Method for rapidly evaluating ship structure damage under fire action based on numerical simulation and MLP

Abstract

The invention provides a numerical simulation and MLP-based rapid assessment method for ship structure damage under fire action, which comprises the following steps: constructing a thermal coupling model based on PyroSim software and ANSYS software, comprehensively considering dual change effects of heat conduction and structural mechanics, and performing thermal coupling numerical simulation on a ship under fire action; a multi-layer perceptron model is adopted to carry out deep learning training on simulation data, and a deep layer perceptron model is constructed to evaluate structural damage under the action of the ship fire; gPU acceleration logic is designed, calculation efficiency of key steps is accelerated and optimized through the GPU, and the aim of rapidly evaluating structural damage under the ship fire action is achieved. According to the technical scheme, the calculation cost can be remarkably reduced, an efficient and accurate damage evaluation result can be provided, and a new technical support and solution are provided for ship structure safety research in a fire scene.

Description

Technical Field

[0001] The present invention relates to the technical field of ship structure damage assessment, and in particular to a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP. Background Art

[0002] With the continuous increase and complexity of shipping routes, the structural damage assessment of ships in extreme scenarios such as fire has become an important research direction to ensure the safe operation of ships, improve shipping efficiency and reduce economic losses. At present, the technologies for ship structural damage assessment in fire scenarios can be mainly divided into three types, namely, the assessment method based on full-scale ship testing, the assessment method based on scaled model testing and the assessment method based on thermal-mechanical coupling analysis of numerical simulation. For the assessment method based on full-scale ship testing, the experimental cost is high, and the error of this assessment method is large due to the uneven distribution of detection data under the combustion environment; for the assessment method based on scaled model testing, although the cost is reduced compared with the full-scale ship testing, there is a large physical difference between the combustion process under scaled and the actual large-scale combustion process, and this method cannot guarantee the accuracy of the prediction results.

[0003] In recent years, with the significant improvement of computer computing power and the continuous improvement of numerical solution methods, numerical simulation and rapid solution analysis have provided more new ideas for the assessment of ship structure damage under fire. However, the current assessment methods for ship structure damage still have the following problems: (1) At present, the deformation and damage that ships are prone to in a fire environment are very complex in their physical processes, mainly involving the dynamic changes of structural mechanical parameters caused by heat conduction and temperature changes during the fire. However, existing simulation methods are difficult to effectively handle these complex thermal coupling processes, making it difficult to accurately simulate ship structures under fire conditions. (2) Due to the large size and complex structure of ships, the thermal coupling process under fire has highly nonlinear characteristics. Relying solely on numerical simulation often requires a large amount of computing resources, which is difficult to meet the real-time requirements in practical applications.

[0004] At present, the numerical simulation methods used for damage assessment of ship structures under fire mainly rely on finite element analysis and fire dynamics simulation. These methods can accurately simulate the evolution of temperature field, stress field and deformation field during the fire process, and provide an important basis for evaluating the mechanical properties of ship structures in high temperature environments. However, since ship structures usually have large-scale complex characteristics, and the thermal-mechanical coupling effect under the action of fire involves the interaction of multiple physical fields, relying solely on numerical simulation for research often requires a lot of computing resources, which is difficult to meet the real-time and high efficiency requirements in practical applications. Especially when responding to sudden fire incidents, the traditional methods are not efficient enough to quickly provide effective damage assessment results, which in turn affects the timeliness of emergency decision-making. Summary of the invention

[0005] According to the technical problems raised above, a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP is provided. The present invention can overcome the shortcomings of the full-scale real ship structure damage test under fire and the numerical simulation test assessment method of the reduced-scale model. At the same time, the present invention can solve the problem that the existing method based on numerical simulation analysis does not consider the effect of complex hull heat conduction, and can also solve the problem that the serial calculation speed is too slow to meet the actual engineering needs.

[0006] The technical means adopted by the present invention are as follows:

[0007] A rapid assessment method for ship structure damage under fire based on numerical simulation and MLP, including:

[0008] S1. Based on PyroSim and ANSYS software, a thermal-mechanical coupling model is constructed, and the dual change effects of heat conduction and structural mechanics are comprehensively considered to perform a thermal-mechanical coupling numerical simulation of the ship under fire.

[0009] S2. Use a multi-layer perceptron model to perform deep learning training on the simulated data and build a deep perceptron model to evaluate the structural damage under the action of ship fire.

[0010] Furthermore, step S1 specifically includes:

[0011] S11. Constructing ship structure model:

[0012] According to the structural drawings and design requirements of the target ship, the geometric model of the ship cabin is created in the PyroSim software, the constructed geometric model is meshed, and the appropriate mesh size is selected to balance the calculation accuracy and efficiency. The minimum mesh unit should be larger than the thinnest wall thickness of the hull.

