Protection device optimization design method and computer readable storage medium

Abstract

The invention discloses a protection device optimization design method and a computer readable storage medium, and belongs to the technical field of bridge engineering structure optimizing.The method comprises the steps that constraints and targets of a protection device are designed according to project basic information; obtaining primary selection parameters and a similarity ratio coefficient set of the protection device according to the constraint and the target; establishing a prediction model of the crushing performance of the protection device, obtaining basic design parameters of the protection device according to the primarily selected parameters and the similarity ratio coefficient set, calculating crushing curves of the protection device under different basic design parameters, and further calculating the protection performance and the construction cost of the protection device under the ship collision condition. And if the fortification requirement and the engineering cost requirement are met, entering an optimization design result set, and returning a similarity ratio coefficient set to carry out the next round of iterative calculation. According to the protection device optimization design method and the computer readable storage medium, constraint conditions and design targets in various actual engineering projects are met based on the extreme learning machine prediction model, and the design efficiency of the protection device is improved.

Description

Technical Field

[0001] The present invention relates to the field of bridge engineering structure optimization, and particularly to an optimization design method for a protection device and a computer-readable storage medium. Background Art

[0002] In the optimization design of bridge engineering structures, improving the anti-impact performance of protection devices is a key link to ensure bridge safety. Currently, the industry generally adopts optimization design methods such as using high-strength materials to enhance the anti-impact ability of protection devices, setting anti-collision blocks around the main supporting structures of bridges to absorb impact energy, and setting vegetation or green belts on both sides of bridges to beautify the environment and assist in absorbing impact force. However, these methods face many challenges in practical applications: First, due to the significant differences in the structural forms and surrounding environments of different bridges, existing protection devices often show insufficient adaptability when dealing with specific working conditions; Second, the impact crushing performance of protection devices is affected by the coupling effects of multiple structural parameters and complex non-linear relationships, and traditional modeling methods are difficult to comprehensively describe this complexity, resulting in the difficulty of accurately predicting and controlling the protection effect; In addition, high maintenance costs also limit the wide application of existing protection devices. If the protection device fails to effectively resist impact, it may lead to serious damage to the bridge structure and even cause serious consequences such as casualties. Summary of the Invention

[0003] The present invention aims to provide an optimization design method for a protection device and a computer-readable storage medium that meet multiple constraint conditions and design goals in actual engineering projects. The optimization design method for the protection device is based on an extreme learning machine prediction model, which can adapt to changing engineering requirements and effectively solve the deficiencies of existing protection devices in meeting multiple constraint conditions and design goals of actual engineering projects.

[0004] To achieve the above object, the technical solution of the present invention is:

[0005] An optimization design method for a protection device, comprising:

[0006] Step S1: Define the basic information of the project;

[0007] Step S2: Design the constraints and objectives of the protection device according to the basic information of the project;

[0008] Step S3: Obtain the initial selection parameters and similarity ratio coefficient set of the protection device according to the constraints and objectives of the protection device;

[0009] Step S4: Establish a prediction model for the crushing performance of the protection device; according to the initial selection parameters and similarity ratio coefficient set of the protection device, obtain multiple groups of basic design parameters of the protection device, and use the established prediction model to calculate the crushing curves of the protection device under different basic design parameters;

[0010] Step S5: Calculate the protection performance of the protection device under ship collision conditions according to the crushing curve; if the fortification requirements are met, enter the optimized design result set, and return to the similarity ratio coefficient set for the next round of iterative calculation;

[0011] Step S6: Calculate the project cost of the protection device according to the basic design parameters and the similarity ratio coefficient; if the project cost requirements are met, enter the optimized design result set, and return to the similarity ratio coefficient set for the next round of iterative calculation.

[0012] Optionally, the project basic information includes: pier width, water area surplus scale, fortification requirements and project cost requirements.

[0013] Optionally, the constraints of the protection device in step S2 include: the width of the protection device is less than or equal to the water area surplus scale, and the axial length of the protection device is greater than the pier width but does not exceed 1.1 times the pier width.

[0014] Optionally, the objectives of designing the protection device in step S2 include: meeting the fortification requirements and meeting the project cost requirements; meeting the fortification requirements includes: the impact force value reduced by the protection device is less than or equal to the peak impact force that the pier can withstand; meeting the project cost requirements includes: on the basis of meeting the fortification requirements, select the solution with the lowest project cost.

