Method and system for predicting life loss of petroleum conveying and transferring hose

Abstract

The invention relates to the technical field of industrial data prediction and simulation modeling, in particular to a life loss prediction method and system for a petroleum transportation and transfer hose, and the method comprises the steps: generating loss distribution data of a hose material based on a multi-modal data fusion and multi-field collaborative simulation technology; according to the method, inter-regional resource allocation and model parameter optimization are realized through a quantum game optimization algorithm and a genetic algorithm, a high-precision regional loss prediction model is constructed, prediction model parameters are dynamically corrected through a difference analysis module of a digital twin system, simulation environment input parameters are iteratively adjusted in combination with a closed-loop feedback optimization process, and a prediction result is obtained. Generating high-precision life prediction data reflecting a real-time operation state; according to the method, the accuracy and adaptability of life prediction are effectively improved, the problem of insufficient response capability to complex working conditions in the prior art is solved, and reliable technical support is provided for operation maintenance and full-life-cycle management of the hose.

Description

Technical Field

[0001] The invention relates to the technical field of industrial data prediction and simulation modeling, and in particular to a method and system for predicting the life loss of a petroleum transfer hose. Background Art

[0002] Oil transfer hoses are widely used in the petrochemical industry, and their performance and service life are directly related to the operational safety and production efficiency of the equipment. Accurately predicting the life loss of oil transfer hoses can not only effectively prevent accidents and ensure the safety of equipment and personnel, but also optimize maintenance and replacement cycles to avoid high costs caused by premature replacement or sudden failures. In addition, accurate life prediction can also provide data support for material selection and product design, thereby improving the overall durability and reliability of the hose.

[0003] The existing technology (Chinese invention patent, publication number: CN118966027B, name: A composite hose life loss prediction method) adopts a composite hose life loss prediction method based on BP neural network, and optimizes the BP neural network by improving the hiking optimization algorithm (HOA). However, this technology has the following main defects: The existing technology lacks targeted modeling for the complex operating environment of the hose (such as loss under multi-field interaction), fails to fully consider the combined influence of the force field, thermal field and chemical field, and the prediction results for extreme working conditions are less accurate; its prediction model is based on predefined data sets and parameter optimization, and fails to dynamically adjust in combination with the real-time operating status, resulting in a weak response of the model to environmental changes; although an improved hiking optimization algorithm is adopted, the optimization algorithm has insufficient global adaptability to complex loss behaviors, especially in multivariable interaction and nonlinear loss prediction scenarios, local optimal solutions may appear; the existing technology has not established a regionalized loss analysis framework, and it is difficult to accurately capture the local loss distribution and its impact on the global life, resulting in limited prediction accuracy. Summary of the invention

[0004] In view of the many problems existing in the above-mentioned prior art, the present invention provides a life loss prediction method and system for oil transfer hoses. The present invention generates loss distribution data by constructing a multi-field collaborative simulation environment, integrating the coupling of force field, thermal field and chemical field; combining quantum game optimization and genetic algorithm to optimize the regional loss prediction model and achieve global consistency; through the difference analysis module of the digital twin system, dynamically adjust the simulation environment parameters and update the prediction model to achieve real-time optimization and high-precision life prediction. The present invention improves the accuracy, adaptability and real-time optimization capabilities of the prediction, and provides a reliable basis for the operation, maintenance and design optimization of the hose.

[0005] A method for predicting the life loss of a petroleum transfer hose comprises the following steps: Collect the physical, chemical and environmental characteristics data of the oil transfer hose during operation, and process the data to generate fused feature data; Based on the fusion feature data, a multi-field collaborative simulation environment for oil transfer hoses is constructed, and coupled modeling of force field, thermal field and chemical field is performed. The finite element analysis method and multi-feature tensor decomposition algorithm are used to simulate the multi-field interaction, and the loss distribution data that characterizes the local loss distribution of oil transfer hose materials is generated. The loss distribution data is divided into multiple local areas of the oil transfer hose, and a regional loss prediction model is constructed. Through quantum optimization and genetic algorithms, inter-regional collaboration and resource allocation are achieved, and global life prediction data including life dissipation trends and remaining life predictions are generated; Based on the global life prediction data and real-time collected operating status data, a digital twin system is constructed to correct the regional loss prediction model and form a closed-loop feedback optimization process, which outputs optimization data that dynamically reflects the operating status and remaining life prediction of the oil transfer hose.

[0006] Preferably, the processing of the physical properties, chemical properties and environmental properties data collected during the operation of the oil transfer hose includes the following steps: identifying and removing abnormal values ​​in the oil transfer hose operation data through a noise filtering algorithm; performing time offset correction based on the time series of the oil transfer hose operation data using a dynamic time alignment method; and using a feature extraction algorithm to respectively extract the stress vibration frequency, corrosion diffusion rate and temperature change rate in the oil transfer hose operation data to generate dynamic feature data after cleaning.

[0007] Preferably, the cleaned dynamic feature data is compressed by a feature compression model, and the feature compression model includes a variational autoencoder. The variational autoencoder performs latent space mapping on the cleaned dynamic feature data, removes low-contribution features, and generates fused feature data with retained key dynamic features.

[0008] Preferably, the construction of the multi-field collaborative simulation environment includes the following steps: A force field model of the oil transfer hose is established based on the mechanical modeling method to simulate the local stress distribution of the oil transfer hose under different pressure gradients and shear stresses. Based on heat conduction analysis, a thermal field model of oil transfer hose is established to calculate the effect of temperature gradient on the thermal aging rate of oil transfer hose materials; The chemical field model of the oil transfer hose is established through diffusion kinetic modeling to predict the diffusion path of corrosive substances in the oil transfer hose material; The above single-field model is modeled into multi-field coupling by numerical calculation method, where multi-field coupling is calculated by the following formula: in, Represents the total loss distribution of oil transfer hose materials; represents the local loss under the force field; Represents the local loss under the action of thermal field; Represents local losses under the action of chemical fields; are the space coordinates respectively.