[0013] S12. Set thermal combustion parameters:

[0014] Determine the fire form, set the location, size and combustion characteristics of the fire source according to the fire form, set the physical property parameters of the ship structure material, the steel type of the ship bulkhead, the shell properties of different parts, set the boundary conditions of the fire simulation, the initial temperature of the simulated environment, the atmospheric pressure and ventilation conditions;

[0015] S13, simulated fire value:

[0016] Select large eddy simulation and set the calculation time step and calculation accuracy to solve the physical model;

[0017] S14. Result output and analysis:

[0018] After the operation is completed, the result data of the fire simulation is output, the simulation results are quantitatively analyzed, and all the heat flux q data of all simulated positions within the set time are extracted and saved as a csv file;

[0019] S15, ANSYS thermal coupling simulation initialization:

[0020] Start the Workbench tool in ANSYS software, establish transient thermal analysis module and transient structural analysis module; use SolidWorks software to draw a ship model with the same size, coordinate system and scale as PyroSim, save the model in SAT file format, and import it into the transient thermal analysis module, and set relevant boundary conditions according to the fire environment simulated by PyroSim;

[0021] S16. Solve the thermal load:

[0022] Import the temperature field data preprocessed in step S14 into the transient thermal analysis module as the node temperature distribution input corresponding to the time step;

[0023] At the same time, the heat flux data is applied to the surface of the fire source area to simulate the actual effects of thermal radiation and thermal convection on the ship structure under fire conditions;

[0024] Configure the time step and time sequence of heat load application;

[0025] Run the transient thermal analysis module to solve the distribution and change law of the temperature field in the ship structure and obtain the temperature T distribution results during the entire fire process;

[0026] Ensure numerical convergence during the analysis and verify through visualization tools whether the calculated temperature field is consistent with the expected fire simulation results;

[0027] S17. Thermal coupling data transfer:

[0028] The result of transient thermal analysis, i.e. the solved temperature distribution data of the whole ship, is transferred to the transient structural analysis module as the input of thermal boundary conditions to simulate the influence of temperature change on the thermal stress and thermal deformation of the ship structure.

[0029] S18. Solve the structural mechanics load:

[0030] Run the transient structural analysis module to calculate the thermal stress and thermal strain distribution of the ship structure under the thermal load conditions solved in step S16; extract the stress σ and strain ε of key nodes or components, and analyze whether there is a risk of material yield or fracture.

[0031] Furthermore, in step S15, all model edge lines are set to a fixed temperature to adapt to the integrity of the ship under real conditions and ensure that the simulation scenario conforms to the actual operating conditions of the ship.

[0032] Furthermore, step S2 specifically includes:

[0033] S21. Standardization of fire and mechanical data:

[0034] The temperature T and heat flux q in the fire scene, as well as the mechanical parameters stress σ and strain ε corresponding to the damage of the ship structure are standardized and converted into a standard normal distribution with a mean of zero and a standard deviation of one to eliminate dimensional differences;

[0035] S22. Dataset division:

[0036] Divide the data set after the standardization process in step S21 into a training set, a validation set and a test set according to the time series;

[0037] S23, training model design and initialization:

[0038] A prediction model based on multi-layer perceptron is designed. The network structure includes input layer, hidden layer and output layer. The input layer has 2 nodes, corresponding to the input variables fire parameter temperature T and heat flux q respectively. The hidden layer consists of two layers, the first layer has 64 neurons and the second layer has 32 neurons. Both layers use ReLU as the activation function. The output layer has 2 nodes, corresponding to the predicted stress σ and strain ε respectively.

[0039] The output at layer l is calculated as follows:

[0040] z (l) =W (l) a (l) +b (l)

[0041] a (l) =f(z (l) )

[0042] Among them, W (l) is the weight matrix, b (l) is the bias vector, a (l) =f(z (l) ) is the result of the activation function;

[0043] Calculate the final output as follows:

[0044]

[0045] Among them, L represents the index of the last layer;

[0046] S24. Loss function definition:

[0047] Define the mean square error as the loss function, the formula is as follows:

[0048]

[0049] Among them, N is the number of samples, that is, the number of samples in the training set, is the predicted value, Y i is the actual value, and the loss function is used to measure the gap between the model prediction and the actual value.

[0050] S25. Optimizer selection and model training:

[0051] Set the initial learning rate to 0.001, select the Adam optimizer, and perform parameter optimization using the following formula:

[0052]

[0053] The training set is input into the prediction model designed in step S23 for forward propagation. After the prediction value is calculated, the error is evaluated by the loss function defined in step S24, and then the gradient is calculated by back propagation, and the weights and biases are updated using the optimizer, as follows:

[0054]

[0055] S26. Validation set evaluation:

[0056] After each round of training is completed, the validation set divided in step S22 is input into the model to evaluate the performance of the model and record the validation error; if the validation error continues to increase, it is necessary to return to step S23 to adjust the model hyperparameters such as the number of hidden layers, the number of neurons, and the learning rate to ensure the optimal model configuration;

[0057] S27, test set performance test:

[0058] Input the test set in step S22 into the model to test its generalization ability on unseen data; verify the reliability of the final model evaluation function by calculating the prediction accuracy and error index. If the reliability verification fails, repeat step S22 until the reliability is verified;

[0059] S28. Model prediction application:

[0060] The temperature T and heat flux q of the target fire scene are input into the trained model in step S23, and the corresponding stress σ and strain ε are directly output.

[0061] Furthermore, step S21 specifically includes:

[0062] S211, the input of each sample is [T, q], for the input data X∈R 2N , N is the number of samples, and the standardized processing is performed. The formula is as follows:

[0063]

[0064] Among them, μ X is the mean of the input data, σ X is the standard deviation of the input data;

[0065] S212. For the output data Y, namely stress σ and strain ε, standardization is performed, and the formula is as follows:

[0066]

[0067] Among them, μ Y is the mean of the output data, σ Y is the standard deviation of the output data.

