A testing method and system for the launch heat flow field of a sea-based rocket

Abstract

The present invention discloses a method and system for testing the launch heat flow field of a sea rocket, comprising the following steps: S1, collecting multi-source heat flow data on a sea rocket launch platform, and performing synchronous processing to generate a heat flow test data set; S2, constructing a sparse autoencoder model; S3, using the monarch butterfly optimization algorithm to optimize the model structure parameters to obtain an optimal parameter combination; S4, applying the optimal structure parameters to process the multi-source heat flow data and output a two-dimensional heat flow distribution map; S5, identifying the heat flux region and potential heat anomalies and outputting heat shock warning information. The present invention realizes high-precision modeling of the launch heat flow field of a sea rocket and heat shock warning by integrating a sparse autoencoder and the monarch butterfly optimization algorithm.

Description

Technical Field

[0001] The present invention relates to the technical fields of thermophysical measurement and intelligent aerospace systems, and particularly to a method and system for testing the launch heat flux field of a sea rocket. Background Art

[0002] With the wide application of sea launch platforms in modern space launch missions, how to efficiently and reliably evaluate the heat flux field characteristics during rocket launches in complex marine environments has become a key issue in enhancing platform safety, mission stability, and structural adaptability. During rocket launches, due to the combined effects of factors such as engine flame impingement, high-temperature gas backflow, tail flame impact, and platform structure reflection, complex, intense, and highly unstable heat flux responses will occur in different areas of the platform, even leading to local structural overheating, abnormal thermal stress, and even thermal failure. Therefore, establishing an accurate, real-time, and intelligent heat flux field testing and heat response identification method has become a key research direction in the field of rocket launch thermal protection and structural health management.

[0003] Existing heat flux field testing methods mainly include three categories: one is multi-point heat flux measurement based on physical sensors, such as thermocouples, infrared thermometers, heat flux meters, etc.; the second is visualization heat distribution acquisition technology based on thermal imagers or infrared imaging systems; the third is an indirect estimation method combined with simulation modeling, such as finite element heat conduction analysis and CFD (Computational Fluid Dynamics) simulation. However, these traditional methods have several significant problems in actual sea rocket launch scenarios. First, the installation density of physical sensors is limited, and it is impossible to restore a planar heat flux field with high spatial resolution. Moreover, the sensors are easily affected by the marine environment, vibration disturbances, and high-temperature damage. Second, although the infrared imaging system can provide a two-dimensional thermal map, it relies on manual analysis or traditional filtering methods in data processing, making it difficult to automatically identify thermal anomaly regions, and it is significantly affected by smoke and water vapor. Third, although numerical simulation methods have auxiliary significance in the design stage, they are extremely sensitive to boundary conditions and initial conditions, making it difficult to adapt to real-time changing data stream inputs and unable to be used for dynamic monitoring and thermal warning at the launch site.

[0004] In recent years, artificial intelligence and deep learning methods have made remarkable progress in structural feature extraction, anomaly recognition, and image modeling. Especially in the field of image reconstruction and sparse representation, autoencoder-based neural networks have demonstrated superior performance. Among them, the sparse autoencoder can more effectively capture the essential structural features in the input data by imposing a sparse constraint on neuron activation, and is particularly suitable for learning the low-dimensional latent representation of heatmap-like data. However, in the existing literature, sparse autoencoders are mostly applied to medical imaging, industrial inspection, and image compression, and their application in rocket heat flux distribution modeling is not yet mature. In particular, there is a lack of an adaptation and optimization mechanism for structural design parameters (such as encoder depth, sparse intensity, path structure, etc.) and task characteristics (such as heat flux concentration, heat spot boundary diffusion).

[0005] In addition, the parameter configuration of the deep model structure greatly affects its performance, and existing methods mostly rely on manual setting or empirical tuning, lacking the ability of automated and globally optimal structure search. In recent years, a class of swarm intelligence optimization algorithms, such as particle swarm optimization, grey wolf optimization, firefly algorithm, etc., have gradually been used for optimizing the structure parameters of neural networks. However, these algorithms are prone to falling into local optima in complex high-dimensional search spaces, and the search strategies lack the hierarchy of biological behavior modeling. In contrast, the monarch butterfly optimization algorithm is a newly emerging bio-inspired optimization algorithm that simulates the migration and survival behavior of monarch butterflies between North America and Central America. It realizes global search and local refinement through the cooperation of migration operations and adjustment operations, has strong convergence and the ability to jump out of local extrema, and is suitable for the search and optimization of the neural network structure with multiple parameters and multiple modules.

[0006] However, there is still a lack of a technical solution that combines sparse autoencoders with swarm intelligence optimization algorithms for rocket launch heat flux image modeling and heat anomaly region recognition. Existing research either focuses on model construction while ignoring parameter adaptation, or only targets heatmap visualization without intelligent structural analysis. Especially in the environment of a maritime launch platform, the heat flux perturbation is intense, the data is complex and multi-source, and the heat anomaly region is not easy to be calibrated in advance, making it difficult for traditional methods to meet the comprehensive requirements such as accuracy, stability, and real-time performance. At the same time, in the existing technology, there is a lack of a subsequent physical meaning-based analysis process for the heat flux map output by the model, such as a lack of structural understanding of the heat flux distribution and intelligent warning means for heat shock levels.

[0007] Therefore, how to provide a test method and system for the launch heat flux field of a maritime rocket is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0008] An object of the present invention is to propose a method and system for testing the launch heat flux field of a sea rocket. The present invention integrates key links such as multi-source heat flux data acquisition, deep feature extraction, swarm intelligence optimization, and heat anomaly recognition and early warning. A sparse autoencoder model with an adaptive structure configuration ability is constructed, and the monarch butterfly optimization algorithm is used to globally optimize and search the structure parameters of the model to ensure that the model structure is highly adapted to the heat flux distribution characteristics. On this basis, the system can efficiently restore the two-dimensional heat flux image during the launch process, identify the distribution of heat flux on the platform structure, accurately locate potential heat anomaly areas, and output heat shock warning information, forming a closed-loop control process for thermal state monitoring and risk warning. This method has the advantages of intelligent adjustable structure, accurate image generation, and timely warning response, significantly improving the safety monitoring and thermal protection capabilities of the sea rocket launch platform in a complex thermal environment.

[0009] A method for testing the launch heat flux field of a sea rocket according to an embodiment of the present invention includes the following steps:

[0010] S1. Collect multi-source heat flux data on the sea rocket launch platform and synchronize the multi-source heat flux data according to a unified time stamp to generate a heat flux test data set;

[0011] S2. Construct a sparse autoencoder model, use the heat flux test data set as the input, and the sparse autoencoder model includes an encoder module, a heat flux attention focusing module, a sparse constraint module, and a decoder module;

[0012] S3. Use the monarch butterfly optimization algorithm to optimize the structure parameters of the sparse autoencoder model, encode each population individual as a set of structure parameter combinations, and obtain the optimized structure parameter combinations;

[0013] S4. Apply the optimized structure parameters to the sparse autoencoder model, use the optimized sparse autoencoder model to process the multi-source heat flux data, and output two-dimensional heat flux distribution map data;

[0014] S5. Based on the two-dimensional heat flux distribution map data, identify the heat flux areas in the structure of the sea rocket launch platform, analyze the distribution of heat flux at different spatial positions, determine the location and intensity of potential heat anomaly areas, and output corresponding heat shock warning information.