[0009] Preferably, the multi-field coupling is achieved by a multi-characteristic tensor decomposition algorithm, which specifically includes the following steps: Constructing a multi-modal tensor of force, thermal and chemical field data for oil hoses ; Use the following formula to transform the tensor To break it down: in, Represents the multi-modal tensor of the oil hose The data point value of , , Respectively represent The decomposition components are Weights on dimensions; represents the rank of tensor decomposition; Coupling loss distribution data is generated based on the decomposed tensor data and used to calculate the sum of local losses in the oil transfer hose.

[0010] Preferably, the establishment of the regional loss prediction model includes the following steps: dividing the loss distribution data into multiple regional data, each regional data represents the loss information of the corresponding sub-region of the oil transfer hose; using the quantum game optimization algorithm to simulate the resource competition and cooperation between regions; combining the genetic algorithm to optimize the parameters of the prediction model of each region, so that the prediction results between regions achieve global consistency.

[0011] Preferably, the quantum game optimization algorithm is implemented by the following steps: optimizing the resource allocation between regions by quantum state superposition, simulating the iterative collapse process of quantum states to determine the optimal allocation; the genetic algorithm optimizes the key parameters of the regional loss prediction model by crossover, mutation and selection operations, and evaluates the model performance using the following fitness function: in, Indicates the fitness of the model; Indicates The actual value of samples; Indicates The predicted value of samples; Represents the total number of samples.

[0012] Preferably, the digital twin system includes a difference analysis module, which generates a difference analysis result by comparing the real-time collected operating status data of the oil transfer hose with the global life prediction data to correct the parameters of the regional loss prediction model and update the status of the digital twin system.

[0013] Preferably, the closed-loop feedback optimization process includes the following steps: dynamically adjusting the input parameters of the multi-field collaborative simulation environment according to the difference analysis results, and recalculating the loss distribution data of the oil transfer hose; inputting the updated loss distribution data into the digital twin system, and updating the real-time operating status and remaining life prediction data of the oil transfer hose until the prediction error converges within the set range.

[0014] A system for implementing the method for predicting the life loss of a petroleum transfer hose comprises: A multimodal data acquisition module is used to collect data on the physical, chemical and environmental characteristics of the oil transfer hose during operation, and process the collected data to generate fused feature data; The multi-field collaborative simulation module is used to build a multi-field collaborative simulation environment for oil transfer hoses based on fusion feature data, conduct coupled modeling of force field, thermal field and chemical field, and use finite element analysis method and multi-feature tensor decomposition algorithm to simulate multi-field interaction, and generate loss distribution data that characterizes the local loss distribution of oil transfer hose materials; The regional loss prediction module is used to divide the loss distribution data into multiple local areas of the oil transfer hose, and build a regional loss prediction model, using quantum optimization and genetic algorithms to achieve inter-regional collaboration and resource allocation, and generate global life prediction data including life dissipation trends and remaining life predictions; The digital twin system module is used to correct the regional loss prediction model and form a closed-loop feedback optimization process based on the global life prediction data and real-time collected operating status data, and output optimization data that dynamically reflects the operating status and remaining life prediction of the oil transfer hose.

[0015] Compared with the prior art, the advantages and beneficial effects of the present invention are: The present invention realizes accurate modeling and prediction of the coupling effects of force field, thermal field and chemical field by constructing a multi-field collaborative simulation environment, thus overcoming the problem that the prior art is insufficiently adaptable to complex working conditions. The present invention realizes dynamic adjustment and iterative optimization based on real-time operating status through difference analysis and closed-loop feedback optimization process, thus solving the problem of lack of real-time performance in the prior art. The present invention achieves global consistency of resource allocation and parameter optimization among regions through the combination of quantum game optimization and genetic algorithm, and improves the global optimization capability of complex loss behaviors. The present invention captures the local loss distribution characteristics and realizes inter-regional collaborative optimization by regional division of loss distribution data and construction of regional prediction models; The combination of multimodal data fusion and digital twin technology in the present invention enables the solution to generate high-precision life prediction data, while improving the adaptability and prediction stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the process of the present invention; Figure 2 A schematic diagram of constructing a multi-field collaborative simulation environment in the present invention; Figure 3 It is a schematic diagram of establishing the regional loss prediction model in the present invention; Figure 4 It is a structural block diagram of the system of the present invention. DETAILED DESCRIPTION

[0017] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure.

[0018] like Figure 1 As shown, a method for predicting the life loss of a petroleum transfer hose comprises the following steps: Collect the physical, chemical and environmental characteristics data of the oil transfer hose during operation, and process the data to generate fused feature data; Preferably, the processing of the physical properties, chemical properties and environmental properties data collected during the operation of the oil transfer hose includes the following steps: identifying and removing abnormal values ​​in the oil transfer hose operation data through a noise filtering algorithm; performing time offset correction based on the time series of the oil transfer hose operation data using a dynamic time alignment method; and using a feature extraction algorithm to respectively extract the stress vibration frequency, corrosion diffusion rate and temperature change rate in the oil transfer hose operation data to generate dynamic feature data after cleaning.

[0019] During the operation of oil transfer hoses, data collection involves multimodal data, including physical property data (such as stress, vibration, etc.), chemical property data (such as the diffusion rate of corrosive substances), and environmental property data (such as temperature, humidity, etc.). These data are usually noisy, incomplete, and have time series deviations in actual collection, so a series of data processing steps are required to ensure the accuracy and consistency of the data in order to generate high-quality feature data for subsequent analysis.