[0068] Further, step S22 specifically includes:

[0069] S221, assuming that there are N samples in total, each sample corresponds to a time point; the data is from t1 to t N Arrangement, {t1,t2,......,t N} is a time series, of which the training set accounts for 80%, the validation set and the test set each account for 10%, assuming:

[0070]

[0071] Among them, N train N is the number of samples in the training set, retaining the largest integer; val N is the number of samples in the validation set, retaining the maximum integer; test is the number of samples in the test set, including the remaining data;

[0072] S222. Divide the data into three parts directly in chronological order, including:

[0073] Training set: starting from the first data t to the Nth train Data until;

[0074] Validation set: from the Nth train +1 data Start, to Nth train +N val Data until;

[0075] Test set: from the Nth train +N val +1 data Start from the beginning and end at the Nth data.

[0076] Furthermore, step S3 specifically includes:

[0077] S31. Design of fire and mechanical data standardization processing kernel function PK1:

[0078] Assign a GPU thread to each data sample, calculate the mean and standard deviation of temperature T, heat flux q, stress σ, and strain ε, and perform standardization to convert them into a standard normal distribution;

[0079] S32. Design time series data segmentation kernel function PK2:

[0080] The standardized data set is divided into training set, validation set and test set according to time series through kernel function. Each data sample corresponds to a thread, which quickly completes data division and allocates it to different memory areas.

[0081] S33. Design forward propagation calculation kernel function PK3:

[0082] During the model training phase, a GPU thread is assigned to each neuron in the hidden layer. The forward propagation of temperature T and heat flux q is completed through parallel computing, including the weighted summation from the input layer to the hidden layer and the ReLU activation function calculation, ensuring that large-scale training data can be efficiently input into the model.

[0083] S34. Design back propagation and gradient calculation kernel function PK4:

[0084] Used to calculate the gradient of the back-propagation stage, each weight parameter is assigned a GPU thread; by parallel calculation of the gradient of the loss function with respect to weights and biases, the efficiency of back-propagation is significantly improved;

[0085] S35, design optimizer updates kernel function PK5:

[0086] Parallelize the update logic of the Adam optimizer; assign a thread to each weight and bias parameter, and update the model parameters based on the calculated gradient; complete the optimizer's learning rate adjustment and momentum calculation through GPU acceleration;

[0087] S36. Design the verification set performance evaluation kernel function PK6:

[0088] After each round of training, a thread is assigned to each validation set sample to quickly complete the validation set error calculation. At the same time, the validation error trend is recorded for real-time adjustment of model hyperparameter configuration.

[0089] S37. Design test set performance test kernel function PK7:

[0090] Compare the predictions of the test set with the true values ​​and calculate the error index; assign a thread to each test sample for parallel processing to evaluate the generalization ability of the model on unseen data;

[0091] S38. Design model prediction application kernel function PK8:

[0092] The temperature T and heat flux q of the target fire scene are input into the trained model, and each input sample is assigned a thread to parallelly calculate the output stress σ and strain ε.

[0093] Furthermore, in step S3, the operation logic and sequence of each designed kernel function include:

[0094] S301, run the fire and mechanics data standardization processing kernel function PK1, the time series data segmentation kernel function PK2 and the forward propagation calculation kernel function PK3, respectively completing data standardization processing, data set division and model initialization;

[0095] S302, enter the time loop, run the back propagation and gradient calculation kernel function PK4 according to the input data and time step of the current fire scene, to calculate the feature map of the input data and update the model state;

[0096] S303, based on the model state at the current time step, run the optimizer to update the kernel function PK5, perform forward propagation to calculate the predicted values ​​of the structural parameters in the fire scene, and run the validation set performance evaluation kernel function PK6 to evaluate the prediction error;

[0097] S304, based on the operation results of the optimizer update kernel function PK5 and the validation set performance evaluation kernel function PK6, the test set performance inspection kernel function PK7 and the model prediction application kernel function PK8 are sequentially run to complete the loss function calculation and parameter optimization respectively;

[0098] S305, based on the running results of the test set performance test kernel function PK7 and the model prediction application kernel function PK8, the performance of the model on the validation set is evaluated, and at the same time, the damage data of the current time step is copied from the video memory to the internal memory and saved to the local computer for result analysis;

[0099] S306. After step S305, verify whether it is within the predetermined error range. If so, the calculation is terminated; if not, repeat steps S303-S305 until the preset time step or training termination condition is reached.

[0100] Compared with the prior art, the present invention has the following advantages:

[0101] 1. The invention provides a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP. By combining PyroSim and ANSYS software, a set of systematic thermal-mechanical coupling models is established, which comprehensively considers the dual change effects of heat conduction and structural mechanics. The model can accurately simulate the heat conduction path of the ship structure under fire and its mechanical damage to the structure, ensuring the accuracy and reliability of fire simulation, thereby effectively making up for the shortcomings of the existing technology in the coupled analysis of structural damage under fire.

