salt, can penetrate into concrete and, upon contact with steel reinforcement, cause corrosion, thereby weakening the overall performance of the concrete structure. Therefore, accurately predicting the chloride ion concentration and diffusion rate in concrete is crucial for assessing and preventing premature failure of concrete structures.

[0003] The process of chloride ion corrosion involves multiple physical and chemical phenomena: chloride ions migrate into concrete through pores and cracks, diffusing according to Fick's second law. The diffusion rate is affected by factors such as the concrete's density and porosity. When the chloride ion concentration exceeds a critical value, it destroys the protective layer on the steel bar surface, causing corrosion. Deep learning, a machine learning method based on artificial neural networks, can automatically learn complex nonlinear relationships from large amounts of data. It has significant advantages in processing high-dimensional and nonlinear data, making it particularly suitable for solving complex problems such as predicting chloride ion concentration in concrete. However, concrete structures require rapid predictions in many scenarios, such as bridges, tunnels, coastal areas, saline-alkali regions, and during concrete curing. Deep learning models typically contain multiple hidden layers and a large number of neurons, resulting in high computational complexity. Even on high-performance computing equipment, the model's inference time can be long. In scenarios such as bridges, tunnels, coastal areas, and saline-alkali regions, real-time monitoring of chloride ion concentration is necessary, and traditional deep learning models struggle to meet this requirement. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a method for predicting chloride ion concentration in concrete based on deep learning, comprising:

[0005] Step 1: Collect concrete structure samples and obtain chloride ion concentration, environmental parameters, curing conditions, and composition information of the concrete structure samples;

[0006] Step 2: pre-processing of chloride ion concentration, environmental parameters, curing conditions, and composition information;

[0007] Step 3: Initialize the parameters of the deep learning model. The deep learning model traverses the pre-treated chloride ion concentration, environmental parameters, curing conditions, and composition information, performs forward propagation to calculate the predicted value, calculates the loss value of the loss function, and performs back propagation to update the parameters to complete the iterative process. Repeat the iterative process until the maximum number of iterations is reached or the loss value of the loss function reaches the minimum, and then stop the iteration to obtain the trained deep learning model. After traversing the pre-treated chloride ion concentration, environmental parameters, curing conditions, and composition information, the deep learning model is verified using the validation set to obtain the verified predicted value and the verified loss value.

[0008] Step 4: Obtain the environmental parameters, curing conditions, and composition information of the concrete structure and input them into the trained deep learning model to predict the chloride ion concentration of the concrete structure. Calculate the prediction uncertainty based on the verified predicted value.

[0009] Step 5: Preset a prediction threshold and compare the prediction uncertainty with the prediction threshold. If the prediction uncertainty is greater than or equal to the prediction threshold, adjust the learning rate of the deep learning model, retrain, and continue to execute step 4 until the prediction uncertainty is less than the prediction threshold. Stop learning rate readjustment and retraining; if the prediction uncertainty is less than the prediction threshold, execute step 6.

[0010] Step 6: Calculate the correction factor based on the environmental parameters, and obtain the chloride ion concentration value of the concrete structure based on the correction factor and the prediction to obtain the final chloride ion concentration.

[0011] Furthermore, chloride ion concentration was used as a prediction label for the deep learning model.

[0012] Furthermore, the correction factor is calculated based on the environmental parameters, including:

[0013] Step 61, obtaining parameter values ​​of concrete structure environmental parameters;

[0014] Step 62, calculating the mean of the parameter value and the standard deviation of the parameter value;

[0015] Step 63 : Calculate a correction factor based on the parameter value of the environmental parameter, the mean value of the parameter value, and the standard deviation of the parameter value.

[0016] Furthermore, the standard deviation of the verified prediction value is used as the prediction uncertainty.

[0017] Furthermore, the adjustment of learning rate includes:

[0018] Step 51, preset the maximum number of training times and the maximum value of verification loss;

[0019] Step 52, obtaining the number of training times;

[0020] Step 53, calculating the prediction uncertainty after the current round of traversal and the prediction uncertainty after the previous round of traversal to obtain the uncertainty change;

[0021] Step 54, calculate the learning rate based on the prediction uncertainty, the uncertainty change, the verification loss value, the number of training times, the maximum number of training times, and the maximum verification loss value.