[0020] In principle, the noise filtering algorithm aims to identify and remove outliers in the collected data through statistical methods, signal processing technology or model-based methods. Specifically in the present invention, outliers usually come from sensor equipment failures, external interference or environmental changes. To this end, the scheme adopts a noise filtering method based on statistical thresholds and timing analysis to detect and remove abnormal points in the collected data. For example, by analyzing the time series fluctuation range of the stress signal and combining the sliding window detection method, the collected points that exceed the normal stress change threshold are judged as noise and eliminated. For corrosion diffusion rate data, based on the chemical reaction law model, data that deviates significantly from the actual diffusion path can be eliminated through smoothing filtering and historical data comparison.

[0021] The core effect of noise filtering is to significantly improve the accuracy of the data, reduce the interference of outliers on subsequent feature extraction and model training, and ensure that the cleaned data can truly reflect the operating status of the oil transfer hose.

[0022] Example: In a simulation experiment, a set of stress signal data of a hose under pressure was collected, of which about 10% of the data points had obvious abnormalities due to equipment fluctuations. Through the noise filtering algorithm based on the sliding window, all abnormal points were successfully eliminated, and the missing data points were linearly interpolated, so that the deviation between the processed stress signal and the theoretical calculation result was less than 1%.

[0023] Dynamic Time Warping (DTW) is an algorithm commonly used in time series analysis. The principle is to align two time series by nonlinear stretching or compression to eliminate the time offset caused by sampling frequency or sensor delay. In the present invention, due to the complex operating environment of the hose, different characteristic data (such as stress signals and temperature data) may have different sampling frequencies and time delays, so DTW is needed to time align multimodal data.

[0024] In specific implementation, by constructing the time-amplitude matrix of stress signals and temperature change rate signals, the distance accumulation matrix between time series is calculated, and the optimal alignment path is found in the matrix. In this way, multimodal data are mapped to a unified time axis, eliminating the offset problem between time series. Dynamic time alignment significantly improves the time synchronization of multimodal data, allowing physical, chemical and environmental characteristics data to be comprehensively analyzed at the same time point, thereby improving the reliability of subsequent feature extraction and fusion.

[0025] Example: In the experiment, 10 seconds of stress signal and temperature signal were collected, and it was found that there was a sampling delay of about 0.5 seconds between the two. Through the dynamic time alignment method, the two signals were successfully aligned, and their maximum time deviation was reduced to 0.01 seconds, meeting the accuracy requirements of engineering applications.

[0026] Feature extraction is a key step in the present invention, which is used to extract dynamic features with predictive value from the cleaned multimodal data. In the present invention, feature extraction is respectively aimed at physical properties, chemical properties and environmental properties data, and different feature extraction algorithms are used.

[0027] Physical property data, for stress signals, extract the main vibration frequency and spectrum energy distribution as features. This is usually achieved through Fourier transform (FFT), where the energy distribution of high-frequency components is used to evaluate the local fatigue state of the hose under high-frequency vibration.

[0028] Chemical property data, for corrosion diffusion rate data, the rate of change of diffusion coefficient and the cumulative length of corrosion path are calculated through feature extraction method based on reaction kinetics as important features to characterize chemical aging of hose materials.

[0029] Environmental characteristic data, for the temperature change rate, through statistical analysis, the average temperature change amplitude, the fluctuation range of the change rate, and the correlation coefficient with the operating load are extracted as important parameters to describe the changes in the hose operating environment.

[0030] The core effect of the feature extraction algorithm is to extract key features that can intuitively reflect the state of the hose from multimodal data, providing a basis for subsequent simulation modeling and life prediction.

[0031] Example: In a test, stress vibration data of a petroleum transfer hose in a complex environment was collected, and the main vibration frequencies were extracted and found to be concentrated in the range of 10 Hz to 30 Hz. The high-frequency components increased significantly after running for 20 hours, indicating that the hose may have local fatigue problems.

[0032] Preferably, the cleaned dynamic feature data is compressed by a feature compression model, and the feature compression model includes a variational autoencoder. The variational autoencoder performs latent space mapping on the cleaned dynamic feature data, removes low-contribution features, and generates fused feature data with retained key dynamic features.

[0033] After the initial cleaning process, dynamic feature data may still have high dimensions and complex features. For example, physical property data may contain multiple frequency components and time series of stress changes, chemical property data may involve multiple change patterns of diffusion rate, and environmental property data may contain the interaction effect of temperature and humidity. Direct use of these data for subsequent modeling and analysis may lead to low computational efficiency and model overfitting. Therefore, it is necessary to use a feature compression model to map it to a low-dimensional space while retaining as much feature information as possible that is critical to life loss prediction.

[0034] The variational autoencoder is a generative deep learning model, which is composed of an encoder and a decoder at its core. The encoder is responsible for mapping the input data to a low-dimensional representation in the latent space, and the decoder restores the original data by reconstructing the low-dimensional representation, thereby ensuring that the representation of the latent space has the greatest information retention. In the present invention, the key functions of the variational autoencoder include the following two points: Latent space mapping: By encoding the cleaned dynamic feature data into a low-dimensional representation of the latent space, redundant information is compressed while removing noise or low-contribution features. Feature selection and reconstruction: The feature representation in the latent space is constrained by the reconstruction loss function to ensure that the low-dimensional feature representation retains important information consistent with the original data during reconstruction.