[0102] 2. The present invention provides a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP, which uses a multi-layer perceptron (MLP) model to perform deep learning training on simulation data to build a model that can quickly assess ship structure damage under fire. The trained MLP model has efficient computing power and high prediction accuracy. The GPU acceleration program further improves the solution efficiency, so that the model can assess fire damage in real time in practical applications.

[0103] 3. The present invention provides a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP, which can not only significantly reduce the calculation cost, but also provide efficient and accurate damage assessment results, providing new technical support and solutions for the study of ship structure safety under fire scenarios.

[0104] Based on the above reasons, the present invention can be widely promoted in the fields of ship structure damage assessment and the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0106] Figure 1 The present invention is a flow chart of the thermal-mechanical coupling numerical simulation of a ship under fire based on PyroSim and ANSYS.

[0107] Figure 2 This is a flow chart of model training of the present invention.

[0108] Figure 3 This is a framework diagram of the deep perception machine kernel function of the present invention.

[0109] Figure 4 It is the operation logic diagram of each kernel function of the present invention. DETAILED DESCRIPTION

[0110] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0111] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0112] Based on the original evaluation of ship structure fire damage only relying on PyroSim fire numerical simulation and ANSYS thermal coupling, this invention innovatively combines multi-layer perceptron and OpenCL-based accelerated solution technology to fully consider the impact of combustion on the overall structure of the ship. This method effectively solves the problem that the traditional thermal coupling calculation speed is difficult to meet engineering needs. By integrating relevant detection data and model solution results, it can achieve rapid evaluation of ship structure damage under fire.

[0113] The principle of numerical simulation of fire on ships using PyroSim is based on its built-in large eddy simulation (LES) model and fire dynamics equations, aiming to accurately predict key physical parameters such as gas temperature and total combustion heat flux during the fire process under set conditions to achieve the restoration of actual fire results. By simulating physical phenomena such as thermal radiation, convective heat transfer and combustion reaction during the fire combustion process, PyroSim can effectively reproduce the propagation path and impact range of the fire in the ship structure. Its core working mechanism includes the following steps: first, by modeling and meshing the geometric structure of the ship cabin, the initial calculation domain of the fire numerical simulation is established; secondly, by inputting parameters such as combustion source characteristics, ventilation conditions and material properties, the fire model is driven to run; finally, by iteratively solving the fire dynamics equations, the spatiotemporal distribution of key physical quantities in the fire process, such as temperature field, smoke concentration and heat flux, is output. This simulation method provides reliable technical support for studying the thermodynamic effects of fire on ship structures, and has a high degree of engineering applicability and analysis accuracy. (The thermal coupling part of ANSYS and PyroSim in the present invention only focuses on the data of model numerical simulation and does not focus on the principle of software)

[0114] The present invention provides a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP, comprising:

[0115] S1. Based on PyroSim and ANSYS software, a thermal-mechanical coupling model is constructed, and the dual change effects of heat conduction and structural mechanics are comprehensively considered to perform a thermal-mechanical coupling numerical simulation of the ship under fire.

[0116] S2. Use a multi-layer perceptron (MLP) model to perform deep learning training on the simulated data and build a deep perceptron model to evaluate the structural damage under the action of ship fire;

[0117] S3. Design GPU acceleration logic to optimize the computational efficiency of key steps through GPU acceleration to achieve the goal of rapid assessment of structural damage under ship fire.

[0118] When specifically implemented, as a preferred embodiment of the present invention, Figure 1 As shown, step S1 specifically includes:

[0119] S11. Constructing ship structure model:

[0120] According to the structural drawings and design requirements of the target ship, the geometric model of the ship cabin is created in the PyroSim software. The important parts must be reproduced more accurately, including the cabin walls, doors and windows, vents and other key structural components. Then the constructed geometric model is meshed, and the appropriate mesh size is selected to balance the calculation accuracy and efficiency. The minimum mesh unit should be larger than the thinnest wall thickness of the hull.

[0121] S12. Set thermal combustion parameters:

[0122] Determine the fire form, and set the location, size and combustion characteristics of the fire source according to the fire form, such as fuel type, maximum heat flux, mass loss rate of the burning material, etc. Common fires during navigation are caused by the leakage of fuels such as gasoline and natural gas. At the same time, set the physical property parameters of the ship's structural materials, the steel type of the ship's bulkheads, and the shell properties of different parts, such as thermal conductivity, specific heat capacity, density and ignition point. Set the boundary conditions of the fire simulation, the initial temperature of the simulated environment, the atmospheric pressure and ventilation conditions, such as natural ventilation or mechanical ventilation.