[0022] Furthermore, the learning rate is:

[0023] ;

[0024] ;

[0025] Where, is the learning rate, is the initial learning rate, U is the prediction uncertainty, T is the prediction threshold, L is the verification loss value, is the maximum value of verification loss, t is the number of training times, is the maximum number of training times, 、 、 are weight coefficients respectively, max is the maximum value operation, is the lower limit of the learning rate.

[0026] Furthermore, the correction factor is:

[0027] ;

[0028] In the formula, C is the correction factor, m is the adjustment coefficient, is the parameter value of the i-th environmental parameter, is the mean value of the parameter value of the i-th environmental parameter, is the standard deviation of the parameter value of the i-th environmental parameter.

[0029] Furthermore, the final chloride ion concentration is:

[0030] ;

[0031] Where, is the final chloride ion concentration, In order to predict the chloride ion concentration of concrete structure, is the sigmoid function, is the exponential decay coefficient, f is the current traversal round, F is the total traversal round, is the dynamic weight coefficient.

[0032] The embodiments of the present invention have the following technical effects:

[0033] The present invention predicts the chloride ion concentration of concrete by a deep learning model, which not only improves the accuracy and reliability of the prediction, but also dynamically adjusts the learning rate by calculating the prediction uncertainty, further optimizing the training process of the model. Specifically, by evaluating the prediction uncertainty, the present invention can promptly find the prediction error of the model under specific conditions, and adjust the learning rate accordingly to ensure that the model can maintain optimal performance and stability at different training stages. In addition, the present invention introduces a correction factor for environmental parameters, generates a correction factor by calculating the mean and standard deviation of the environmental parameters, and further adjusts the predicted value. This correction method based on environmental parameters not only takes into account the impact of the external environment on the chloride ion concentration of concrete, but also improves the robustness and adaptability of the prediction results. Ultimately, by combining the correction factor and the model prediction value, the present invention can provide more accurate and reliable chloride ion concentration prediction results, providing powerful technical support for the maintenance and management of concrete structures. This method has significant advantages in terms of real-time monitoring, early warning systems, and maintenance decision support, and can effectively prevent and delay the corrosion of concrete structures, extend their service life, reduce maintenance costs, and enhance the safety and reliability of infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 This is a flowchart of a method for predicting concrete chloride ion concentration based on deep learning provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0037] Figure 1 This is a schematic diagram of a method for predicting chloride ion concentration in concrete based on deep learning provided by an embodiment of the present invention. Figure 1 , specifically including:

[0038] Step 1: Collect concrete structure samples and obtain chloride ion concentration, environmental parameters, curing conditions, and composition information of the concrete structure samples.

[0039] Environmental parameters include, but are not limited to, temperature, humidity, rainfall, wind speed, salt content, pH, UV intensity, and air pollution index. Curing conditions include, but are not limited to, curing time, curing temperature, curing humidity, curing method, curing medium, curing frequency, curing pressure, and curing ventilation. Component information includes, but is not limited to, cement information, aggregate information, admixture information, and admixture information.

[0040] Step 2: Preprocessing of chloride ion concentration, environmental parameters, curing conditions, and composition information.

[0041] Step 3: Initialize the parameters of the deep learning model. The deep learning model traverses the pre-treated chloride ion concentration, environmental parameters, curing conditions, and composition information, performs forward propagation to calculate the predicted value, calculates the loss value of the loss function, and performs back propagation to update the parameters to complete the iterative process. Repeat the iterative process until the maximum number of iterations is reached or the loss value of the loss function reaches the minimum, and then stop the iteration to obtain the trained deep learning model. After traversing the pre-treated chloride ion concentration, environmental parameters, curing conditions, and composition information, use the validation set to verify the deep learning model to obtain the validation prediction value and validation loss value.

[0042] Select an appropriate deep learning model, such as a multilayer perceptron (MLP), convolutional neural network (CNN), or recurrent neural network (RNN), as the deep learning model architecture. Determine the number of model layers and the number of neurons in each layer. For example, you can choose an MLP model with three hidden layers, each with 128 neurons. Model parameters include weights, biases, activation functions, loss functions, and optimizers. Divide the preprocessed data into a training set and a validation set, with the training set accounting for 80% and the validation set accounting for 20%. Input the training set data into the model, perform a forward pass to calculate the predicted values, and use the selected loss function to calculate the loss between the predicted values ​​and the true values. Use the backpropagation algorithm to calculate the gradient of the loss function with respect to the model parameters, and use the optimizer to update the model parameters based on the calculated gradients. Set a maximum number of epochs (e.g., 100). Repeat the forward pass, loss calculation, backpropagation, and parameter update process until the maximum number of epochs is reached or the loss function reaches a minimum.