[0035] In the present invention, the variational autoencoder is used to process the cleaned dynamic feature data (including physical properties, chemical properties and environmental characteristics data), specifically including the following steps: (1) The cleaned dynamic feature data is input into the encoder part of the variational autoencoder. The data includes the main vibration frequency of the stress signal, the change pattern of the corrosion diffusion rate, the dynamic amplitude of the temperature change, etc.

[0036] (2) The encoder maps the high-dimensional feature data to generate a low-dimensional feature representation in the latent space. In this process, the variational autoencoder imposes regularization constraints on the representation of the latent space to ensure that its distribution satisfies the Gaussian distribution in order to preserve the global importance of the features.

[0037] (3) The low-dimensional feature representation of the latent space is input into the decoder, and the reconstruction error is calculated to optimize the model parameters by reconstructing the original dynamic feature data. The goal of model optimization is to minimize the reconstruction error while achieving maximum compression of the features.

[0038] (4) The optimized latent space representation is used as the final output to form fused feature data, which is a low-dimensional representation of the high-dimensional dynamic feature data and retains the most important information in the physical, chemical, and environmental properties for life loss prediction.

[0039] While removing redundant information and low-contribution features, the fused feature data can fully reflect the core information related to life loss in the dynamic feature data, such as key stress change patterns, corrosion diffusion trends, and temperature influence laws. The compressed fused feature data has a lower dimension but contains a higher information density, which can significantly improve the computational efficiency of subsequent simulation modeling and prediction algorithms and reduce the risk of overfitting. The fused feature data can express the dynamic feature data in a more compact form through a low-dimensional representation of the latent space, thereby supporting the subsequent prediction model to run in a resource-constrained environment.

[0040] Embodiment: In an experiment, multimodal data of oil hose under complex operating conditions were collected, including physical property data (stress vibration signal, 200 feature dimensions), chemical property data (corrosion diffusion rate signal, 50 feature dimensions) and environmental property data (temperature change signal, 30 feature dimensions). These data were processed using a variational autoencoder. First, the 280-dimensional high-dimensional data was mapped to a 10-dimensional latent space representation through the encoder, and the reconstruction quality was verified by the decoder. The results show that after feature compression, the fused feature data can accurately reflect the key information of the original data, and its reconstruction error is less than 3%. Further verification found that the model accuracy of life loss prediction using fused feature data increased by about 15%, and the computational efficiency increased by 50%.

[0041] like Figure 2 As shown, based on the fusion feature data, a multi-field collaborative simulation environment for oil transfer hoses is constructed, the force field, thermal field and chemical field are coupled and modeled, the finite element analysis method and multi-feature tensor decomposition algorithm are used to simulate the multi-field interaction, and the loss distribution data that characterizes the local loss distribution of the oil transfer hose material is generated; The multi-field collaborative simulation environment is a comprehensive modeling framework designed for the coupled effects of multiple physical effects on oil transfer hoses under complex working conditions. Its goal is to reproduce the combined effects of force fields (such as internal pressure and external loads), thermal fields (such as temperature gradients), and chemical fields (such as corrosion diffusion) on hose materials through numerical simulation methods. Through this simulation environment, the loss behavior of hose materials under complex conditions can be systematically revealed.

[0042] In the specific implementation, the simulation environment takes fused feature data as input. The fused feature data contains key dynamic information such as stress vibration frequency, corrosion diffusion rate and temperature change rate. These data are used as boundary conditions and initial parameters of the multi-field simulation model for simulating driving force field, thermal field and chemical field.

[0043] Force field modeling, based on mechanical modeling methods, calculates the stress distribution of hoses under different pressure gradients and shear stresses through finite element analysis (FEA). The input data includes stress vibration frequency and pipe wall thickness. The modeling process decomposes the hose into multiple finite element units and calculates the stress distribution of each unit.

[0044] Thermal field modeling uses heat conduction analysis methods to establish a thermal field model to describe the heat flow transfer and material thermal aging process of the hose under the action of temperature gradient. The input data is the temperature change rate and ambient temperature distribution. By simulating the transfer path and rate of heat flow, the heat impact distribution of different areas of the hose is generated.

[0045] Chemical field modeling, based on the principle of diffusion dynamics, builds a chemical field model to predict the diffusion path and rate of corrosive substances (such as corrosive products produced by chemical reactions). The input data includes corrosion diffusion rate and material corrosion resistance parameters. By simulating the diffusion behavior of corrosive substances in hose materials, the spatial distribution of corrosion effects is generated.

[0046] The multi-field collaborative simulation environment is not only a simulation of a single field (force field, thermal field, chemical field), but more importantly, a comprehensive modeling of the interaction between multiple fields. The interaction between single fields (such as the effect of stress field on heat flow transfer, or the promotion of temperature gradient on corrosion diffusion) is reflected through coupled modeling.

[0047] In the present invention, the finite element method is used as the basis for numerical calculation, and the multi-modal data of the force field, thermal field and chemical field are decomposed and reorganized through the multi-feature tensor decomposition algorithm to extract the correlation characteristics between the fields. For example, the coupling of the force field and the thermal field will be reflected in the thermal expansion effect of the hose material, while the coupling of the chemical field and the thermal field is manifested as the dynamic characteristics of accelerated corrosion in a high temperature environment. Through the tensor decomposition algorithm, the core characteristics of these interactions can be accurately captured, and the spatial distribution of the local loss of the hose material can be generated based on this.

[0048] The final output of multi-field collaborative simulation is loss distribution data, which represents the local loss state of the hose material in the form of spatial coordinates. These data are obtained through the calculation results of the coupled multi-field model, and mainly include the following information: stress loss in each local area; degree of thermal aging caused by temperature gradient; depth and range of corrosion diffusion in the material. Loss distribution data is used for subsequent regional loss prediction modeling, which can significantly improve the accuracy of the life prediction model.