[0123] S13, simulated fire value:

[0124] Select large eddy simulation (LES) and set the calculation time step and calculation accuracy to solve the physical model to ensure the numerical stability of the simulation and the accuracy of the results;

[0125] S14. Result output and analysis:

[0126] After the run is completed, the fire simulation result data is output, including temperature field, heat flux distribution and fire propagation path, etc., to conduct quantitative analysis of the simulation results. The tool fds2ascii provided in the FDS program is used to extract all heat flux q data of all simulated positions within the set time and save it as a csv file for subsequent processing;

[0127] S15, ANSYS thermal coupling simulation initialization:

[0128] Start the Workbench tool in ANSYS software, establish the transient thermal analysis module (Transient Thermal) and the transient structural analysis module (Transient Structural); use SolidWorks software to draw a ship model with the same size, coordinate system and scale as PyroSim, save the model in SAT file format, and import it into the transient thermal analysis module, and set relevant boundary conditions according to the fire environment simulated by PyroSim;

[0129] S16. Solve the thermal load:

[0130] Import the temperature field data preprocessed in step S14 into the transient thermal analysis module as the node temperature distribution input corresponding to the time step;

[0131] At the same time, the heat flux data is applied to the surface of the fire source area to simulate the actual effects of thermal radiation and thermal convection on the ship structure under fire conditions;

[0132] Configure the time step and the time series of heat load application to accurately restore the dynamic heat transfer process during the fire;

[0133] Run the transient thermal analysis module to solve the distribution and change law of the temperature field in the ship structure and obtain the temperature T distribution results during the entire fire process;

[0134] Ensure numerical convergence during the analysis and verify through visualization tools whether the calculated temperature field is consistent with the expected fire simulation results;

[0135] S17. Thermal coupling data transfer:

[0136] The result of transient thermal analysis, i.e. the solved temperature distribution data of the whole ship, is transferred to the transient structural analysis module as the input of thermal boundary conditions to simulate the influence of temperature change on the thermal stress and thermal deformation of the ship structure.

[0137] S18. Solve the structural mechanics load:

[0138] Run the transient structural analysis module to calculate the thermal stress and thermal strain distribution of the ship structure under the thermal load conditions solved in step S16; extract the stress σ and strain ε of key nodes or components, and analyze whether there is a risk of material yield or fracture.

[0139] In specific implementation, as a preferred embodiment of the present invention, in step S15, all model edge lines are set to a fixed temperature to adapt to the integrity of the ship under real conditions and ensure that the simulation scene meets the actual operating conditions of the ship.

[0140] When specifically implemented, as a preferred embodiment of the present invention, Figure 2 As shown, step S2 specifically includes:

[0141] S21. Standardization of fire and mechanical data:

[0142] The temperature T and heat flux q in the fire scene, as well as the mechanical parameters stress σ and strain ε corresponding to the damage of the ship structure are standardized and converted into a standard normal distribution with a mean of zero and a standard deviation of one to eliminate dimensional differences;

[0143] S22. Dataset division:

[0144] Divide the data set after the standardization process in step S21 into a training set, a validation set and a test set according to the time series;

[0145] S23, training model design and initialization:

[0146] A prediction model based on multi-layer perceptron (MLP) is designed. The network structure includes input layer, hidden layer and output layer. The input layer has 2 nodes, corresponding to the input variables fire parameter temperature T and heat flux q respectively. The hidden layer consists of two layers, the first layer has 64 neurons and the second layer has 32 neurons. Both layers use ReLU as the activation function. The output layer has 2 nodes, corresponding to the predicted stress σ and strain ε respectively.

[0147] The output at layer l is calculated as follows:

[0148] z (l) =W (l) a (l) +b (l)

[0149] a (l) =f(z (l) )

[0150] Among them, W (l) is the weight matrix, b (l) is the bias vector, a (l) =f(z (l) ) is the result of the activation function;

[0151] Calculate the final output as follows:

[0152]

[0153] Among them, L represents the index of the last layer;

[0154] S24. Loss function definition:

[0155] Define mean square error (MSE) as the loss function, the formula is as follows:

[0156]

[0157] Among them, N is the number of samples, that is, the number of samples in the training set, is the predicted value, Y i is the actual value, and the loss function is used to measure the gap between the model prediction and the actual value.

[0158] S25. Optimizer selection and model training:

[0159] Set the initial learning rate to 0.001, select the Adam optimizer, and perform parameter optimization using the following formula:

[0160]

[0161] The training set is input into the prediction model designed in step S23 for forward propagation. After the prediction value is calculated, the error is evaluated by the loss function defined in step S24, and then the gradient is calculated by back propagation, and the weights and biases are updated using the optimizer, as follows:

[0162]

[0163] S26. Validation set evaluation:

[0164] After each round of training is completed, the validation set divided in step S22 is input into the model to evaluate the performance of the model and record the validation error; if the validation error continues to increase, it is necessary to return to step S23 to adjust the model hyperparameters such as the number of hidden layers, the number of neurons, and the learning rate to ensure the optimal model configuration;

[0165] S27, test set performance test:

[0166] Input the test set in step S22 into the model to test its generalization ability on unseen data; verify the reliability of the final model evaluation function by calculating the prediction accuracy and error index. If the reliability verification fails, repeat step S22 until the reliability is verified;

[0167] S28. Model prediction application:

[0168] The temperature T and heat flux q of the target fire scene are input into the trained model in step S23, and the corresponding stress σ and strain ε are directly output.

[0169] In specific implementation, as a preferred embodiment of the present invention, step S21 specifically includes:

[0170] S211, the input of each sample is [T, q], for the input data X∈R 2N , N is the number of samples, and the standardized processing is performed. The formula is as follows:

[0171]

[0172] Among them, μ X is the mean of the input data, σ X is the standard deviation of the input data;

[0173] S212. For the output data Y, namely stress σ and strain ε, standardization is performed, and the formula is as follows:

[0174]

[0175] Among them, μ Y is the mean of the output data, σ Yis the standard deviation of the output data. The purpose of this step is to make the model learn the output more efficiently and avoid deviations during training.