[0043] Using a pre-split validation set, input the trained model and perform a forward pass to calculate validation predictions. Calculate the validation loss between the validation predictions and the true values ​​using the selected loss function. Calculate performance metrics on the validation set, such as mean squared error (MSE), mean squared logarithmic error (MSLE), and R² score. Record the validation predictions and validation loss for subsequent model tuning and evaluation.

[0044] The chloride ion concentration is used as the prediction label of the deep learning model, and the predicted value obtained by the model is the chloride ion concentration.

[0045] Step 4: Obtain the environmental parameters, curing conditions, and composition information of the concrete structure, and input them into the trained deep learning model to predict the chloride ion concentration value of the concrete structure. Based on the verified predicted value, the prediction uncertainty is obtained.

[0046] The standard deviation of the verified predicted values ​​is used as the prediction uncertainty. The standard deviation reflects the degree of dispersion of the predicted values. The larger the standard deviation, the higher the prediction uncertainty of the model.

[0047] Step 5: Preset a prediction threshold and compare the prediction uncertainty with the prediction threshold. If the prediction uncertainty is greater than or equal to the prediction threshold, make a first adjustment to the learning rate of the deep learning model, retrain and continue to execute step 4 until the prediction uncertainty is less than the prediction threshold, then stop the learning rate readjustment and retraining; if the prediction uncertainty is less than the prediction threshold, execute step 6.

[0048] In this embodiment, the average value and standard deviation of all verification prediction values ​​during the training process are calculated, and the sum of the average value and the standard deviation is used as the prediction threshold.

[0049] Step 51: preset the maximum number of training times and the maximum value of verification loss.

[0050] This example sets the maximum number of training cycles to 100 to prevent overtraining of the model. A reasonable maximum validation loss is set to prevent the model from underperforming on the validation set. For example, 0.05 can be used.

[0051] Step 52: Obtain the number of training times.

[0052] Specifically refers to the current number of training times.

[0053] Step 53: Calculate the prediction uncertainty after the current round of traversal and the prediction uncertainty after the previous round of traversal to obtain the uncertainty change.

[0054] An epoch is the process by which the model performs a complete forward and backward pass on the entire training dataset. A round of training consists of performing forward and backward pass on all examples in the training set, i.e., executing one epoch of training. Forward propagation is performed on each example in the validation set using the updated model to obtain a validation prediction. Based on this validation prediction, the prediction uncertainty for the current round is calculated and recorded. The prediction uncertainty is calculated and recorded at the end of the previous epoch.

[0055] ;

[0056] is the forecast uncertainty of the rth round, is the forecast uncertainty of the r-1th round.

[0057] Step 54, calculate the learning rate based on the prediction uncertainty, the uncertainty change, the verification loss value, the number of training times, the maximum number of training times, and the maximum verification loss value.

[0058] ;

[0059] ;

[0060] Where, is the learning rate, is the initial learning rate, U is the prediction uncertainty, T is the prediction threshold, L is the verification loss value, is the maximum value of verification loss, t is the number of training times, is the maximum number of training times, 、 、 are weight coefficients respectively, max is the maximum value operation, is the lower limit of the learning rate.

[0061] This embodiment sets a maximum value operation and sets a learning rate lower limit for the learning rate. When the calculated learning rate is less than or equal to the learning rate lower limit, , when the calculated learning rate is greater than the lower limit of the learning rate, the learning rate is calculated .

[0062] By dynamically adjusting the learning rate based on prediction uncertainty, uncertainty variation, validation loss, number of training runs, maximum number of training runs, and maximum validation loss, this method significantly improves model performance in predicting chloride ion concentration in concrete. Specifically, this method not only flexibly adjusts the learning rate based on the model's current uncertainty and performance on the validation set, but also dynamically balances model exploration and exploitation during training, avoiding overfitting and underfitting. The introduction of prediction uncertainty enables the model to automatically reduce the learning rate when uncertainty is high, enabling more detailed parameter optimization and improving prediction stability. Considering uncertainty variation helps the model identify fluctuations during training and adjust the learning strategy accordingly. The combination of validation loss and maximum validation loss ensures that the model consistently performs optimally on unseen data, enhancing its generalization ability. Furthermore, by limiting the number of training runs and maximum number of training runs, the model achieves optimal performance within a limited training time, conserving computational resources. In summary, this adaptive learning rate adjustment method not only improves the model's prediction accuracy and stability, but also enhances its adaptability to diverse environments and conditions, providing more reliable technical support for subsequent chloride ion concentration prediction.