[0015] Optionally, in step S3, the preliminary selection parameters include: the width of the protection device, the axial length of the protection device, the type of the protection device, the shell thickness, the thickness of the circumferential angle steel plate, the thickness of the axial angle steel plate, the circumferential angle steel spacing and the type of filling material; calculate the width of the protection device and the axial length of the protection device according to the constraints of the protection device, and arrange the widths of the protection devices in descending order to form a width parameter set of the protection device; calculate the similarity ratio coefficient set according to the width parameter set of the protection device and the ratio of the model sizes; the types of the protection devices include: steel protection device, steel-PUF protection device and steel-PUF-GFRP protection device; determine the recommended type of the protection device according to the axial length of the protection device.

[0016] Optionally, establishing a prediction model for the crushing performance of the protection device in step S4 includes: training based on an extreme learning machine prediction model to obtain the relationship between the basic design parameters and the crushing performance; the input variables of the extreme learning machine prediction model include: deformation amount, shell thickness, thickness of circumferential angle steel plates, thickness of axial angle steel plates, circumferential angle steel spacing, and filling material type, and the filling material type includes: steel, steel-PUF, and steel-GFRP-PUF; the output variable of the extreme learning machine prediction model includes: impact force value; the crushing curve is a curve of the impact force value of the protection device changing with the deformation amount.

[0017] Optionally, in step S4, the basic design parameter = the initial selection parameter × the similarity ratio coefficient in the similarity ratio coefficient set.

[0018] Optionally, calculating the protection performance of the protection device under ship collision conditions in step S5 includes: evaluating the protection performance of the protection device under ship collision conditions for all similarity ratio coefficients using the DME method.

[0019] Optionally, returning the similarity ratio coefficient set for the next round of iterative calculation includes: reselecting a similarity ratio coefficient in the similarity ratio coefficient set to generate a set of corresponding basic design parameters for calculation.

[0020] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements a protection device optimization design method as described in any one of the above.

[0021] Based on the extreme learning machine prediction model, the iterative optimization of the protection device structure in this application meets the constraint conditions and design goals in various actual engineering projects, providing a reliable basis and guidance for actual engineering applications. By constructing an extreme learning machine prediction model, the crushing performance of the protection device can be quickly predicted based on known basic design parameters, reducing the time of model tests and numerical simulations, and significantly improving the design efficiency of the protection device. At the same time, the extreme learning machine prediction model provides data-driven technical support for the optimization and evaluation of the protection device performance, realizing the rapid optimization and performance evaluation of the multi-objective optimization problem of the protection device, helping to achieve the balance between performance and engineering cost, and further promoting the design and optimization process of the protection device.

[0022] To make the above features and advantages of this application more obvious and understandable, specific embodiments are given below and are described in detail in conjunction with the accompanying drawings as follows. Brief Description of the Drawings

[0023] Figure 1 It is a flowchart of the protection device optimization design method proposed in this application.

[0024] Figure 2Schematic diagram of the neural network structure of the ELM prediction model.

[0025] Figure 3 Schematic diagram of the crushing curve.

[0026] Figure 4 Schematic diagram of the relationship between the calculation accuracy and the number of iterations of the ELM prediction model.

[0027] Figure 5 In figure (a) of [], it is a schematic diagram comparing the true impact force value and the predicted impact force value of the training set.

[0028] Figure 5 In figure (b) of [], it is a schematic diagram comparing the true impact force value and the predicted impact force value of the test set.

[0029] Figure 6 In figure (a) of [], it is a schematic diagram of the coefficient of determination R 2 of the training set.

[0030] Figure 6 In figure (b) of [], it is a schematic diagram of the coefficient of determination R 2 of the test set.

[0031] Figure 7 Comparison chart of the crushing curves of the ELM prediction model and the FEA model.

[0032] Figure 8 In figure (a) of [], it is a schematic diagram of the bridge of Class III waterway (1000 DWT) under working condition 1.

[0033] Figure 8 In figure (b) of [], it is a schematic diagram of the bridge of Class III waterway (1000 DWT) under working condition 2.

[0034] Figure 8 In figure (c) of [], it is a schematic diagram of the bridge of Class III waterway (1000 DWT) under working condition 3.

[0035] Figure 9 In figure (a) of [], it is a schematic diagram of the relationship between the number of iterations and the peak impact force of the ELM prediction model under working condition 1.