[0015] Optionally, the multi-source heat flux data specifically includes an infrared image sequence, a thermocouple measurement point heat flux value, ambient wind speed and temperature data, rocket attitude parameters, and platform structure state information.

[0016] Optionally, the S2 specifically includes:

[0017] S21. Set the heat flux test data set as the input matrix , where is the set of real numbers, represents the number of samples, represents the dimension of the heat flux characteristics of each sample, including the infrared image sequence, the heat flux value of the thermocouple measurement point, the environmental wind speed and temperature data, the rocket attitude parameters and the platform structure state information;

[0018] S22. Construct the encoder module of the sparse autoencoder model, which adopts a multi-path parallel structure, including a full-image perception path, a local heat zone path, and an edge detail path, to process the whole image, local heat zone, and edge contour information respectively. The full-image perception path outputs a low-frequency feature map, the local heat zone path outputs a medium-frequency feature map, and the edge detail path outputs a high-frequency feature map. The stacking depth of the convolutional layers of each path is controlled by the multi-scale path fusion depth factor ;

[0019] S23. Set the kernel size, stride, and normalization parameters of each convolutional path, and splice and fuse the low-frequency feature map, medium-frequency feature map, and high-frequency feature map to form a latent feature representation ;

[0020] S24. Construct a heat flux attention focusing module, introduce a channel attention and spatial attention mechanism for the latent feature representation , set the spatial attention diffusion radius as the attention diffusion radius control coefficient , and generate a weighted feature representation according to the attention response ;

[0021] S25. Construct a sparse constraint module, set the sparse target value , and introduce a regional sparse adjustment factor. According to the response characteristics of different input feature regions, dynamically adjust the activation and inhibition intensity of each hidden neuron according to the regional sparse distribution coefficient to form an adjustable regional sparse control strategy:

[0022] S26. Introduce an inter-layer sparse adjustment unit between the encoder module, the heat flux attention focusing module, and the sparse constraint module to monitor the activation output of each hidden layer according to the regional feature importance, and dynamically adjust the sparse intensity layer by layer according to the regional sparse distribution coefficient;

[0023] S27. Construct a decoder module, input the weighted feature representation into the decoding path, adopt a combination structure of transposed convolution and upsampling to restore the output dimension, and generate the output data ;

[0024] S28. Define the set of structural parameters of the sparse autoencoder model, including the number of layers of the encoder and decoder, the number of neurons in each layer, the sparse target value , the regional sparse distribution coefficient , Multi-scale path fusion depth factor , Attention diffusion radius control coefficient ;

[0025] S29. Complete the structure initialization of the sparse autoencoder model, and load the current parameter configuration for pre-training.

[0026] Optionally, the S3 specifically includes:

[0027] S31. Initialize the population size of the monarch butterfly optimization algorithm, and divide it into a northern migration sub-population and a southern regulation sub-population;

[0028] S32. Represent each monarch butterfly individual using a structure-aware encoding method, and encode the monarch butterfly individual as :

[0029] ;

[0030] Among them, represents the structure diagram of the sparse autoencoder model, defining the module connection relationship, enabling status and path layout, represents the corresponding combination of structure parameters, including the number of layers of the encoder and decoder, the number of neurons in each layer, the global sparsity target value , regional sparse distribution coefficient , multi-scale path fusion depth factor , attention diffusion radius control coefficient ;

[0031] S33. Perform structure initialization and pre-training on the sparse autoencoder model corresponding to each monarch butterfly individual, and use the heat flux test dataset to evaluate the reconstruction ability and high-heat region response ability;

[0032] S34. Define the fitness function of the monarch butterfly individual , combined with the reconstruction error of the heat flux image , high-heat region reconstruction error and structural complexity :

[0033] ;

[0034] Among them, is the weighting coefficient;

[0035] S35. Calculate the structural covariance entropy diversity index of the current generation population :

[0036] ;

[0037] Among them, represents the The value of the th structural parameter dimension of an individual, is the population average of the dimension, is the population size, is the structural parameter dimension, is a small positive number, is the logarithmic function;

[0038] S36. Adopt a non-linear migration probability adjustment mechanism based on the diversity index to calculate the migration probability of the th generation:

[0039] ;

[0040] Among them, is the steepness adjustment factor, is the balance threshold, is the exponential function; Generate a random number for each individual. If is satisfied, then mark the individual as a migration candidate individual;

[0041] S37. Perform multi-center attraction update on the migration candidate individuals. Let the set of guiding centers be , where is the structural parameter combination of the jth guiding center individual, , is the number of migration guiding centers. Update the structural parameter combination based on the fitness entropy weight as :

[0042] ;

[0043] Among them, is the random scaling factor, is the guiding weight of the jth guiding center, is the structural parameter combination of the jth guiding center individual, is the guiding weight of the kth guiding center;

[0044] S38. Perform adjustment operations on the individuals in the subpopulation that did not participate in migration. Dynamically control the perturbation amplitude according to the distance from the current optimal individual, and update the structural parameter vector as :

[0045] ;

[0046] Among them, is the reference perturbation amplitude, is the maximum individual distance in the current generation population, is the stability constant, is the current combination of structural parameters for the i-th individual, is the complete encoding of the individual with the optimal fitness in the current generation;

[0047] S39. Evaluate the fitness values of all newly generated individuals, and select the top q% of the optimal individuals to form an elite set for retention;

[0048] S310. Determine whether the iteration termination condition is satisfied, including reaching the maximum number of iterations or the fitness change of the optimal individual being lower than the set threshold in several consecutive generations;

[0049] S311. If the termination condition is not satisfied, then merge the elite individuals and the remaining updated individuals to form the next generation population, and return to step S33;

[0050] S312. If the termination condition is satisfied, then output the individual with the optimal fitness , where is the structure diagram encoding corresponding to the individual with the optimal fitness, is the optimal combination of structural parameters of the sparse autoencoder model.

[0051] Optionally, the S4 specifically includes:

[0052] S41. Apply the obtained optimal combination of structural parameters to the sparse autoencoder model, and decompose the optimal combination of structural parameters into , where represents the optimal number of encoder layers, represents the optimal number of decoder layers, represents the optimal number of neurons in each layer, is the optimal sparsity target value, is the regional sparse distribution coefficient, is the multi-scale path fusion depth factor, is the attention diffusion radius control coefficient;

[0053] S42. Configure the parallel convolution path structure of the multi-scale encoder module of the sparse autoencoder according to the optimal number of encoder layers and the multi-scale path fusion depth factor, set the number of convolution layers and receptive field of each path, and set the diffusion window size of the spatial attention convolution according to the attention diffusion radius control coefficient;

[0054] S43. Configure the density of all neurons based on the optimal number of neurons in each layer, and set the sparse activation constraint weights for different heat flow regions according to the regional sparse distribution coefficient;

[0055] S44. Construct the structure of the sparse autoencoder model based on the optimal combination of structural parameters , expressed as a function mapping , where Denote the input heat flux test data set, as the potential representation feature tensor;

[0056] S45. Input the newly collected multi-source heat flux data during the sea rocket launch process into the optimized sparse autoencoder model, perform the encoding-focusing-decoding process, and obtain a two-dimensional heat flux feature map ;

[0057] S46. Normalize and filter the reconstructed output of the optimized sparse autoencoder model, and output the two-dimensional heat flux distribution map data.