[0176] In specific implementation, as a preferred embodiment of the present invention, step S22 specifically includes:

[0177] S221, assuming that there are N samples in total, each sample corresponds to a time point; the data is from t1 to t N Arrangement, {t1,t2,......,t N} is a time series, of which the training set accounts for 80%, the validation set and the test set each account for 10%, assuming:

[0178]

[0179] Among them, N train N is the number of samples in the training set, retaining the largest integer; val N is the number of samples in the validation set, retaining the maximum integer; test is the number of samples in the test set, including the remaining data;

[0180] S222. Divide the data into three parts directly in chronological order, including:

[0181] Training set: starting from the first data t to the Nth train Data until;

[0182] Validation set: from the Nth train +1 data Start, to Nth train +N val Data until;

[0183] Test set: from the Nth train +N val +1 data Start from the beginning and end at the Nth data.

[0184] When specifically implemented, as a preferred embodiment of the present invention, Figure 3 As shown, step S3 specifically includes:

[0185] S31. Design of fire and mechanical data standardization processing kernel function PK1:

[0186] A GPU thread is assigned to each data sample to calculate the mean and standard deviation of temperature T, heat flux q, stress σ, and strain ε, and normalize them to convert them into a standard normal distribution. Parallel computing can significantly improve the efficiency of standardization for large-scale sample sets.

[0187] S32. Design time series data segmentation kernel function PK2:

[0188] The standardized data set is divided into training set, validation set and test set according to time series through kernel function. Each data sample corresponds to a thread, which quickly completes data division and allocates it to different memory areas.

[0189] S33. Design forward propagation calculation kernel function PK3:

[0190] During the model training phase, a GPU thread is assigned to each neuron in the hidden layer. The forward propagation of temperature T and heat flux q is completed through parallel computing, including the weighted summation from the input layer to the hidden layer and the ReLU activation function calculation, ensuring that large-scale training data can be efficiently input into the model.

[0191] S34. Design back propagation and gradient calculation kernel function PK4:

[0192] Used to calculate the gradient of the back-propagation stage, each weight parameter is assigned a GPU thread; by parallel calculation of the gradient of the loss function with respect to weights and biases, the efficiency of back-propagation is significantly improved;

[0193] S35, design optimizer updates kernel function PK5:

[0194] Parallelize the update logic of the Adam optimizer; assign a thread to each weight and bias parameter, and update the model parameters based on the calculated gradient; complete the optimizer's learning rate adjustment and momentum calculation through GPU acceleration;

[0195] S36. Design the verification set performance evaluation kernel function PK6:

[0196] After each round of training, a thread is assigned to each validation set sample to quickly complete the validation set error calculation. At the same time, the validation error trend is recorded for real-time adjustment of model hyperparameter configuration.

[0197] S37. Design test set performance test kernel function PK7:

[0198] Compare the predictions of the test set with the true values ​​and calculate the error index (such as MSE); assign a thread to each test sample for parallel processing to evaluate the generalization ability of the model on unseen data;

[0199] S38. Design model prediction application kernel function PK8:

[0200] The temperature T and heat flux q of the target fire scene are input into the trained model, and each input sample is assigned a thread to parallelly calculate the output stress σ and strain ε.

[0201] Through the design and implementation of the above kernel function, the computational efficiency of the fire structure damage assessment process can be significantly improved, the demand for rapid assessment can be met, and an efficient solution can be provided for the safety assessment of complex ship structures.

[0202] When specifically implemented, as a preferred embodiment of the present invention, Figure 4 As shown, in step S3, the operation logic and sequence of each designed kernel function include:

[0203] S301, run the fire and mechanics data standardization processing kernel function PK1, the time series data segmentation kernel function PK2 and the forward propagation calculation kernel function PK3, respectively completing data standardization processing, data set division and model initialization;

[0204] S302, enter the time loop, run the back propagation and gradient calculation kernel function PK4 according to the input data and time step of the current fire scene, to calculate the feature map of the input data and update the model state;

[0205] S303, based on the model state at the current time step, run the optimizer to update the kernel function PK5, perform forward propagation to calculate the predicted values ​​of the structural parameters in the fire scene, and run the validation set performance evaluation kernel function PK6 to evaluate the prediction error;

[0206] S304, based on the operation results of the optimizer update kernel function PK5 and the validation set performance evaluation kernel function PK6, the test set performance inspection kernel function PK7 and the model prediction application kernel function PK8 are sequentially run to complete the loss function calculation and parameter optimization respectively;

[0207] S305, based on the running results of the test set performance test kernel function PK7 and the model prediction application kernel function PK8, the performance of the model on the validation set is evaluated, and at the same time, the damage data of the current time step is copied from the video memory to the internal memory and saved to the local computer for result analysis;

[0208] S306. After step S305, verify whether it is within the predetermined error range. If so, the calculation is terminated; if not, repeat steps S303-S305 until the preset time step or training termination condition is reached.

[0209] Through the above technical route, using deep learning models and GPU accelerated design, we can efficiently complete the rapid assessment of ship structure damage under fire and provide support for subsequent structural safety analysis.