[0036] Figure 9 In figure (b) of [], it is a schematic diagram of the relationship between the number of iterations and the project cost of the ELM prediction model under working condition 1.

[0037] Figure 10 In figure (a) of [], it is a schematic diagram of the relationship between the number of iterations and the peak impact force of the ELM prediction model under working condition 2.

[0038] Figure 10 In figure (b) of [], it is a schematic diagram of the relationship between the number of iterations and the project cost of the ELM prediction model under working condition 2.

[0039] Figure 11 In Figure (a), it is a schematic diagram of the number of iterations and the peak impact force of the ELM prediction model in working condition 3.

[0040] Figure 11 In Figure (b), it is a schematic diagram of the number of iterations of the ELM prediction model and the project cost in working condition 3. Specific implementation manners

[0041] To make the objectives and technical solutions of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the described embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0042] In an embodiment of the present application, please refer to Figure 1 , Figure 1 which is a flowchart of the optimization design method for the protection device proposed in the present application, including: steps S1 to S6.

[0043] Step S1: Define the basic information of the project.

[0044] Step S2: Design the constraints and objectives of the protection device according to the basic information of the project.

[0045] Step S3: Obtain the initial selection parameters and similarity ratio coefficient set of the protection device according to the constraints and objectives of the protection device.

[0046] Step S4: Establish a prediction model for the crushing performance of the protection device; according to the initial selection parameters and similarity ratio coefficient set of the protection device, obtain multiple groups of basic design parameters of the protection device, and use the established prediction model to calculate the crushing curves of the protection device under different basic design parameters.

[0047] Step S5: Calculate the protection performance of the protection device under ship collision conditions according to the crushing curve of the protection device; if the fortification requirements are met, enter the optimization design result set and return to the similarity ratio coefficient set for the next round of iterative calculation.

[0048] Step S6: Calculate the project cost of the protection device according to the basic design parameters and similarity ratio coefficient; if it meets the requirement of being less than the project cost of the basic information of the project, enter the optimization design result set and return to the similarity ratio coefficient set for the next round of iterative calculation.

[0049] In step S1, the basic information of the project includes: pier width, water area surplus scale, fortification requirements and project cost requirements.

[0050] In step S2, the pier width, the water area surplus scale, the fortification requirements, and the project cost requirements jointly determine the size and performance requirements of the protection device. Among them, the pier width and the water area surplus scale directly limit the width and the axial length of the protection device. The width of the protection device cannot exceed the water area surplus scale; the axial length of the protection device must be coordinated with the pier width, that is, the axial length of the protection device should be greater than the pier width but generally not exceed 1.1 times of it. The constraints of the protection device are expressed by the formula:

[0051]

[0052] Wherein, W F is the width of the protection device, W B is the water area surplus scale, L B is the pier width, L F is the axial length of the protection device. This range of the axial length of the protection device provides the necessary flexibility for the layout of the protection device, and at the same time allows a certain number of rubber damping elements to be arranged between the protection device and the pier body to adjust the gap between the two. This design flexibility not only helps to buffer the energy transfer during ship impact, but also provides an operation space for further optimization design.

[0053] As an example, the objectives of designing the protection device in step S2 include: meeting the fortification requirements and the project cost requirements. Meeting the fortification requirements and the project cost requirements is the core objective of the optimization of the protection device. Meeting the fortification requirements includes: ensuring that the protection performance of the protection device meets the minimum fortification requirements, that is, the impact force value reduced by the protection device should be less than the peak impact force that the pier can withstand. Meeting the project cost requirements includes: on the basis of meeting the fortification requirements, the ultimate goal of the optimization design of the protection device is to reduce the project cost, that is, through means such as comparison and selection of different schemes, to maximize the economic benefits under the premise of meeting the fortification requirements. The objectives of the protection device are expressed by the formula:

[0054]

[0055] Wherein, F F is the impact force reduced by the protection device, F min is the peak impact force that the pier can withstand, E c is the project cost, and min is the minimum value.