[0058] Optionally, the S5 specifically includes:

[0059] S51. Obtain the output two-dimensional heat flux distribution map data, which contains the calorific value distribution information at different spatial positions;

[0060] S52. Utilize the calorific value gradient change feature to extract the heat response mutation region from the two-dimensional heat flux distribution map data, and combine the launch platform structure layout information to identify the heat flux regions in the sea rocket launch platform structure, covering the rocket flame impact area, ground reflection area, and wake flow area;

[0061] S53. Conduct spatial modeling analysis on the identified heat flux regions, evaluate the coverage range, relative position relationship, and calorific value density distribution of different heat flux regions on the platform structure, and determine the distribution characteristics and propagation trends of each heat flux region in the horizontal and vertical directions;

[0062] S54. Based on the spatial modeling results and calorific value characteristics, conduct focused analysis on the phenomenon of abnormal temperature concentration in the heat flux regions, and determine the location and heat response intensity level of potential heat anomaly regions in the platform structure;

[0063] S55. Compare and verify the determined heat anomaly regions with the two-dimensional heat flux distribution map data, evaluate the consistency performance of the heat anomaly regions in the actual heat flux response, and form a heat shock determination result;

[0064] S56. Generate corresponding heat shock warning information according to the heat shock determination result, clarify the warning level, influence range, and structural risk regions, and assist in the pre-launch structural thermal safety assessment and risk prompt during the mission execution process.

[0065] A launch heat flux field test system for a sea rocket according to an embodiment of the present invention includes the following modules:

[0066] A data acquisition module, configured to collect multi-source heat flux data of a sea rocket launch platform, complete time synchronization and preprocessing, and construct a heat flux data set;

[0067] A model construction module for constructing a sparse autoencoder model;

[0068] A feature extraction module for inputting a heat flux dataset into the sparse autoencoder model to extract the latent features of the two-dimensional heat flux distribution;

[0069] A structure optimization module for globally optimizing the structural parameters of the sparse autoencoder model;

[0070] A heat flux generation module for processing multi-source heat flux data based on the optimized sparse autoencoder model and outputting two-dimensional heat flux distribution map data;

[0071] A heat flux identification module for analyzing the two-dimensional heat flux distribution map data to identify the heat flux regions and potential heat anomalies in the platform structure;

[0072] An early warning module for outputting heat shock warning information and marking the abnormal regions and risk levels.

[0073] The beneficial effects of the present invention are as follows:

[0074] By introducing a deep modeling strategy combining a sparse autoencoder and the monarch butterfly optimization algorithm, the present invention breaks through the limitations of the existing offshore rocket launch heat flux field testing technology in aspects such as inaccurate feature extraction, fixed model structure, low response efficiency, and lack of intelligent early warning. The sparse autoencoder model constructed by using a structure-aware coding mechanism can extract the latent information with spatial distribution characteristics from multi-source heat flux data to form a more discriminative two-dimensional heat flux map; the structural parameters of the model are globally optimized by the monarch butterfly optimization algorithm, enabling the core configurations such as the coding depth, sparsity, and neuron density to be adaptively adjusted according to the characteristics of the heat flux field, thereby enhancing the expression ability and generalization performance of the model. The present invention not only realizes the high-precision restoration of the heat flux field image, but also further combines the map data to model and analyze the heat flux regions in the offshore rocket launch platform structure, can effectively identify the location and intensity of potential heat anomaly regions, and automatically output heat shock warning information, thus realizing the full-process closed-loop monitoring and control from data acquisition, model construction, image generation to risk warning. Compared with the existing methods, the present invention has the remarkable advantages of intelligent structural configuration, high accuracy of image generation, strong automation degree of heat risk identification, and applicability to dynamic and complex launch environments. Description of the Drawings

[0075] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, but do not constitute a limitation to the present invention. In the drawings:

[0076] Figure 1 is a flowchart of a method and system for testing the heat flux field of an offshore rocket launch proposed by the present invention;

[0077] Figure 2 The optimization flowchart of the structure parameters of the monarch butterfly optimization algorithm for a method and system for testing the launch heat flow field of an offshore rocket proposed by the present invention. Specific embodiments

[0078] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are all simplified schematic diagrams, only illustrating the basic structure of the present invention in a schematic manner, so they only show the components related to the present invention.

[0079] Reference Figure 1 , a method for testing the launch heat flow field of an offshore rocket, comprising the following steps:

[0080] S1. Collect multi-source heat flow data on the offshore rocket launch platform, and synchronize the multi-source heat flow data according to a unified timestamp to generate a heat flow test data set;

[0081] S2. Construct a sparse autoencoder model, use the heat flow test data set as the input, and the sparse autoencoder model includes an encoder module, a heat flow attention focusing module, a sparse constraint module, and a decoder module;

[0082] S3. Use the monarch butterfly optimization algorithm to optimize the structure parameters of the sparse autoencoder model, encode each population individual into a set of structure parameter combinations, and obtain the optimized structure parameter combinations;

[0083] S4. Apply the optimized structure parameters to the sparse autoencoder model, use the optimized sparse autoencoder model to process the multi-source heat flow data, and output two-dimensional heat flow distribution map data;

[0084] S5. Based on the two-dimensional heat flow distribution map data, identify the heat flux regions in the structure of the offshore rocket launch platform, analyze the distribution of the heat flux at different spatial positions, determine the location and intensity of potential heat anomaly regions, and output corresponding heat shock warning information.

[0085] The present invention realizes the intelligent modeling and risk identification of the heat flux data of the offshore rocket launch platform by constructing a sparse autoencoder model integrating the monarch butterfly optimization algorithm. Compared with the defects of traditional heat flux testing methods, such as low density of physical sensor layout, large response delay, and manual analysis dependence for image processing, the present invention can automatically extract heat flux features based on multi-source data through the optimized model structure, and effectively generate a high-precision two-dimensional heat flux distribution map. By using the output results of the model to further identify the heat flux regions in the platform structure and analyze the aggregation law of heat values at different spatial positions, it can accurately judge the position and intensity of potential heat anomaly regions, and output heat shock warning information, realizing the dynamic monitoring and intelligent warning of the heat response state. The overall solution has the advantages of strong structure adaptability, high image expression accuracy, and high degree of automation in risk identification, is applicable to the platform heat safety guarantee in complex launch environments, and has good engineering practicability and deployment value.