[0210] 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP, characterized in that: include: S1. Based on PyroSim and ANSYS software, a thermal-mechanical coupling model is constructed, and the dual change effects of heat conduction and structural mechanics are comprehensively considered to perform a thermal-mechanical coupling numerical simulation of the ship under fire. S2. Use a multi-layer perceptron model to conduct deep learning training on the simulated data and build a deep perceptron model to evaluate the structural damage of the ship under the action of fire; S3. Design GPU acceleration logic to optimize the computational efficiency of key steps through GPU acceleration to achieve the goal of rapid assessment of structural damage under ship fire.

2. According to claim 1, a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP is characterized in that: Step S1 specifically includes: S11. Constructing ship structure model: According to the structural drawings and design requirements of the target ship, the geometric model of the ship cabin is created in the PyroSim software, the constructed geometric model is meshed, and the appropriate mesh size is selected to balance the calculation accuracy and efficiency. The minimum mesh unit should be larger than the thinnest wall thickness of the hull. S12. Set thermal combustion parameters: Determine the fire form, set the location, size and combustion characteristics of the fire source according to the fire form, set the physical property parameters of the ship structure material, the steel type of the ship bulkhead, the shell properties of different parts, set the boundary conditions of the fire simulation, the initial temperature of the simulated environment, the atmospheric pressure and ventilation conditions. S13, simulated fire value: Select large eddy simulation and set the calculation time step and calculation accuracy to solve the physical model; S14. Result output and analysis: After the operation is completed, the result data of the fire simulation is output, the simulation results are quantitatively analyzed, and all the heat flux q data of all simulated positions within the set time are extracted and saved as a csv file; S15, ANSYS thermal coupling simulation initialization: Start the Workbench tool in ANSYS software, establish transient thermal analysis module and transient structural analysis module; use SolidWorks software to draw a ship model with the same size, coordinate system and scale as PyroSim, save the model in SAT file format, and import it into the transient thermal analysis module, and set relevant boundary conditions according to the fire environment simulated by PyroSim; S16. Solve the thermal load: Import the temperature field data preprocessed in step S14 into the transient thermal analysis module as the node temperature distribution input corresponding to the time step; At the same time, the heat flux data is applied to the surface of the fire source area to simulate the actual effects of thermal radiation and thermal convection on the ship structure under fire conditions; Configure the time step and time sequence of heat load application; Run the transient thermal analysis module to solve the distribution and change law of the temperature field in the ship structure and obtain the temperature T distribution results during the entire fire process; Ensure numerical convergence during the analysis and verify through visualization tools whether the calculated temperature field is consistent with the expected fire simulation results; S17. Thermal coupling data transfer: The result of transient thermal analysis, i.e. the solved temperature distribution data of the whole ship, is transferred to the transient structural analysis module as the input of thermal boundary conditions to simulate the influence of temperature change on the thermal stress and thermal deformation of the ship structure. S18. Solve the structural mechanics load: Run the transient structural analysis module to calculate the thermal stress and thermal strain distribution of the ship structure under the thermal load conditions solved in step S16; extract the stress σ and strain ε of key nodes or components, and analyze whether there is a risk of material yield or fracture.

3. According to claim 1, a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP is characterized in that: In step S15, all model edge lines are set to a fixed temperature to adapt to the integrity of the ship under real conditions and ensure that the simulation scenario conforms to the actual operating conditions of the ship.

4. According to claim 1, a method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP is characterized in that: Step S2 specifically includes: S21. Standardization of fire and mechanical data: The temperature T and heat flux q in the fire scene, as well as the mechanical parameters stress σ and strain ε corresponding to the damage of the ship structure are standardized and converted into a standard normal distribution with a mean of zero and a standard deviation of one to eliminate dimensional differences; S22. Dataset division: Divide the data set after the standardization process in step S21 into a training set, a validation set and a test set according to the time series; S23. Training model design and initialization: A prediction model based on multi-layer perceptron is designed. The network structure includes input layer, hidden layer and output layer. The input layer has 2 nodes, corresponding to the input variables fire parameter temperature T and heat flux q respectively. The hidden layer consists of two layers, the first layer has 64 neurons and the second layer has 32 neurons. Both layers use ReLU as the activation function. The output layer has 2 nodes, corresponding to the predicted stress σ and strain ε respectively. The output at layer l is calculated as follows: z (l) =W (l) a (l) +b (l) a (l) =f(z (l) ) Among them, W (l) is the weight matrix, b (l) is the bias vector, a (l) =f(z (l) ) is the result of the activation function; Calculate the final output as follows: Among them, L represents the index of the last layer; S24. Loss function definition: Define the mean square error as the loss function, the formula is as follows: Among them, N is the number of samples, that is, the number of samples in the training set, is the predicted value, Y i is the actual value, and the loss function is used to measure the gap between the model prediction and the actual value. S25. Optimizer selection and model training: Set the initial learning rate to 0.001, select the Adam optimizer, and perform parameter optimization using the following formula: The training set is input into the prediction model designed in step S23 for forward propagation. After the prediction value is calculated, the error is evaluated by the loss function defined in step S24, and then the gradient is calculated by back propagation, and the weights and biases are updated using the optimizer, as follows: S26. Validation set evaluation: After each round of training is completed, the validation set divided in step S22 is input into the model to evaluate the performance of the model and record the validation error; if the validation error continues to increase, it is necessary to return to step S23 to adjust the model hyperparameters such as the number of hidden layers, the number of neurons, and the learning rate to ensure the optimal model configuration; S27, test set performance test: Input the test set in step S22 into the model to test its generalization ability on unseen data; verify the reliability of the final model evaluation function by calculating the prediction accuracy and error index. If the reliability verification fails, repeat step S22 until the reliability is verified; S28. Model prediction application: The temperature T and heat flux q of the target fire scene are input into the trained model in step S23, and the corresponding stress σ and strain ε are directly output.