[0049] Preferably, the construction of the multi-field collaborative simulation environment includes the following steps: A force field model of the oil transfer hose is established based on the mechanical modeling method to simulate the local stress distribution of the oil transfer hose under different pressure gradients and shear stresses. Based on heat conduction analysis, a thermal field model of oil transfer hose is established to calculate the effect of temperature gradient on the thermal aging rate of oil transfer hose materials; The chemical field model of the oil transfer hose is established through diffusion kinetic modeling to predict the diffusion path of corrosive substances in the oil transfer hose material; The above single-field model is modeled into multi-field coupling by numerical calculation method, where multi-field coupling is calculated by the following formula: in, Represents the total loss distribution of oil transfer hose materials; represents the local loss under the force field; Represents the local loss under the action of thermal field; Represents local losses under the action of chemical fields; are the space coordinates respectively.

[0050] The force field model is established based on the mechanical modeling method to simulate the local stress distribution of the oil transfer hose during operation. The hose will be subjected to internal pressure, shear stress and vibration load during the high-pressure oil transportation process. These mechanical factors will cause material fatigue in the local area of ​​the hose.

[0051] In the specific implementation, the hose is divided into multiple finite element units through the finite element analysis (FEA) method, and the stress distribution of each unit is calculated. The input parameters include the internal pressure gradient, the shear stress magnitude, and the mechanical properties of the hose material (such as elastic modulus and Poisson's ratio). The numerical results of the stress distribution are used to calculate the mechanical loss of the local material of the hose.

[0052] The thermal field model is constructed by heat conduction analysis method to simulate the effect of temperature gradient on the thermal aging rate of hose materials. When the hose is transporting high-temperature oil, it will be subjected to heat conduction from the internal fluid, and the external ambient temperature may cause temperature difference. This thermal gradient will cause material performance degradation and aging.

[0053] In the modeling process, a heat conduction model is established based on Fourier's law of heat conduction. The input data includes the temperature of the petroleum fluid, the external environment temperature, the thermal conductivity and heat capacity parameters of the material. By calculating the heat flux density and temperature distribution, the heat loss distribution of the local area of ​​the hose is generated.

[0054] The chemical field model is established through diffusion kinetic modeling to predict the diffusion path of corrosive substances in hose materials. Petroleum may contain corrosive substances (such as hydrogen sulfide or carbon dioxide), which will penetrate into the hose material through diffusion under certain temperature and pressure conditions, causing internal corrosion of the material.

[0055] In specific implementation, a diffusion model of the chemical field is established based on Fick's law, and the input parameters include the diffusion coefficient of the corrosive substance, the corrosion resistance parameters of the material, and the ambient temperature and pressure. The modeling results can accurately predict the diffusion depth and distribution of corrosive substances inside the material.

[0056] Multi-field coupling modeling is the key to the present invention, which realizes the synergistic modeling of force field, thermal field and chemical field through numerical calculation methods. The purpose of multi-field coupling is to simulate the interaction effects between different physical fields under actual operating conditions, such as: The influence of temperature gradient on mechanical properties (such as high temperature leading to reduced material strength); the accelerating effect of force field stress concentration on corrosion diffusion; the promoting effect of temperature increase on corrosion reaction rate.

[0057] In multi-field coupling, the following formula is used to comprehensively calculate the results of each single-field model: By mapping the calculation results of each field into a unified spatial coordinate system, three-dimensional total loss distribution data is generated.

[0058] Through multi-field coupling modeling, the solution can fully capture the interaction effects between force fields, thermal fields, and chemical fields. For example, stress concentration may accelerate corrosion diffusion, while temperature gradients further promote corrosion reactions. This comprehensive modeling significantly improves the simulation accuracy of complex working conditions. The generated total loss distribution data not only covers the loss results of each single-field model, but also accurately reflects the impact of multi-field interactions on hose material loss, providing a reliable basis for regional loss prediction. Through the total loss distribution data, high-risk areas in the hose that are prone to loss can be located more accurately, providing high-quality data for the input of subsequent life prediction models, thereby significantly improving the accuracy and reliability of the prediction.

[0059] In an example, in a certain oil transportation project, the hose operating conditions include an internal pressure gradient of 12 MPa / m, an ambient temperature of 80°C, and the presence of corrosive hydrogen sulfide (diffusion coefficient of 0.02 mm² / s). Through the multi-field collaborative simulation environment of the present invention, the force field, thermal field, and chemical field are modeled separately, and multi-field coupling is achieved through numerical calculation to generate the total loss distribution data of the hose.

[0060] The modeling results show that the bending area of ​​the hose has significantly higher losses than the straight section (the total loss is only 3 times that of the straight section) due to stress concentration (stress loss reaches 8 MPa) and superposition of temperature gradient (heat loss is 5 MJ / m³), accompanied by accelerated corrosion diffusion (corrosion loss depth reaches 1.2 mm). Subsequent optimization of the design (such as reducing the pressure gradient to 10 MPa / m and increasing the thickness of the anti-corrosion coating at the bend) and re-modeling verification found that the total loss in the bending area was reduced to 60% of the original.

[0061] Preferably, the multi-field coupling is achieved by a multi-characteristic tensor decomposition algorithm, which specifically includes the following steps: Constructing a multi-modal tensor of force, thermal and chemical field data for oil hoses ; Use the following formula to transform the tensor To break it down: in, Represents the multi-modal tensor of the oil hose The data point value of , , Respectively represent The decomposition components are Weights on dimensions; The rank of the tensor decomposition, that is, the number of low-dimensional components decomposed, is usually determined by data complexity and computational efficiency; Coupling loss distribution data is generated based on the decomposed tensor data and used to calculate the sum of local losses in the oil transfer hose.