[0086] In this embodiment, the multi-source heat flux data specifically includes infrared image sequences, thermocouple measurement point heat flux values, environmental wind speed and temperature data, rocket attitude parameters, and platform structure state information.

[0087] In this embodiment, the S2 specifically includes:

[0088] S21. Set the heat flux test data set as the input matrix , where is the real number set, represents the number of samples, represents the heat flux feature dimension of each sample, including infrared image sequences, thermocouple measurement point heat flux values, environmental wind speed and temperature data, rocket attitude parameters, and platform structure state information;

[0089] S22. Construct the encoder module of the sparse autoencoder model, adopting a multi-path parallel structure, including a full-image perception path, a local heat area path, and an edge detail path, which respectively process the whole image, local heat areas, and edge contour information. The full-image perception path outputs a low-frequency feature map, the local heat area path outputs a medium-frequency feature map, and the edge detail path outputs a high-frequency feature map. The stacking depth of the convolutional layers of each path is controlled by the multi-scale path fusion depth factor ;

[0090] S23. Set the kernel size, stride, and normalization parameters of each convolutional path, and splice and fuse the low-frequency feature map, medium-frequency feature map, and high-frequency feature map to form a potential feature representation ;

[0091] S24. Construct a heat flux attention focusing module, introduce a channel attention and a spatial attention mechanism for the potential feature representation , and set the spatial attention diffusion radius as the attention diffusion radius control coefficient , and generate a weighted feature representation according to the attention response ;

[0092] S25. Construct a sparse constraint module and set a sparse target value , and introduce a regional sparse adjustment factor. According to the response characteristics of different input feature regions, the activation and inhibition intensities of each hidden neuron are dynamically adjusted according to the regional sparse distribution coefficient to form an adjustable regional sparse control strategy:

[0093] S26. Introduce an inter-layer sparse adjustment unit between the encoder module, the heat flow attention focusing module and the sparse constraint module to monitor the activation output of each hidden layer according to the regional feature importance, and realize the dynamic adjustment of the sparse intensity layer by layer according to the regional sparse distribution coefficient;

[0094] S27. Construct a decoder module, input the weighted feature representation into the decoding path, and use a combination structure of deconvolution and upsampling to restore the output dimension to generate output data ;

[0095] S28. Define the set of structural parameters of the sparse autoencoder model, including the number of layers of the encoder and decoder, the number of neurons in each layer, the sparse target value , the regional sparse distribution coefficient , the multi-scale path fusion depth factor , the attention diffusion radius control coefficient ;

[0096] S29. Complete the structural initialization of the sparse autoencoder model, and load the current parameter configuration for pre-training.

[0097] Through the systematic design and module-level improvement of the sparse autoencoder model structure, the present invention realizes the efficient multi-scale extraction and regional sparse perception expression of heat flow image features. The multi-path parallel encoder structure is adopted to process the whole image, local heat region and edge detail information respectively, and the convolution depth is flexibly controlled by combining the multi-scale path fusion depth factor, so that the model has good hierarchical perception ability. By introducing the channel attention and spatial attention mechanisms, the model can adaptively focus on key heat regions and effectively express the heat spot regions through the attention diffusion radius control. For the heat feature responses of different regions, the present invention sets a regional sparse adjustment factor, combined with the inter-layer sparse adjustment mechanism, to realize the dynamic control of the activation intensity of hidden neurons, and improve the model's feature retention ability for high-heat regions and compression ability for low-correlation regions. The sparse autoencoder constructed by this method not only has adjustable structural parameters and strong perception ability, but also can balance the reconstruction accuracy of global and local heat features, laying an efficient expression foundation for subsequent heat flow map generation and heat anomaly recognition, and has the remarkable advantages of stable modeling performance, strong optimizability and high adaptability.

[0098] In this embodiment, step S3 specifically includes:

[0099] S31. Initialize the population size of the monarch butterfly optimization algorithm and divide it into a northern migration sub-population and a southern regulation sub-population;

[0100] S32. Represent each monarch butterfly individual using a structure-aware coding method, and encode the monarch butterfly individual as :

[0101] ;

[0102] Among them, represents the structural diagram of the sparse autoencoder model, defining the module connection relationship, enabling state, and path layout, represents the corresponding structural parameter combination, including the number of layers of the encoder and decoder, the number of neurons in each layer, the global sparse target value , the regional sparse distribution coefficient , the multi-scale path fusion depth factor , the attention diffusion radius control coefficient ;

[0103] S33. Initialize the structure and pre-train the sparse autoencoder model corresponding to each monarch butterfly individual, and use the heat flow test data set to evaluate the reconstruction ability and the high-heat region response ability;

[0104] S34. Define the fitness function of the monarch butterfly individual , combined with the reconstruction error of the heat flow image, the reconstruction error of the high-heat region, and the structural complexity :

[0105] ;

[0106] Among them, is the weighting coefficient;

[0107] Fitness function , its practical significance lies in comprehensively measuring the expression ability and resource efficiency of different model structures in the heat flux image modeling task by considering the overall reconstruction error of the heat flux image, the local reconstruction error of the high-temperature region, and the model structure complexity. The three terms in the formula respectively reflect the performance of the model in overall reconstruction accuracy, key heat feature retention ability, and computational resource consumption; through adjustment by the weighting coefficient, the optimization process can focus on accuracy or complexity control according to application requirements, thus achieving a dynamic balance between performance and efficiency. Specifically, the smaller the reconstruction error, the more accurate the model is in restoring the heat flux image; the smaller the error in the high-temperature region, the stronger the model's ability to capture important heat spot information; and the lower the structure complexity, the more concise the model and the higher the inference efficiency. As the optimization goal, this fitness function enables the monarch butterfly algorithm to effectively guide the search process to converge to the optimal structure combination with high accuracy, fast response, and reasonable resources.

[0108] S35. Calculate the structural covariance entropy diversity index of the current generation population :

[0109] ;

[0110] Among them, represents the value of the th individual in the th structural parameter dimension, is the population average of the dimension, is the population size, is the structural parameter dimension, is a small positive number, is the logarithmic function;

[0111] The formula for the structural covariance entropy index used to measure the diversity of the current population. Its practical significance lies in calculating the variance of each structural parameter dimension in the entire population and introducing the form of the entropy function for measurement, thereby reflecting the breadth and dispersion of the distribution of the model structure parameters. This index not only considers the degree of change of each parameter dimension but also strengthens the response to the highly dispersed state through the logarithmic term, enabling the dynamic evaluation of whether the population tends to converge or fall into a local optimum during the optimization process. Specifically, when the structural parameters of each individual in the population are highly similar, the covariance entropy value is low, indicating that the search space shrinks and the individual diversity decreases, and it may be necessary to increase the exploration intensity; conversely, when the entropy value is high, it indicates that the population structure has rich diversity, which helps to maintain the globality of the search and jump out of local extrema. As the basis for the migration probability adjustment mechanism, this index enables the algorithm to adaptively adjust the search strategy, achieve stable convergence from early wide-area exploration to late-stage, effectively improve the efficiency and robustness of the optimization, and is a key means to ensure the global search ability and optimization quality.