5. A method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP according to claim 4, characterized in that: Step S21 specifically includes: S211, the input of each sample is [T, q], for the input data X∈R 2N , N is the number of samples, and the standardized processing is performed. The formula is as follows: Among them, μ X is the mean of the input data, σ X is the standard deviation of the input data; S212. For the output data Y, namely stress σ and strain ε, standardization is performed, and the formula is as follows: Among them, μ Y is the mean of the output data, σ Y is the standard deviation of the output data.

6. A method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP according to claim 4, characterized in that: Step S22 specifically includes: S221, assuming that there are N samples in total, each sample corresponds to a time point; the data is from t1 to t N Arrangement, {t1,t2,......,t N } is a time series, of which the training set accounts for 80%, the validation set and the test set each account for 10%, assuming: Among them, N train N is the number of samples in the training set, retaining the largest integer; val N is the number of samples in the validation set, retaining the maximum integer; test is the number of samples in the test set, including the remaining data; S222. Divide the data into three parts directly in chronological order, including: Training set: starting from the first data t to the Nth train Data until; Validation set: from the Nth train +1 data Start, to Nth train +N val Data until; Test set: from the Nth train +N val +1 data Start from the beginning and end at the Nth data.

7. A method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP according to claim 1, characterized in that: Step S3 specifically includes: S31. Design of fire and mechanical data standardization processing kernel function PK1: Assign a GPU thread to each data sample, calculate the mean and standard deviation of temperature T, heat flux q, stress σ, and strain ε, and perform standardization to convert them into a standard normal distribution; S32. Design time series data segmentation kernel function PK2: The standardized data set is divided into training set, validation set and test set according to time series through kernel function. Each data sample corresponds to a thread, which quickly completes data division and allocates it to different memory areas. S33. Design forward propagation calculation kernel function PK3: During the model training phase, a GPU thread is assigned to each neuron in the hidden layer. The forward propagation of temperature T and heat flux q is completed through parallel computing, including the weighted summation from the input layer to the hidden layer and the calculation of the ReLU activation function, ensuring that large-scale training data can be efficiently input into the model. S34. Design back propagation and gradient calculation kernel function PK4: Used to calculate the gradient of the back-propagation stage, each weight parameter is assigned a GPU thread; by parallel calculation of the gradient of the loss function with respect to weights and biases, the efficiency of back-propagation is significantly improved; S35, design optimizer updates kernel function PK5: Parallelize the update logic of the Adam optimizer; assign a thread to each weight and bias parameter, and update the model parameters based on the calculated gradient; complete the optimizer's learning rate adjustment and momentum calculation through GPU acceleration; S36. Design the verification set performance evaluation kernel function PK6: After each round of training, a thread is assigned to each validation set sample to quickly complete the validation set error calculation. At the same time, the validation error trend is recorded for real-time adjustment of model hyperparameter configuration. S37. Design test set performance test kernel function PK7: Compare the predictions of the test set with the true values ​​and calculate the error index; assign a thread to each test sample for parallel processing to evaluate the generalization ability of the model on unseen data; S38. Design model prediction application kernel function PK8: The temperature T and heat flux q of the target fire scene are input into the trained model, and each input sample is assigned a thread to parallelly calculate the output stress σ and strain ε.

8. A method for rapid assessment of ship structure damage under fire based on numerical simulation and MLP according to claim 7, characterized in that: In step S3, the operation logic and sequence of each designed kernel function include: S301, run the fire and mechanics data standardization processing kernel function PK1, the time series data segmentation kernel function PK2 and the forward propagation calculation kernel function PK3, respectively completing data standardization processing, data set division and model initialization; S302, enter the time loop, run the back propagation and gradient calculation kernel function PK4 according to the input data and time step of the current fire scene, to calculate the feature map of the input data and update the model state; S303, based on the model state at the current time step, run the optimizer to update the kernel function PK5, perform forward propagation to calculate the predicted values ​​of the structural parameters in the fire scene, and run the validation set performance evaluation kernel function PK6 to evaluate the prediction error; S304, based on the operation results of the optimizer update kernel function PK5 and the validation set performance evaluation kernel function PK6, the test set performance inspection kernel function PK7 and the model prediction application kernel function PK8 are sequentially run to complete the loss function calculation and parameter optimization respectively; S305, based on the running results of the test set performance test kernel function PK7 and the model prediction application kernel function PK8, the performance of the model on the validation set is evaluated, and at the same time, the damage data of the current time step is copied from the video memory to the internal memory and saved to the local computer for result analysis; S306. After step S305, verify whether it is within the predetermined error range. If so, the calculation is terminated; if not, repeat steps S303-S305 until the preset time step or training termination condition is reached.

Images