[0062] The multimodal tensor is a high-dimensional data structure used to describe the spatial distribution of multi-field (force field, thermal field and chemical field) data and their coupling relationship in the oil transmission hose. The construction is based on the following logic: (1) Input data: force field data (such as local stress magnitude), thermal field data (such as local temperature change) and chemical field data (such as corrosion diffusion depth).

[0063] (2) Spatial dimension: tensor The dimensions represent the local position of the hose in three-dimensional space, and the value range covers the entire spatial range of the oil transfer hose.

[0064] (3) Tensor value: each tensor data point Represents the data value after the combined influence of the force field, thermal field and chemical field corresponding to the position.

[0065] The purpose of tensor construction is to organize the spatial information and inter-field interaction characteristics of multi-field data in a unified data structure, providing a basis for subsequent tensor decomposition.

[0066] In order to extract the coupling characteristics between the force field, thermal field and chemical field and reduce the computational complexity of high-dimensional data, the present invention adopts a multi-feature tensor decomposition algorithm to The principle of tensor decomposition is to transform high-dimensional data Decomposed into a combination of multiple low-dimensional components, thus revealing the potential pattern of interaction between fields. The calculation formula is: .

[0067] The implementation steps include: (1) Initialize tensors: Map force field, thermal field, and chemical field data to tensors The corresponding position of is used to complete the initialization of the tensor.

[0068] (2) Decomposition algorithm: A tensor decomposition algorithm based on the minimum error criterion is used to optimize iterative calculation , , The value of ensures that the tensor decomposition result can reconstruct the original tensor as accurately as possible. .

[0069] (3) Extracting coupling features: low-dimensional components in the decomposition results , , It represents the weights of force field, thermal field and chemical field in different spatial dimensions. By analyzing these components, the interaction characteristics between fields can be extracted.

[0070] After completing the tensor decomposition, the sum of the local losses of the oil transfer hose is calculated based on the decomposed tensor data. The coupling loss distribution at each location is calculated by the decomposed components, which can reflect the comprehensive influence of the force field, thermal field and chemical field at that location. The coupling loss distribution data is stored in the form of three-dimensional spatial coordinates, providing high-precision input for subsequent life loss prediction.

[0071] Through the tensor decomposition algorithm, the present invention can extract the interaction characteristics between force fields, thermal fields and chemical fields from high-dimensional multimodal data. For example, it is found that the high temperature environment in a specific area enhances the stress concentration effect, and the stress concentration accelerates the corrosion diffusion. Tensor decomposition maps high-dimensional data into multiple low-dimensional components, significantly reducing the complexity of subsequent calculations, while retaining key information on multi-field interactions, improving modeling efficiency and the compactness of data expression. The coupling loss distribution data generated after tensor decomposition can more accurately describe the degree of loss at each location of the hose, providing a reliable basis for subsequent regional loss prediction and life assessment.

[0072] Embodiment, in a certain experiment, the operation data of the oil transfer hose includes: Force field data: local stress distribution range is 5~15 MPa; thermal field data: temperature gradient range is 30~80 ℃; chemical field data: corrosion diffusion rate is 0.05~0.2 mm / day.

[0073] Construct a multimodal tensor based on this data , the tensor size is 100×100×100, representing the multi-field distribution in the hose length, diameter, and time series dimensions.

[0074] Through the multi-feature tensor decomposition algorithm, the tensor is decomposed into ranks The low-dimensional components of the high-temperature region are used to extract the following interaction features: stress concentration effect in the high-temperature region: force field weight in the high-temperature region The significant increase indicates that temperature has an enhancing effect on local stress concentration. The accelerating effect of stress on corrosion diffusion: The chemical field weight in the region with greater stress It increases significantly, indicating that stress concentration has a significant effect on the corrosion diffusion rate.

[0075] The generated coupling loss distribution data shows that the loss in the curved part of the hose is significantly higher than that in the straight section, with the total loss value reaching 4 times that of the straight section.

[0076] The loss distribution data is divided into multiple local areas of the oil transfer hose, and a regional loss prediction model is constructed. Through quantum optimization and genetic algorithms, inter-regional collaboration and resource allocation are achieved, and global life prediction data including life dissipation trends and remaining life predictions are generated; Based on the loss distribution data generated by multi-field collaborative simulation, the present invention divides the petroleum transfer hose into spatial regions. The goal of regional division is to refine the loss distribution of the hose to local regions, so as to capture the loss characteristics of different regions and provide an accurate data basis for subsequent modeling. In the specific implementation, based on the geometric structure of the hose (such as length, radius, etc.) and the characteristics of the loss distribution, the hose is divided into several independent regions, for example, divided into several segmented regions of equal length according to the length of the pipe section, or divided into high-loss and low-loss regions according to the gradient change of the loss data. Each local region corresponds to a set of loss distribution data, including the comprehensive loss of the force field, thermal field and chemical field to the region.

[0077] For each local area, the present invention constructs a regional loss prediction model through loss distribution data. The core function of the model is to predict the life dissipation trend and remaining life of the area based on the local loss data. (1) Model input: comprehensive data of force field loss, thermal field loss and chemical field loss in each area, which constitute the input vector of the model. (2) Model output: life dissipation trend (indicating the time evolution law of material loss) and remaining life (predicting the usable time of the material under current operating conditions) of the area. (3) Algorithm selection: adopt data-driven machine learning methods, such as regression models trained based on historical operating data or prediction models based on physical laws, to ensure that the prediction results are highly accurate.