[0056] In step S3, the preliminary selection parameters include: the width of the protection device, the axial length of the protection device, the type of the protection device, the thickness of the outer shell, the thickness of the circumferential angle steel plate, the thickness of the axial angle steel plate, the circumferential angle steel spacing, and the type of filling material. Calculate the width and axial length of the protection device according to the constraints of the protection device obtained in step S2; the thickness of the outer shell, the thickness of the circumferential angle steel plate, the thickness of the axial angle steel plate, the circumferential angle steel spacing, and the type of filling material are the initial parameters of the set protection device. Arrange the calculated widths of the protection devices in descending order to form a width parameter set of the protection devices for subsequent optimization, and then calculate a similarity ratio coefficient set according to the ratio of the width parameter set of the protection devices to the model size; wherein, the similarity ratio coefficient set includes the similarity ratio coefficients calculated according to the ratio of the width of the protection device to the model size.

[0057] Furthermore, the types of protection devices include: steel protection devices, steel-PUF protection devices, steel-PUF-GFRP protection devices, etc.; determine the recommended type of protection device according to the axial length of the protection device. For example, in the scenario where the width of the pier is relatively narrow, it is recommended to use a steel-PUF-GFRP protection device because the axial length of the protection device is relatively short, and the energy absorption capacity per unit length needs to be maximized to ensure meeting the requirements of the protection performance; in the scenario where the width of the pier is relatively wide, it is recommended to use a steel protection device. Although its energy absorption capacity per unit length is relatively low, its structure is more easily fitted to the bow of the ship and has stronger adaptability, thus effectively dispersing the impact force; in the scenario where the width of the pier is moderate, it is recommended to use a steel-PUF protection structure because it can achieve a good balance between the protection performance and the energy absorption capacity.

[0058] Furthermore, the model size is expressed as the size of the scaled-down model of the protection device for experimental testing. Since the size of the protection device is very large and it is difficult to conduct full-scale tests, it is necessary to scale down the protection device so that the scaled-down model of the protection device meets the requirements of laboratory tests, that is, the scaled-down model of the protection device can be placed in the laboratory.

[0059] In step S4, establishing the prediction model of the crushing performance of the protection device includes: training based on the extreme learning machine prediction model (ELM) to obtain the relationship between the basic design parameters of the protection device and the crushing performance. In the embodiments of the present application, taking the ELM prediction model of the machine learning model as an example, it can efficiently capture the potential correlations and action mechanisms among the basic design parameters, thereby providing higher accuracy for the prediction of the crushing performance. The ELM prediction model includes: an input layer, a hidden layer, and an output layer. The input layer includes: N input variables; the hidden layer includes: hidden layer nodes.

[0060] Specifically, define a training set containing N samples. Please refer to Figure 2 , Figure 2Schematic diagram of the neural network structure of the ELM prediction model, using [x 1 , x 2 , x 3 ··· x N to represent a given set of input variables; represents the weight from the Nth input variable of the input layer to the jth neuron of the hidden layer, and b j represents the threshold of the jth neuron. Among them, the weight from the Nth input variable of the input layer to the jth neuron of the hidden layer and the threshold of the neurons in the hidden layer are directly determined by random initialization and do not need to be further adjusted after setting, thus avoiding the multiple weight and bias updates required by the complex backpropagation algorithm in the BP neural network and greatly reducing the computational complexity. The calculation between the hidden layer with hidden layer nodes and the output layer is performed using the output weight matrix, which is expressed by the formula:

[0061]

[0062] where, represents the output weight matrix between the hidden layer with hidden layer nodes and the output layer, represents the output weight from the th hidden layer node to the jth neuron, T represents the target matrix of the output variable, represents the th output variable, and m represents the dimension of the target matrix T.

[0063] Multiply the jth input variable x j by the weight w j corresponding to the input variable x ji to the ith neuron, and then add the threshold of this neuron. After passing through the activation function f(x j ), the output value y j of the jth neuron is obtained. The activation function of the single hidden layer neural network with hidden layer nodes is:

[0064]

[0065] where, x j represents the jth input variable, β i represents the output weight matrix between the ith hidden layer and the output layer, and w ji represents the weight from the jth input variable x j to the ith neuron.

[0066] Rewrite formula (5) into matrix form:

[0067] H·β = T

[0068] Formula (6) Further, from Formula (6), we get:

[0069] β = H -1 ·T

[0070] Formula (7)

[0071] Among them, H represents the output matrix of the hidden layer, which is directly determined by the analytical solution without relying on the iterative optimization process, making the overall calculation more efficient. β represents the output layer matrix. The output layer matrix β and the output matrix H of the hidden layer are expressed by the formula as:

[0072]

[0073] In this embodiment, 27 groups of real crushing curve data of three types of protective devices are used to establish a database, and a total of 1420 groups of input variables are obtained. The input variables are divided into a training set (80%) and a test set (20%) according to a ratio. 1136 groups of input variables in the training set are used for the training of the ELM prediction model, and the trained ELM prediction model is tested for reliability through 284 groups of input variables in the test set.