[0063] In another embodiment, when the prediction uncertainty is less than the prediction threshold, in this embodiment, the learning rate is preferably also appropriately adjusted:

[0064] ;

[0065] In this formula, the minimum validation loss is taken into account Even when uncertainty is low, the model may not have fully converged. Increasing the learning rate appropriately can accelerate convergence, especially in the early stages of training. In the early stages of training, model uncertainty is typically high, so a larger learning rate can be used to quickly approach the optimal solution. Later in training, when model uncertainty is low, a smaller learning rate can be used to fine-tune model parameters and improve model accuracy.

[0066] Step 6: Calculate the correction factor based on the environmental parameters, and obtain the chloride ion concentration value of the concrete structure based on the correction factor and the prediction to obtain the final chloride ion concentration.

[0067] Step 61: Obtain parameter values ​​of concrete structure environmental parameters.

[0068] Step 62: Calculate the mean and standard deviation of the parameter values.

[0069] Step 63 : Calculate a correction factor based on the parameter value of the environmental parameter, the mean value of the parameter value, and the standard deviation of the parameter value.

[0070] By calculating correction factors based on the parameter values, mean values, and standard deviations of environmental parameters, the model's accuracy and reliability in predicting chloride ion concentration in concrete structures can be significantly improved. This approach not only captures the changing trends of environmental parameters but also quantifies the impact of these changes on chloride ion concentration. Specifically, the mean and standard deviation of the parameter values ​​provide statistical characteristics of the environmental parameters, helping to identify their distribution and fluctuations. The introduction of correction factors enables the model to dynamically adjust its predictions under varying environmental conditions, better adapting to changes in practical application scenarios. For example, in environments with large temperature and humidity fluctuations, the correction factors can be adjusted based on the actual values ​​and statistical characteristics of these parameters, ensuring that the predictions are more accurate than those in the real world. Furthermore, this approach reduces the risk of overfitting and improves its generalization ability, making the model's predictions more stable and accurate across diverse environmental conditions. In summary, the correction factor calculation method based on the statistical characteristics of environmental parameters provides a more scientific and effective means for predicting chloride ion concentration.

[0071] ;

[0072] In the formula, C is the correction factor, m is the adjustment coefficient, is the parameter value of the i-th environmental parameter, is the mean value of the parameter value of the i-th environmental parameter, is the standard deviation of the parameter value of the i-th environmental parameter.

[0073] ;

[0074] Where, is the final chloride ion concentration, In order to predict the chloride ion concentration of concrete structure, is the sigmoid function, is the exponential decay coefficient, f is the current traversal round, F is the total traversal round, is the dynamic weight coefficient.

[0075] Calculating the final predicted value using the above formula has the following outstanding advantages:

[0076] First, the formula cleverly integrates multiple important factors, including the initial prediction value, the sigmoid function, the exponential decay coefficient, the current iteration round, the total iteration rounds, and the dynamic weight coefficient. This ensures that the final prediction result not only depends on the original prediction value, but also fully considers the dynamic changes and environmental factors during the model training process, thereby greatly improving the accuracy of the prediction.

[0077] Secondly, the introduction of the sigmoid function can smooth out changes in predicted values ​​to a certain extent, preventing large deviations in overall predictions caused by individual extreme values. Furthermore, the inclusion of an exponential decay coefficient and a dynamic weight coefficient enables the model to converge quickly in the early stages of training, while allowing for slow adjustments as convergence approaches, effectively avoiding issues such as premature stopping or overfitting.

[0078] Finally, the formula's flexibility lies in its ability to adapt to different application scenarios and data characteristics by adjusting the values ​​of various parameters, thereby achieving personalized prediction results. Overall, this design ensures both the accuracy of the prediction results and the robustness and applicability of the model, making it an efficient and practical prediction method.

[0079] It should be noted that the terms used in the present invention are only for describing specific embodiments and are not intended to limit the scope of this application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular and may also include the plural. The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the presence of other identical elements in the process, method or device comprising the elements.