[0112] S36. Adopt a non-linear migration probability adjustment mechanism based on diversity metrics to calculate the migration probability of the th generation :

[0113] ;

[0114] Among them, is the steepness adjustment factor, is the balance threshold, is the exponential function; generate a random number for each individual. If is satisfied, then mark the individual as a migration candidate individual;

[0115] The non-linear migration probability adjustment function for dynamically controlling the migration probability. Its practical significance lies in calculating the migration probability in the form of a Sigmoid function according to the structural covariance entropy diversity metric of the current population, so as to achieve adaptive adjustment of the population behavior state. This mechanism can flexibly determine whether an individual participates in the migration operation according to the change of population diversity, thus effectively balancing the strategy selection between global search and local exploitation. When is relatively high, it indicates that the distribution of population structure parameters is wide and the individual differences are large, and the migration probability is suppressed to encourage retaining the current exploration direction; when is relatively low, it means that the population tends to converge and the degree of structural homogenization is high, and the migration probability increases to promote individuals to perform jump updates to multiple centers, so as to jump out of the local extreme value trap. This formula controls the response sensitivity and turning point of the migration probability change through the steepness factor and the threshold parameter , ensuring dynamic adjustment of the optimization behavior at different evolutionary stages, and is one of the important mechanisms for realizing the adaptive search strategy of swarm intelligence algorithms.

[0116] S37. Perform multi-center attraction update on the migration candidate individuals. Let the set of guiding centers be , where is the combination of structural parameters of the jth guiding center individual, , is the number of migration guiding centers. Update the combination of structural parameters based on the fitness entropy weight as :

[0117] ;

[0118] Among them, is the random scaling factor, is the guiding weight of the jth guiding center, is the combination of structural parameters of the jth guiding center individual, is the guiding weight of the k-th guiding center;

[0119] Update the structural parameter combination The formula embodies the multi-center attraction update mechanism introduced in the optimization process of the present invention. Its core idea is: instead of allowing individuals to evolve only towards a single optimal solution, multiple structural configurations with better performance are used as guiding centers to form a more directional and diverse parameter update path. In each optimization iteration, the algorithm constructs weights through entropy values based on the performance scores of multiple guiding centers. These weights reflect the importance of each center in the current optimization stage. Subsequently, candidate individuals will adjust their parameters under the guidance of these centers, and different guiding centers will have different degrees of influence on the individuals, so that the individual update direction integrates multiple advantageous features and avoids falling into local optima. In addition, by introducing a random adjustment factor within a certain range, each parameter update has appropriate perturbation, enhancing the exploration ability of the search. This mechanism effectively improves the flexibility and stability of the optimization path, makes the structural search more extensive and in-depth, can find a better configuration scheme in the sparse autoencoder structure space, and ultimately improves the overall effect of the heat flow image modeling and the adaptability of the model structure.

[0120] S38. Perform an adjustment operation on the individuals in the sub-population that have not participated in migration, dynamically control the perturbation amplitude according to the distance from the current optimal individual, and update the structural parameter vector to :

[0121] ;

[0122] where is the reference perturbation amplitude, is the maximum individual distance in the current generation population, is the stability constant, is the current structural parameter combination of the i-th individual, is the complete coding of the individual with the optimal fitness in the current generation;

[0123] Update the structural parameter vector The formula is a local perturbation update strategy implemented by the present invention for individuals that do not participate in the migration operation during the optimization process, aiming to enhance the local search ability and maintain the diversity of the population structure. The practical significance of this formula lies in: by measuring the difference between the current individual and the global optimal individual, adaptively adjusting the perturbation amplitude of its structural parameters according to the size of the difference, so as to achieve a dynamic adjustment mechanism of "taking big steps to explore when the distance is far, and taking small steps for fine-tuning when the distance is close". When an individual is quite different from the optimal structural configuration, the system will assign it a strong perturbation amplitude to guide it to quickly jump out of the current state and search for new structural possibilities; while when an individual is close to the optimal structure, a small perturbation amplitude is used for fine-tuning to improve the accuracy and reduce the structural fluctuation. This mechanism realizes the controllability and adaptability of the perturbation process by introducing the relative distance from the optimal solution as a regulatory factor and combining the basic perturbation intensity with the stability parameter. Overall, this perturbation strategy based on the difference in the position state of individuals helps the algorithm improve the local convergence quality while maintaining the search activity, and is a key step to improve the optimization accuracy and stability of the final sparse autoencoder structural parameters.

[0124] S39. Evaluate the fitness values of all newly generated individuals, and select the top q% of the optimal individuals to form an elite set for retention;

[0125] S310. Judge whether the iteration termination condition is satisfied, including reaching the maximum number of iterations or the fitness change of the optimal individual being lower than the set threshold in several consecutive generations;

[0126] S311. If the termination condition is not satisfied, then combine the elite individuals and the remaining updated individuals to form the next generation population, and return to step S33;

[0127] S312. If the termination condition is satisfied, then output the individual with the optimal fitness , where, is the structure diagram encoding corresponding to the individual with the optimal fitness, is the optimal structural parameter combination of the sparse autoencoder model.

[0128] The present invention adaptively searches for and globally optimizes the structural parameters of a sparse autoencoder model by introducing the monarch butterfly optimization algorithm, effectively overcoming the defects of traditional deep models that rely on manual configuration of structural parameters and are prone to falling into local optima. By constructing a structure-aware individual coding method, key parameters such as the number of encoder layers, the number of neurons, the sparse control factor, the depth of the multi-scale path, and the attention diffusion range are jointly optimized to ensure a high degree of matching between the model structure and the characteristics of the heat flux data. The covariance entropy index is used to evaluate the population diversity, and combined with the non-linear migration probability adjustment mechanism and the multi-center fitness entropy weight guidance strategy, the algorithm has the ability of dynamic search adjustment and local fine exploration. The perturbation amplitude between individuals is dynamically adjusted according to the structural distance from the optimal individual, improving the search efficiency and stability. The optimized structural parameters not only improve the reconstruction accuracy of the model and the perception ability of the high-temperature region, but also enhance the adaptability of the model to the complex heat flux data structure, realizing the optimal structural configuration for heat flux map construction, and having the beneficial effects of strong search intelligence, high convergence efficiency, and good result stability.

[0129] In this embodiment, step S4 specifically includes:

[0130] S41. Apply the obtained optimal structural parameter combination to the sparse autoencoder model, and decompose the optimal structural parameter combination into , where represents the optimal number of encoder layers, represents the optimal number of decoder layers, represents the optimal number of neurons per layer, is the optimal sparsity target value, is the regional sparse distribution coefficient, is the multi-scale path fusion depth factor, is the attention diffusion radius control coefficient;

[0131] S42. Configure the parallel convolution path structure of the multi-scale encoder module of the sparse autoencoder according to the optimal number of encoder layers and the multi-scale path fusion depth factor, set the number of convolution layers and the receptive field of each path, and set the diffusion window size of the spatial attention convolution according to the attention diffusion radius control coefficient;

[0132] S43. Configure the density of all neurons based on the optimal number of neurons per layer, and set the sparse activation constraint weights for different heat flux regions according to the regional sparse distribution coefficient;

[0133] S44. Construct a sparse autoencoder model structure based on the optimal structural parameter combination , expressed as a function mapping , where represents the input heat flux test data set, is the latent representation feature tensor;

[0134] S45. Input the multi-source heat flux data during the offshore rocket launch newly collected into the optimized sparse autoencoder model, execute the encoding-focusing-decoding process, and obtain a two-dimensional heat flux feature map. ;

[0135] S46. Perform normalization and filtering processing on the reconstructed output of the optimized sparse autoencoder model, and output two-dimensional heat flux distribution map data.