[0074] As an example, the input variables of the ELM prediction model include: deformation amount, shell thickness, thickness of circumferential angle steel plate, thickness of axial angle steel plate, circumferential angle steel spacing, and filling material type. The filling material types include: steel, steel-PUF, and steel-GFRP-PUF; the output variables of the ELM prediction model include: impact force value. Please refer to Figure 3 , Figure 3 which is a schematic diagram of the crushing curve. The crushing curve is the curve of the impact force value of the protective device changing with the deformation amount. The selection of these input variables aims to comprehensively characterize the basic design parameters of the protective device to ensure that the established prediction model can accurately reflect the relationship between the crushing performance of the protective device and the basic design parameters.

[0075] Further, since the data of the input variables used have different data magnitudes, it is necessary to solve this through data normalization. Scaling the data ensures the same treatment for all input variables and avoids causing bias in the ELM prediction model. The formula for data normalization is expressed as follows:

[0076]

[0077] Among them, x i represents the i-th input variable, x i,norm represents the data normalization value of the i-th input variable after data normalization, x max represents the maximum value of the selected input variables, and x min represents the minimum value of the selected input variables.

[0078] Further, during the training process, the input variables are randomly permuted to expose the ELM prediction model to more diverse data and to exclude the similarity of the input variables from the same reference.

[0079] Further, the training dataset is learned and trained by the ELM prediction model to obtain a neural network with the weights of each part determined, thereby constructing the relationship between the input variables and the output variables. Please refer to Figure 4 , Figure 4 which is a schematic diagram of the relationship between the calculation accuracy and the number of iterations of the ELM prediction model. The maximum number of iterations is set to 100. It can be seen from Figure 4 that as the number of iterations increases, the relative error of the ELM prediction model gradually decreases. After the number of iterations exceeds 50 times, the calculation relative error of the model can be stabilized within 0.2%. It can be seen that with the increase of the number of iterations, although the convergence speed decreases, relatively high calculation accuracy can be achieved. Therefore, it is necessary to limit the number of iterations to avoid overfitting the model and controlling the length of the training process.

[0080] As an example, when performing inversion analysis based on the ELM prediction model, the number of neurons in the hidden layer is determined to be 100 by the trial-and-error method. A single-hidden-layer neural network is trained using 1136 groups of input variables in the training set and their corresponding true impact force values of the crushing curves. After the training is completed, 284 groups of input variables in the test set are used for cross-validation. The 284 groups of input variables in the test set are randomly distributed. The impact force values of the crushing curves corresponding to these input variables in the test set are input into the trained ELM prediction model. After being processed by the ELM prediction model, the predicted impact force values of the 284 groups of input variables in the test set are output to evaluate the prediction accuracy of the ELM prediction model.

[0081] Please refer to Figure 5 , Figure 5 in which Figure (a) is a schematic diagram of the comparison between the true impact force values and the predicted impact force values of the training set, Figure 5 in which Figure (b) is a schematic diagram of the comparison between the true impact force values and the predicted impact force values of the test set. The true impact force values and the predicted impact force values are compared to test the performance and accuracy of the ELM prediction model.

[0082] Further, please refer to Figure 6 , Figure 6 in which Figure (a) is a schematic diagram of the coefficient of determination R 2 of the training set, Figure 6 in which Figure (b) is a schematic diagram of the coefficient of determination R 2 of the test set. The coefficient of determination R 2 is used as a measure to evaluate the ability of the ELM prediction model to explain the variability of the data. Therefore, the coefficient of determination R2 A higher value indicates a better fit of the ELM prediction model. By comparing the coefficient of determination R of the randomly assigned training set and test set 2 to evaluate the performance of the ELM prediction model, the coefficient of determination R 2 is expressed by the formula:

[0083]

[0084] where y i represents the true impact force value of the output of the j-th neuron, represents the predicted impact force value of the i-th input variable, N represents the number of samples in the training set or test set, represents the average value of y i . After calculation, the coefficient of determination R of the training set in this embodiment 2 is 0.9738, and the coefficient of determination R of the test set 2 is 0.9392, and there is no obvious overfitting phenomenon.