[0078] After completing the loss prediction for each region, the solution introduces quantum optimization and genetic algorithms to achieve inter-regional collaboration and resource allocation optimization. Specifically, quantum optimization is used to simulate inter-regional resource allocation decisions, and genetic algorithms are used to globally optimize model parameters. The combination of the two improves regional collaboration efficiency and prediction accuracy.

[0079] The quantum optimization algorithm simulates resource competition and collaborative decision-making between regions based on quantum superposition and quantum collapse mechanisms. For example, by establishing a quantum state space where each region corresponds to a quantum bit state value, the optimal allocation of resources (such as operating pressure or load) is simulated. The quantum collapse process will find an optimal solution to determine the allocation ratio of resources in each region.

[0080] The genetic algorithm optimizes the parameters of the regional loss prediction model through crossover, mutation and selection operations to ensure the global consistency of the prediction results of each region. For example, by adjusting the weight parameters of the regional model, the global error is minimized.

[0081] Through the optimized regional loss prediction model and regional cooperation mechanism, global life prediction data is finally generated. The global life prediction data includes: life dissipation trend: reflecting the time evolution law of the overall loss of oil transfer hoses, such as predicting whether the loss rate increases or slows down over time; remaining life prediction: based on the weighted average of the remaining life of each region, predicting the remaining usable time of the hose as a whole. The generation of global life prediction data depends on the collaborative optimization of regional models, which can reflect the overall life status of the hose under complex operating conditions.

[0082] Through the regional processing of loss distribution data and the construction of regional loss prediction models, the present invention can accurately capture the loss characteristics of each local area of ​​the oil transfer hose and provide high-precision local life prediction results. Through the combination of quantum optimization and genetic algorithms, the scheme achieves synergy between regions, optimizes resource allocation and improves the reliability and consistency of global prediction. The generated global life prediction data can fully reflect the life dissipation law and overall health status of the hose, providing a scientific basis for operation decisions and maintenance strategies.

[0083] Example: In a certain oil transportation project, the running length of the oil transfer hose is 100 meters. Based on the geometric structure and loss distribution data, the hose is divided into 10 local areas (each section is 10 meters long). The following operations are completed through the regionalized loss prediction model and optimization algorithm: (1) Regional processing of loss distribution data: The comprehensive losses of force field, thermal field and chemical field in each region were analyzed using simulation data. It was found that the comprehensive losses in the bending parts (regions 3 and 8) were significantly higher than those in other regions.

[0084] (2) Construction of regional loss prediction model: A regression model based on historical operation data is established for each region to predict the life dissipation trend and remaining life of each region. For example, the model of region 3 predicts that its remaining life is 50 days, while the remaining life of the straight pipe section is 150 days.

[0085] (3) Regional collaboration and optimization: Through the quantum optimization algorithm, operating pressure resources are preferentially allocated to areas with shorter lifespans (such as area 3), and model parameters are optimized through genetic algorithms to ensure the consistency of global prediction results.

[0086] (4) Generation of global life prediction data: Based on the optimized regional prediction results, global life prediction data is generated, showing that the remaining life of the hose as a whole is 80 days, and pointing out the key high-loss areas.

[0087] Preferably, Figure 3As shown, the establishment of the regional loss prediction model includes the following steps: dividing the loss distribution data into multiple regional data, each regional data represents the loss information of the corresponding sub-region of the oil transfer hose; using the quantum game optimization algorithm to simulate the resource competition and cooperation between regions; combining the genetic algorithm to optimize the parameters of the prediction model of each region, so that the prediction results between regions reach global consistency.

[0088] Before the regional loss prediction model is established, the loss distribution data generated by multi-field coupling is first regionalized. The goal of regional division is to refine the loss distribution into each sub-region of the hose, and the data of each region reflects the local loss characteristics.

[0089] The following steps are performed during the specific implementation: (1) Input data: Coupling loss distribution data of force field, thermal field and chemical field, stored with three-dimensional spatial coordinates as index. (2) Division method: Based on the geometric characteristics of the oil hose (such as length and bending radius) and the gradient change of loss distribution data, the hose is divided into several sub-areas. For example, for a 100-meter hose, it can be divided into 10 equal-length areas every 10 meters, or the high-loss area can be separated separately according to the loss gradient change.

[0090] The data of each sub-region includes the comprehensive loss value and its time series changes, which are used to build a local prediction model.

[0091] In a multi-region model, the loss characteristics of different regions may affect each other (e.g., a high-loss region may cause coordinated loss in an adjacent region), so it is necessary to model resource competition and collaboration between regions. To this end, the present invention uses a quantum game optimization algorithm to simulate the resource allocation and collaboration mechanism between regions.

[0092] Quantum game is a method that combines quantum mechanics and game theory, simulating the decision-making process among multiple game players through quantum superposition and quantum collapse mechanisms. In this invention, resources between regions (such as pressure distribution and operating parameters) are regarded as resource variables of the game, and each region participates in competition and collaboration as a game player.

[0093] Specific implementation steps: (1) Quantum state initialization: assign a quantum bit to each region, and the superposition state of the quantum bit represents the resource state of the region. The resource allocation state can be represented by a probability distribution Indicates that and Represent the probability of low resource and high resource allocation respectively. (2) Resource competition and collaboration modeling: Establish the payoff function of the game. The function takes the resource status and loss data of each region as input and outputs the payoff of each region. For example, for high-loss regions, the payoff function tends to allocate more resources (such as reducing pressure or increasing protective measures). (3) Quantum collapse: Find the global optimal solution through the quantum collapse mechanism, that is, the resource allocation plan with the smallest overall loss. Finally, output the resource allocation ratio of each region.