[0136] In the present invention, the optimal structural parameter combination obtained by the monarch butterfly optimization algorithm is accurately applied to the sparse autoencoder model to construct an optimal network structure that highly matches the heat flux characteristics. This method not only ensures the effective configuration of structural factors such as the number of encoder layers, neuron density, and multi-scale path depth, but also realizes targeted control in terms of the attention mechanism and sparse strategy, enabling the model to have stronger expression and compression capabilities when facing heat flux regions with different scales and different response characteristics. Through the collaborative setting of the optimal attention diffusion radius and regional sparse distribution coefficient, the focusing effect of the model on high heat density regions and the constraint effect on low-correlation regions are enhanced. The model structure is constructed in the form of function mapping, which is convenient for system integration and deployment. In practical applications, the model can accurately restore the two-dimensional heat flux distribution during the offshore rocket launch, with high-quality reconstructed images and clear detail expression, and can normalize the output results of the model to improve the consistency and interpretability of the data. The overall scheme has the advantages of high structural matching degree, strong output accuracy, and good reconstruction stability, providing high-quality heat map data support for the subsequent heat flux identification and early warning module.

[0137] In this embodiment, the specific steps of S5 are as follows:

[0138] S51. Obtain the output two-dimensional heat flux distribution map data, which contains heat value distribution information at different spatial positions.

[0139] S52. Utilize the heat value gradient change characteristics to extract the heat response mutation regions from the two-dimensional heat flux distribution map data, and combine the structural layout information of the launch platform to identify the heat flux regions in the offshore rocket launch platform structure, including the rocket flame impact area, ground reflection area, and wake flow area.

[0140] S53. Conduct spatial modeling analysis on the identified heat flux regions, evaluate the coverage range, relative position relationship, and heat value density distribution of different heat flux regions on the platform structure, and determine the distribution characteristics and propagation trends of each heat flux region in the horizontal and vertical directions.

[0141] S54. Based on the spatial modeling results and heat value characteristics, conduct focused analysis on the phenomenon of abnormal concentration of temperature existing in the heat flux regions to determine the location and heat response intensity level of potential heat anomaly regions in the platform structure.

[0142] S55. Compare and verify the determined thermal anomaly regions with the two-dimensional heat flux distribution map data, evaluate the consistency performance of the thermal anomaly regions in the actual heat flux response, and form the thermal shock determination result;

[0143] S56. According to the thermal shock determination result, generate corresponding thermal shock warning information, clarify the warning level, influence range and structural risk area, and assist in the structural thermal safety assessment before launch and the risk prompt during the mission execution.

[0144] The present invention constructs a complete heat flux region identification and thermal shock warning analysis process based on the two-dimensional heat flux distribution map data output by the optimization model, significantly improving the response perception ability and safety guarantee level of the offshore rocket launch platform in a complex thermal environment. This method utilizes the characteristics of sudden changes in heat value gradient and combines the platform structure layout information to accurately identify typical heat flux regions such as the rocket flame impact area, ground reflection area and wake flow around the flame, and quantifies the heat coverage range, relative position relationship and propagation trend of each region based on the spatial modeling method. On this basis, the system further focuses on the region with concentrated temperature anomalies, comprehensively evaluates its position, intensity and spatial continuity, and scientifically determines the thermal shock risk level. By comparing and verifying the anomaly region with the heat flux map, the accuracy and credibility of the warning are effectively improved. The finally output thermal shock warning information has the characteristics of hierarchical prompt, risk positioning and strong platform adaptability, and can provide strong support for the structural thermal safety assessment before launch and the risk prompt during the launch process. The overall method has the beneficial effects of high identification accuracy, strong response timeliness and good engineering applicability.

[0145] Reference Figure 2 , a launch heat flow field test system for an offshore rocket, includes the following modules:

[0146] The data acquisition module is used to collect multi-source heat flow data of the offshore rocket launch platform, complete time synchronization and preprocessing, and construct a heat flow data set;

[0147] The model construction module is used to construct a sparse autoencoder model;

[0148] The feature extraction module is used to input the heat flow data set into the sparse autoencoder model to extract the potential features of the two-dimensional heat flux distribution;

[0149] The structure optimization module is used to globally optimize the structural parameters of the sparse autoencoder model;

[0150] The heat flow generation module is used to process the multi-source heat flow data based on the optimized sparse autoencoder model and output the two-dimensional heat flux distribution map data;

[0151] A heat flux identification module for analyzing two-dimensional heat flow distribution map data to identify heat flux regions and potential heat anomalies in the platform structure;

[0152] An early warning module for outputting heat shock early warning information and marking abnormal regions and risk levels.

[0153] Embodiment 1:

[0154] To verify the feasibility of the present invention in implementation, the present invention is applied to the launch mission of a certain liquid carrier rocket on a certain offshore mobile platform as an application scenario. The platform is equipped with various types of heat flow sensors and infrared image acquisition devices, which can record relevant heat flow data such as flame jet, tail flame reflection, and platform structure heat response during the rocket launch process in real time. The duration of the launch mission is 163 seconds, involving multiple working stages, including ignition, takeoff, passing through the platform section, and tail flame pulling away stage, which are key periods with significant changes in heat load distribution.

[0155] In this embodiment, the system collected heat flux change data at 124 measurement points through thermocouple sensors pre-laid in areas such as the platform deck, reflection wall, and support arm, and obtained an infrared image sequence with a resolution of 512×512 through a dual-band infrared camera. In addition, platform environment data (temperature, humidity, wind speed) and rocket attitude parameters (pitch angle, nozzle direction vector, etc.) were also synchronously collected as multi-source input features of the model.

[0156] First, the data acquisition module performs unified timestamp alignment and normalization processing on the above multi-source data to generate a heat flow test data set for training. In the model construction stage, the sparse autoencoder model adopts a three-path parallel encoder structure to process full-map information, local high-temperature regions, and edge details respectively, and configures an attention mechanism for spatial focus extraction. In the optimization stage, the monarch butterfly optimization algorithm is introduced to globally search and optimize the structure parameters through 200 rounds of evolution process to obtain the optimal model configuration. Its encoder has 4 layers, and the number of neurons in each layer is 128, 256, 128, and 64 respectively. The optimal sparsity target is 0.18, the regional sparsity factor is 0.26, the multi-scale fusion depth factor is set to 3, and the attention diffusion control coefficient is 4.5.