[0085] As an example, after establishing the prediction model of the crushing performance of the protection device, according to the preliminary selection parameters of the protection device and the similarity ratio coefficient set in step S3, multiple groups of basic design parameters of the protection device are obtained. Specifically, the basic design parameter = the preliminary selection parameter × the similarity ratio coefficient in the similarity ratio coefficient set. Input the basic design parameters of the test ELM prediction model into the trained ELM prediction model. A set of basic design parameters of the test ELM prediction model is shown in Table 1. Compare the crushing curve obtained by the ELM prediction model with the crushing curve calculated by the finite element model FEA model. Please refer to Figure 7 , Figure 7 is the comparison chart of the crushing curves of the ELM prediction model and the FEA model. The comparison results show that the prediction results of the ELM prediction model are in good agreement with the calculation results of the FEA model. The effective deformation amounts obtained by the ELM prediction model and the FEA model are 1.3 m and 1.29 m respectively. The peak impact force of the ELM prediction model in the elastic stage is 0.76 MN, and that of the FEA model is 0.8 MN. The calculation efficiency brought by the ELM prediction model is greatly improved, and it has good application prospects in structural optimization design.

[0086] Table 1 Basic design parameters of the test ELM prediction model

[0087]

[0088] As an example, a set of data of basic design parameters corresponds to a similarity ratio coefficient. After obtaining the similarity ratio coefficient, the basic design parameters of the protection device obtained under the similarity ratio coefficient are often not integers. To meet the requirement of integer data in the project, the method of rounding is used to correct the basic design parameters to obtain the integer data of the basic design parameters.

[0089] In step S5, calculating the protection performance of the protection device under ship collision conditions includes: quickly evaluating the protection performance of the protection device under ship collision conditions at all similarity ratio coefficients by the DME method. The returning the similarity ratio coefficient set for the next round of iterative calculation includes: reselecting a similarity ratio coefficient from the similarity ratio coefficient set and generating a set of corresponding basic design parameters for calculation.

[0090] In step S6, calculating the project cost of the protection device at all similarity ratio coefficients; the returning the similarity ratio coefficient set for the next round of iterative calculation includes: reselecting the similarity ratio coefficient from the similarity ratio coefficient set and generating a set of corresponding basic design parameters for calculation.

[0091] In an embodiment of the present application, three Class III waterway (1000 DWT) bridges are selected as the objects of optimization design. Please refer to Figure 8 , Figure 8 Figure (a) in Figure 8 is a schematic diagram of a Class III waterway (1000 DWT) bridge under working condition 1, Figure 8 Figure (b) in

[0092] is a schematic diagram of a Class III waterway (1000 DWT) bridge under working condition 2,

[0093]

[0094] Figure (c) in

[0095] is a schematic diagram of a Class III waterway (1000 DWT) bridge under working condition 3. The bridge types, spans, and waterway widths of these three bridges are all different, and the project basic information is shown in Table 2. Based on the above optimization design process, the protection devices of each bridge are optimized.

[0092] Table 2 Project basic information of three Class III waterway (1000 DWT) bridges

[0093]

[0094] Among them, on the premise of meeting the anti-collision performance requirements, the design of the protection devices of the above three Class III waterway (1000 DWT) bridges strives to be optimized within the project cost range. For the convenience of comparison, the project cost is only the material price of the protection device on the ship impact side. In actual projects, the project cost of the protection device is also affected by comprehensive factors such as the overall scale of the bridge pier and construction and installation. At the same time, in the design process, it is assumed that the representative ship types are all straight-tilted bow ships, and the possibility of ships with flying shear type, bulbous bow type, etc. bypassing the protection device and directly hitting the bridge pier is not considered.