[0080] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the internal parts of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting chloride ion concentration in concrete based on deep learning, characterized in that: include: Step 1: Collect concrete structure samples and obtain chloride ion concentration, environmental parameters, curing conditions, and composition information of the concrete structure samples; Step 2: pre-processing of chloride ion concentration, environmental parameters, curing conditions, and composition information; Step 3: Initialize the parameters of the deep learning model. The deep learning model traverses the pre-treated chloride ion concentration, environmental parameters, curing conditions, and composition information, performs forward propagation to calculate the predicted value, calculates the loss value of the loss function, and performs back propagation to update the parameters to complete the iterative process. Repeat the iterative process until the maximum number of iterations is reached or the loss value of the loss function reaches the minimum, and then stop the iteration to obtain the trained deep learning model. After traversing the pre-treated chloride ion concentration, environmental parameters, curing conditions, and composition information, the deep learning model is verified using the validation set to obtain the verified predicted value and the verified loss value. Step 4: Obtain the environmental parameters, curing conditions, and composition information of the concrete structure and input them into the trained deep learning model to predict the chloride ion concentration of the concrete structure. Calculate the prediction uncertainty based on the verified predicted value. Step 5: Preset a prediction threshold and compare the prediction uncertainty with the prediction threshold. If the prediction uncertainty is greater than or equal to the prediction threshold, adjust the learning rate of the deep learning model, retrain, and continue to execute step 4 until the prediction uncertainty is less than the prediction threshold. Stop learning rate readjustment and retraining; if the prediction uncertainty is less than the prediction threshold, execute step 6. Step 6: Calculate the correction factor based on the environmental parameters, and obtain the chloride ion concentration value of the concrete structure based on the correction factor and the prediction to obtain the final chloride ion concentration.

2. A method for predicting chloride ion concentration in concrete based on deep learning according to claim 1, characterized in that: Chloride ion concentration was used as the predicted label for the deep learning model.

3. A method for predicting chloride ion concentration in concrete based on deep learning according to claim 2, characterized in that: Calculate correction factors based on environmental parameters, including: Step 61, obtaining parameter values ​​of concrete structure environmental parameters; Step 62, calculating the mean of the parameter value and the standard deviation of the parameter value; Step 63 : Calculate a correction factor based on the parameter value of the environmental parameter, the mean value of the parameter value, and the standard deviation of the parameter value.

4. A method for predicting chloride ion concentration in concrete based on deep learning according to claim 3, characterized in that: The standard deviation of the verified predicted value is used as the prediction uncertainty.

5. A method for predicting chloride ion concentration in concrete based on deep learning according to claim 4, characterized in that: Adjustment of learning rate, including: Step 51, preset the maximum number of training times and the maximum value of verification loss; Step 52, obtaining the number of training times; Step 53, calculating the prediction uncertainty after the current round of traversal and the prediction uncertainty after the previous round of traversal to obtain the uncertainty change; Step 54, calculate the learning rate based on the prediction uncertainty, the uncertainty change, the verification loss value, the number of training times, the maximum number of training times, and the maximum verification loss value.

6. A method for predicting chloride ion concentration in concrete based on deep learning according to claim 5, characterized in that: The learning rate is: ； ； Where, is the learning rate, is the initial learning rate, U is the prediction uncertainty, T is the prediction threshold, L is the verification loss value, is the maximum value of verification loss, t is the number of training times, is the maximum number of training times, 、 、 are weight coefficients respectively, max is the maximum value operation, is the lower limit of the learning rate; It represents the change in prediction uncertainty of the rth training round relative to the r-1th training round.

7. The method for predicting chloride ion concentration in concrete based on deep learning according to claim 3, characterized in that: The correction factor is: ； In the formula, C is the correction factor, m is the adjustment coefficient, is the parameter value of the i-th environmental parameter, is the mean value of the parameter value of the i-th environmental parameter, is the standard deviation of the parameter value of the i-th environmental parameter.

8. The method for predicting chloride ion concentration in concrete based on deep learning according to claim 1, characterized in that: The final chloride ion concentration is: ； Where, is the final chloride ion concentration, In order to predict the chloride ion concentration of concrete structure, is the sigmoid function, is the exponential decay coefficient, f is the current traversal round, F is the total traversal round, is the dynamic weight coefficient, and C is the correction factor.

Images