[0157] Subsequently, the optimized sparse autoencoder model is used to process the newly acquired heat flux data during the launch process. The system can generate a two-dimensional heat flux distribution map for each frame within 2.3 seconds, and the error between the image output result and the measured value of the sensor has decreased significantly. During the thermal anomaly analysis stage, the model automatically identifies the high heat flux regions on the platform structure and successfully locates three regions with sudden increases in heat values at the flame impingement area (about 8.6 meters from the center of the platform), the wake flow around the flame area (the left rear edge of the platform), and the strong ground reflection tropical area (the bottom of the platform reflector), and respectively gives early warning levels of Ⅲ, Ⅱ, and Ⅳ. The system outputs to the mission control terminal in a graphic and text manner.

[0158] Compared with the traditional method based on infrared imaging + manual interpretation, this method has obvious advantages in terms of response time, modeling accuracy, and thermal anomaly recognition accuracy. Under actual measurement conditions, the average reconstruction error of the model for infrared images is 3.26%, and the local reconstruction error in the high heat area is 2.01%, which is about 31% higher than that of the unoptimized sparse autoencoder; at the same time, the positioning accuracy of the thermal anomaly area has increased from 72% of the original manual annotation method to 91%, and the average advance time for the system to automatically generate early warning prompts is 6.8 seconds, significantly improving the ability to predict the structural thermal safety during rocket launch.

[0159] Table 1 Performance comparison table of different methods in the heat flux test task

[0160]

[0161] From the perspective of the overall accuracy of heat flux image modeling, the method of the present invention performs optimally in terms of both average reconstruction error and local reconstruction error in the high heat area. Specifically, the average error of the present invention in the overall thermal image reconstruction is only 3.26%, which is about 1.45 percentage points lower than that of the traditional sparse autoencoder and more than 2 percentage points lower than that of the convolutional neural network method, fully indicating that the optimized structural parameter configuration is more suitable for the distribution characteristics of heat flux images, especially in maintaining details in key heat areas such as high-temperature flame jets and wake reflections, with stronger expressive ability. The error in the high heat area is only 2.01%, which is of great significance in the actual rocket launch safety analysis.

[0162] In terms of response speed, the single-frame processing time of the method of the present invention is only 2.3 seconds, saving about 2.5 seconds and 1.2 seconds respectively compared with the convolutional neural network and the traditional unoptimized method, with obvious real-time advantages. The traditional manual image analysis method takes longer, usually exceeding 20 seconds, and obviously it is difficult to meet the requirements of real-time monitoring and early warning of the task.

[0163] In terms of the ability to identify and warn of thermal anomalies, the recognition accuracy of the present invention is as high as 91.2%, far superior to 72.3% of traditional manual analysis, and also superior to the range of 80% - 85% of other deep learning models. The system can also achieve an average warning time of 6.8 seconds in advance, effectively helping operators make intervention judgments before the thermal load increases, while traditional manual methods lack the ability to sense in advance.

[0164] In terms of false alarm control, the regional false alarm rate of the present invention is controlled at 4.6%, which is significantly lower than 9.2% and 14.7% of traditional sparse autoencoders and manual analysis, indicating that the model has better discriminative ability for regional thermal characteristics, the warning information is more reliable, and it is applicable to the variable and complex thermal environment in the launch mission.

[0165] From the above performance indicators, it can be seen that the method of the present invention is significantly superior to the existing methods in terms of modeling accuracy, response speed, anomaly recognition rate and false alarm control, reflecting the synergistic advantages of structural optimization and model customization.

[0166] The above is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and all should be covered within the protection scope of the present invention.

Claims

1. A method for testing the launch heat flow field of a sea-based rocket, characterized in that It includes the following steps: S1. Collect multi-source heat flux data on the offshore rocket launch platform, synchronize the multi-source heat flux data according to the unified timestamp, and generate a heat flux test data set; S2. Build a sparse autoencoder model, use the heat flux test data set as the input. The sparse autoencoder model includes an encoder module, a heat flux attention focusing module, a sparse constraint module, and a decoder module; S3. Use the monarch butterfly optimization algorithm to optimize the structural parameters of the sparse autoencoder model, encode each population individual into a set of structural parameter combinations, and obtain the optimized structural parameter combinations; S4. Apply the optimized structural parameters to the sparse autoencoder model, use the optimized sparse autoencoder model to process the multi-source heat flux data, and output two-dimensional heat flux distribution map data; S5. Based on the two-dimensional heat flux distribution map data, identify the heat flux regions in the offshore rocket launch platform structure, analyze the distribution of heat flux at different spatial positions, determine the location and intensity of potential heat anomaly regions, and output the corresponding heat shock warning information.

2. The method for testing the launch heat flow field of an offshore rocket according to claim 1, characterized in that, The multi-source heat flux data specifically includes infrared image sequences, thermocouple measurement point heat flux values, ambient wind speed and temperature data, rocket attitude parameters, and platform structure state information.

3. The method for testing the launch heat flow field of an offshore rocket according to claim 1, characterized in that, The S2 specifically includes: S21. Set the heat flux test data set as the input matrix , where is a set of real numbers, represents the number of samples, represents the heat flux feature dimension of each sample, including infrared image sequences, thermocouple measurement point heat flux values, ambient wind speed and temperature data, rocket attitude parameters, and platform structure status information; S22. Construct the encoder module of the sparse autoencoder model, which adopts a multi-path parallel structure, including a full-image perception path, a local hot-spot path, and an edge detail path, to process the information of the whole image, local hot-spots, and edge contours respectively. The full-image perception path outputs a low-frequency feature map, the local hot-spot path outputs a medium-frequency feature map, and the edge detail path outputs a high-frequency feature map. The stacking depth of the convolutional layers of each path is controlled by the multi-scale path fusion depth factor Control; S23. Set the kernel size, stride, and normalization parameters of each convolutional path, and splice and fuse the low-frequency feature map, intermediate-frequency feature map, and high-frequency feature map to form a potential feature representation ; S24. Construct a heat flow attention focusing module for potential feature representation Introduce the channel attention and spatial attention mechanisms, and set the spatial attention diffusion radius as the attention diffusion radius control coefficient and generate a weighted feature representation according to the attention response ; S25. Construct a sparse constraint module and set a sparse target value , and introduce a regional sparse adjustment factor. According to the response characteristics of different input feature regions, the activation and inhibition intensities of each hidden neuron are dynamically adjusted according to the regional sparse distribution coefficient to form an adjustable regional sparse control strategy: S26. Introduce an inter-layer sparse adjustment unit between the encoder module, the heat flux attention focusing module, and the sparse constraint module, monitor the activation outputs of each hidden layer according to the importance of regional features, and realize dynamic adjustment of the layer-by-layer sparse intensity according to the regional sparse distribution coefficient; S27. Construct a decoder module to input the weighted feature representation into the decoding path, and use a combination structure of transposed convolution and upsampling to restore the output dimension and generate output data ; S28. Define the set of structural parameters of the sparse autoencoder model, including the number of layers of the encoder and decoder, the number of neurons in each layer, the sparse target value , the regional sparse distribution coefficient , the multi-scale path fusion depth factor , the attention diffusion radius control coefficient ; S29. Complete the structural initialization of the sparse autoencoder model, and load the current parameter configuration for pre-training.