[0095] As an example, after obtaining the basic information of the project, first design the constraints and objectives of the protection device according to the basic information of the project; secondly, obtain the preliminary selection parameters and similarity ratio coefficient sets of the protection device according to the constraints and objectives of the protection device, where the preliminary selection parameters include: the width of the protection device, the axial length of the protection device, and the type of the protection device, and the similarity ratio coefficient sets include: the width parameter set of the protection device and the similarity ratio coefficient set of the ratio of the model size; then, according to the preliminary selection parameters and similarity ratio coefficient sets of the protection device, obtain the basic design parameters of the protection device, establish a prediction model for the crushing performance of the protection device, and calculate the crushing curves of the protection device under different basic design parameters; then, according to the crushing curves of the protection device, calculate the protection performance of the protection device under ship collision conditions. If the fortification requirements are met, enter the optimized design result set. If not, return to the similarity ratio coefficient set for the next round of iterative calculation; finally, calculate the project cost of the protection device according to the basic design parameters and similarity ratio coefficients. If the project cost requirements are met, enter the optimized design result set. If not, return to the similarity ratio coefficient set for the next round of iterative calculation.

[0096] As an example, please refer to Figure 9 , Figure 9 In Figure (a) of [reference], it is a schematic diagram of the number of iterations of the ELM prediction model and the peak impact force in working condition 1. In working condition 1, a total of 160 iterative calculations were completed. Among all the schemes of the ELM prediction model, the maximum impact force was 6.95 MN, and the minimum impact force was 4.85 MN. Among them, there were 45 groups of schemes that met the fortification requirements. Figure 9 In Figure (b) of [reference], it is a schematic diagram of the number of iterations of the ELM prediction model and the project cost in working condition 1. In terms of project cost, the project cost range of all schemes was 57,000 yuan to 73,000 yuan. Among them, there were 4 groups of schemes that met the project cost requirements. After comprehensive analysis of the protection performance and cost, it was finally determined that there were 2 groups of schemes that met all design requirements.

[0097] As an example, please refer to Figure 10 , Figure 10 In Figure (a) of [reference], it is a schematic diagram of the number of iterations of the ELM prediction model and the peak impact force in working condition 2. In working condition 2, a total of 95 iterative optimizations were carried out. The calculated maximum impact force was 6.44 MN, and the minimum impact force was 5.01 MN. There were 3 groups of schemes that met the fortification requirements. Figure 10 In Figure (b) of [reference], it is a schematic diagram of the number of iterations of the ELM prediction model and the project cost in working condition 2. In terms of project cost, the project cost range of all schemes was 57,500 yuan to 79,700 yuan. Among them, there were 12 groups of schemes that met the project cost requirements. After comprehensive analysis of the protection performance and cost, it was finally determined that there were 3 groups of schemes that met all design requirements.

[0098] As an example, please refer to Figure 11, Figure 11 Figure (a) in Figure 11 is a schematic diagram of the number of iterations of the ELM prediction model and the peak impact force in working condition 3. In working condition 3, a total of 300 iterative calculations were carried out. The maximum impact force was 7.03 MN, and the minimum impact force was 6.95 MN. There were 3 groups of schemes that met the fortification requirements. Figure 11 Figure (b) in Figure 11 is a schematic diagram of the number of iterations of the ELM prediction model and the project cost in working condition 3. The project cost range of all schemes was from 56,500 yuan to 160,000 yuan. Among them, there were 10 groups of schemes that met the project cost requirements. After comprehensive analysis of the protection performance and cost, it was finally determined that there were 2 groups of schemes that met all design requirements.

[0099] As an example, please refer to Table 3, which gives the optimized design results of the protection device under three working conditions.

[0100] Table 3 Optimized Design Results of Protection Device under Three Working Conditions

[0101]

[0102]

[0103] Specifically, the comparative analysis of the optimized design results of the protection device under three working conditions also shows that the protection material with the filling material type of steel-PUF-GFRP is more suitable for the scenario with a narrower pier width, the protection material with the filling material type of steel is more suitable for the scenario with a wider pier width, and the protection material with the filling material type of steel-PUF is more suitable for the scenario with a moderate pier width.

[0104] As an example, select the optimized design results of the protection device under three working conditions, select the protection device with the best protection performance among them, and the similarity ratio coefficient corresponding to the selected protection device is called the optimal similarity ratio coefficient.

[0105] In another embodiment of the present application, a computer-readable storage medium is further provided, storing a computer program, and when the computer program is executed by a processor, it implements an optimization design method of a protection device as described above.

[0106] In summary, the design of the bridge protection device involves various influencing factors, and different types of protection devices have their respective applicable ranges. Based on the ELM prediction model, this application iteratively optimizes the structure of the protection device, meeting the constraint conditions and design objectives in various actual engineering projects, providing a reliable basis and guidance for actual engineering applications. By constructing the ELM prediction model, the crushing performance of the protection device can be quickly predicted based on known structural parameters, reducing the time of model tests and numerical simulations, and significantly improving the design efficiency of the protection device. At the same time, the ELM prediction model provides data-driven technical support for the optimization and evaluation of the protection device performance, realizes the rapid optimization and performance evaluation of the multi-objective optimization problem of the protection device, helps to achieve the balance between performance and engineering cost, and further promotes the design and optimization process of the protection device.

Claims

1. A protective device optimization design method, characterized in that: include: Step S1: clarify the basic information of the project; Step S2: designing constraints and objectives of the protection device according to the basic information of the project; Step S3: obtaining the preliminary parameters and similarity ratio coefficient set of the protection device according to the constraints and objectives of the protection device; Step S4: establishing a prediction model for the crushing performance of the protective device; obtaining multiple sets of basic design parameters of the protective device according to the preliminary selected parameters of the protective device and the similarity ratio coefficient set, and using the established prediction model to calculate the crushing curves of the protective device under different basic design parameters; Step S5: Calculate the protection performance of the protection device under the ship collision condition according to the crush curve; if the defense requirements are met, enter the optimization design result set and return to the similarity ratio coefficient set for the next round of iterative calculation; Step S6: Calculating the engineering cost of the protective device according to the basic design parameters and the similarity ratio coefficient; If the engineering cost requirements are met, the optimization design result set is entered and the similarity ratio coefficient set is returned to perform the next round of iterative calculation.

2. The protective device optimization design method according to claim 1, characterized in that: The basic information of the project includes: pier width, water area margin, defense requirements and project cost requirements.

3. The protective device optimization design method according to claim 2, characterized in that: The constraints of the protection device in step S2 include: the width of the protection device is less than or equal to the surplus dimension of the water area, and the axial length of the protection device is greater than the width of the pier but not more than 1.1 times the width of the pier.

4. The protective device optimization design method according to claim 2, characterized in that: The objectives of designing the protective device in step S2 include: meeting defense requirements and meeting project cost requirements; meeting the defense requirements includes: the impact force value after being reduced by the protective device is less than or equal to the peak impact force that the pier can withstand; meeting the project cost requirements includes: on the basis of meeting the defense requirements, selecting the plan with the lowest project cost.

5. The protective device optimization design method according to claim 3, characterized in that: In step S3, the preliminary selected parameters include: the width of the protective device, the axial length of the protective device and the type of the protective device, the shell thickness, the thickness of the circumferential angle steel plate, the thickness of the axial angle steel plate, the spacing of the circumferential angle steels and the type of filling material; the width of the protective device and the axial length of the protective device are calculated according to the constraints of the protective device, and the widths of the protective device are arranged in descending order as a width parameter set of the protective device; a similarity ratio coefficient set is calculated according to the ratio of the width parameter set of the protective device to the model size; the types of the protective device include: steel protective devices, steel-PUF protective devices and steel-PUF-GFRP protective devices; the recommended type of the protective device is determined according to the axial length of the protective device.

6. The protective device optimization design method according to claim 5, characterized in that: In step S4, a prediction model for the crush performance of the protective device is established, including: training based on an extreme learning machine prediction model to obtain the relationship between the basic design parameters and the crush performance; the input variables of the extreme learning machine prediction model include: deformation, shell thickness, annular angle steel plate thickness, axial angle steel plate thickness, annular angle steel spacing and filling material type, and the filling material types include: steel, steel-PUF and steel-GFRP-PUF; the output variables of the extreme learning machine prediction model include: impact force value; the crush curve is a curve in which the impact force value of the protective device changes with the deformation.

7. The protective device optimization design method according to claim 6, characterized in that: In the step S4, basic design parameter=primary parameter×similar ratio coefficient in the similarity ratio coefficient set.

8. The protective device optimization design method according to claim 5, characterized in that: The step S5 of calculating the protective performance of the protective device under the ship collision condition includes: using the DME method to evaluate the protective performance of the protective device under the ship collision condition under all similarity ratio coefficients.

9. The protective device optimization design method according to claim 5, characterized in that: Returning the similarity ratio coefficient set to perform the next round of iterative calculation includes: reselecting a similarity ratio coefficient in the similarity ratio coefficient set, and generating a set of corresponding basic design parameters for calculation.

10. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, a protective device optimization design method as described in any one of claims 1 to 9 is implemented.

Images