4. A method for testing the launch heat flow field of a sea rocket according to claim 3, characterized in that, The S3 specifically includes: S31. Initialize the population size of the monarch butterfly optimization algorithm, and divide it into a northern migration sub-population and a southern adjustment sub-population; S32. Represent each monarch butterfly individual using a structure-aware coding method, and code the monarch butterfly individual as : ； Among them, represents the structural diagram of the sparse autoencoder model, defining the module connection relationship, enabling state, and path layout, represents the corresponding combination of structural parameters, including the number of layers of the encoder and decoder, the number of neurons in each layer, the global sparse target value , the regional sparse distribution coefficient , the multi-scale path fusion depth factor , the attention diffusion radius control coefficient ; S33. Initialize and pre-train the structural sparse autoencoder model corresponding to each monarch butterfly individual, and use the heat flux test data set to evaluate the reconstruction ability and the high-heat region response ability; S34. Define the fitness function of individual monarch butterflies , combined with the reconstruction error of the heat flux image , the reconstruction error of the high-temperature area and the structural complexity : ； Among them, is a weighting coefficient; S35. Calculate the structural covariance entropy diversity index of the current generation population : ； Among them, represents the value of the -th individual in the -th structural parameter dimension, is the population average of the dimension, is the population size, is the structural parameter dimension, is a tiny positive number, is the logarithmic function; S36. Adopt a non-linear migration probability adjustment mechanism based on diversity metrics to calculate the migration probability of the generation : ； Among them, is the steepness adjustment factor, is the balance threshold, is an exponential function; generate a random number for each individual. If is satisfied, then mark the individual as a migration candidate individual; S37. Perform multi-center attraction update on the migration candidate individuals. Let the set of guiding centers be , where is the structural parameter combination of the j-th guiding center individual, , is the number of migration guiding centers. Update the structural parameter combination based on the fitness entropy weight as : ； Among them, is a random scaling factor, is the guiding weight of the j-th guiding center, is the combination of structural parameters of the individual of the j-th guiding center, is the guiding weight of the k-th guiding center; S38. Perform a regulation operation on the individuals in the sub-population that did not participate in migration, dynamically control the perturbation amplitude according to the distance from the current optimal individual, and update the structure parameter vector to :[[]]END]] ； Among them, is the reference perturbation amplitude, is the maximum individual distance in the current generation population, is the stability constant, is the current structural parameter combination of the i-th individual, is the complete coding of the individual with the optimal fitness in the current generation; S39. Evaluate the fitness values of all newly generated individuals, and select the top q% of the optimal individuals to form an elite set for retention; S310. Judge whether the iteration termination condition is satisfied, including reaching the maximum number of iterations or the fitness change of the optimal individual being lower than the set threshold in several consecutive generations; S311. If the termination condition is not satisfied, merge the elite individuals and the remaining updated individuals to form the next generation population, and return to step S33; S312. If the termination condition is satisfied, output the individual with the optimal fitness. , where is the structure diagram code corresponding to the individual with the optimal fitness, is the optimal structure parameter combination of the sparse autoencoder model.

5. The method for testing the launch heat flow field of an offshore rocket according to claim 4, characterized in that, The S4 specifically includes: S41. Apply the obtained optimal structural parameter combination to the sparse autoencoder model, and decompose the optimal structural parameter combination into , where represents the optimal number of encoder layers, represents the optimal number of decoder layers, represents the optimal number of neurons in each layer, is the optimal sparsity target value, is the regional sparse distribution coefficient, is the multi-scale path fusion depth factor, is the attention diffusion radius control coefficient; S42. Configure the parallel convolution path structure of the multi-scale encoder module of the sparse autoencoder according to the optimal encoder layer number and the multi-scale path fusion depth factor, set the number of convolution layers and the receptive field of each path, and set the diffusion window size of the spatial attention convolution according to the attention diffusion radius control coefficient; S43. Configure the density of all neurons based on the optimal number of neurons in each layer, and set the sparse activation constraint weights for different heat flux regions according to the regional sparse distribution coefficient; S44. Construct a sparse autoencoder model structure based on the optimal combination of structural parameters , represented as a function mapping , where represents the input heat flux test data set is the latent representation feature tensor S45. Input the multi-source heat flux data during the offshore rocket launch newly collected into the optimized sparse autoencoder model, perform the encoding-focusing-decoding process, and obtain a two-dimensional heat flux feature map ; S46. Normalize and filter the reconstructed output of the optimized sparse autoencoder model, and output two-dimensional heat flux distribution map data.

6. A method for testing the launch heat flux field of an offshore rocket according to claim 5, characterized in that, The S5 specifically includes: S51. Obtain the data of the output two-dimensional heat flux distribution map, where the two-dimensional heat flux distribution map data contains the heat value distribution information at different spatial positions; S52. Utilize the characteristics of heat value gradient change to extract the heat response mutation region from the two-dimensional heat flux distribution map data, and combine the structural layout information of the launch platform to identify the heat flux regions in the structure of the offshore rocket launch platform, covering the rocket flame impact area, the ground reflection area, and the wake flow area; S53. Conduct spatial modeling analysis on the identified heat flux regions to evaluate the coverage range, relative position relationship, and heat value density distribution of different heat flux regions on the platform structure, and determine the distribution characteristics and propagation trends of each heat flux region in the horizontal and vertical directions; S54. Based on the spatial modeling results and heat value characteristics, conduct focused analysis on the phenomenon of abnormal temperature concentration in the heat flux regions to determine the location and heat response intensity level of potential heat anomaly regions in the platform structure; S55. Compare and verify the determined heat anomaly regions with the two-dimensional heat flux distribution map data to evaluate the consistency performance of the heat anomaly regions in the actual heat flux response, and form a heat shock determination result; S56. According to the heat shock determination result, generate corresponding heat shock warning information, clarify the warning level, influence range, and structural risk regions, and assist in the pre-launch structural thermal safety assessment and risk prompt during the mission execution process.

7. A launch heat flux field test system for a sea rocket, and a launch heat flux field test method for a sea rocket according to any one of claims 1 to 6, characterized in that It includes the following modules: Data acquisition module, which is used to collect multi-source heat flux data of the offshore rocket launch platform, complete time synchronization and preprocessing, and construct a heat flux data set; Model construction module, which is used to construct a sparse autoencoder model; Feature extraction module, which is used to input the heat flux data set into the sparse autoencoder model to extract the potential features of the two-dimensional heat flux distribution; Structure optimization module, which is used to globally optimize the structural parameters of the sparse autoencoder model; Heat flux generation module, which is used to process the multi-source heat flux data based on the optimized sparse autoencoder model and output the two-dimensional heat flux distribution map data; Heat flux identification module, which is used to analyze the two-dimensional heat flux distribution map data to identify the heat flux regions and potential heat anomalies in the platform structure; Warning module, which is used to output heat shock warning information and mark the abnormal regions and risk levels.

Images