[0094] After completing the resource allocation between regions, the loss prediction model of each region is optimized for parameters to ensure the global consistency of the model output. The present invention uses a genetic algorithm to optimize the model parameters. The genetic algorithm simulates the selection, crossover and mutation process of biological evolution and searches for the optimal solution through iterative optimization. In the present invention, the genetic algorithm is used to optimize the parameters (such as weights and learning rates) of each regional prediction model to minimize the global prediction error. Specific implementation steps: (1) Initialization of population: Generate several sets of initial parameter combinations for each regional prediction model as the population of the algorithm. (2) Fitness function: Define the fitness function to measure the quality of parameter combinations. The fitness function takes the prediction error of the model as the target. The smaller the error, the higher the fitness. (3) Selection and crossover: Select excellent parameter combinations according to the fitness function, and generate new parameter combinations through crossover operations. (4) Mutation operation: Randomly perturb some parameters to explore new parameter space. (5) Iterative optimization: After multiple rounds of iterations, it finally converges to the optimal parameter combination to ensure that the output of each regional prediction model has high accuracy and the global prediction results are consistent.

[0095] Through the combined application of quantum game optimization and genetic algorithm, the present invention not only optimizes the prediction model of each region, but also achieves global consistency of prediction results between regions. The goal of global consistency is to make the prediction results of all regions consistent in time and space, so as to generate the overall hose life dissipation trend and remaining life prediction.

[0096] By dividing regional data and establishing a regional prediction model, the present invention can capture the loss law of each local area and achieve high-precision regional life prediction. The quantum game optimization algorithm simulates the resource competition and cooperation mechanism between high-loss areas and low-loss areas, and achieves global optimization of resource allocation. By optimizing the parameters of the regional prediction model through genetic algorithms, the reliability and consistency of the global life prediction results are guaranteed, and the cumulative effect of local prediction errors is reduced. The combination of quantum optimization and genetic algorithms not only improves the prediction accuracy, but also significantly reduces the iterative optimization time of the global prediction model.

[0097] In an example, in a certain oil transportation project, the operation data of the oil transfer hose is divided into 10 local areas (each section is 10 meters long). Based on the regional data, the following steps are completed: (1) Regional data processing: The force field, thermal field and chemical field loss information of each region was extracted, and it was found that the comprehensive loss values ​​of the third and eighth regions were significantly higher than those of other regions.

[0098] (2) Quantum game optimization: simulate the allocation of resources (operating pressure), and use the quantum optimization algorithm to determine that more resources (such as reducing operating pressure) will be allocated to high-loss areas. In the end, the resource allocation ratio is: the third area obtains 15% of the resources, the eighth area obtains 20% of the resources, and the remaining areas share 65% of the resources.

[0099] (3) Genetic algorithm optimization: The parameters of the prediction model for each region are optimized and the global error is reduced to below 1% through multiple rounds of iterations.

[0100] (4) Global life prediction results: Global data including life dissipation trend and remaining life prediction are finally generated, showing that the overall remaining life of the hose is 80 days, and pointing out that the remaining life of the key high-loss area is only 50 days.

[0101] Preferably, the quantum game optimization algorithm is implemented by the following steps: optimizing the resource allocation between regions by quantum state superposition, simulating the iterative collapse process of quantum states to determine the optimal allocation; the genetic algorithm optimizes the key parameters of the regional loss prediction model by crossover, mutation and selection operations, and evaluates the model performance using the following fitness function: in, Indicates the fitness of the model; Indicates The actual value of samples; Indicates The predicted value of samples; Represents the total number of samples.

[0102] The quantum game optimization algorithm is used to simulate resource competition and cooperation between regions, and find the global optimal solution for regional resource allocation through the superposition and collapse mechanism of quantum mechanics. In this invention, resource allocation refers to the dynamic adjustment of operating conditions (such as operating pressure or protective measures), with the goal of allocating more resources to high-loss areas in priority to delay local losses and optimize the overall life of the hose. Implementation steps: (1) Quantum state initialization: A quantum bit is assigned to each region. The superposition state of each quantum bit represents the resource state of the region. For example: Indicates that and Respectively represent the area The probabilities of the low-resource state and the high-resource state.

[0103] (2) Profit function construction: Defining the profit function To evaluate the resource allocation effect of each region, the benefit function is related to the reduction of regional loss and the contribution of global loss reduction. For example, high-loss regions have higher benefits after adding resources.

[0104] (3) Quantum state evolution: The evolution of quantum superposition states is used to simulate resource cooperation and competition among regions. Before the quantum state collapses, all possible resource allocation schemes are considered simultaneously to find the potential global optimal solution.

[0105] (4) Quantum state collapse: Using the quantum measurement mechanism, the superposition state is collapsed into a specific allocation state, that is, the resource allocation ratio of each area is determined to ensure that more resources are allocated to high-loss areas first.

[0106] After completing resource allocation, the genetic algorithm is used to optimize the model parameters for the loss prediction model of each region. The genetic algorithm gradually optimizes the weights and learning parameters of the regional model by simulating the natural selection, crossover and mutation process, making the prediction results of each model more accurate and consistent with the global goal. Implementation steps: (1) Population initialization: Generate several sets of initial parameter combinations (populations), such as weights, learning rates, etc., for each regional prediction model.

[0107] (2) Fitness function definition: Using fitness function The model performance of each parameter combination is evaluated. The fitness function is defined as the mean absolute value of the prediction error, and the formula is as follows: .

[0108] (3) Selection and crossover: Select the parameter combination with better performance according to the fitness function, and generate a new parameter combination through crossover operation. For example, take part of the weights of two high fitness parameter combinations and perform linear weighting to form a new combination.

[0109] (4) Mutation operation: Randomly adjust some parameters to explore more possible parameter spaces to avoid falling into local optimal solutions.

[0110] (5) Iterative optimization: After multiple rounds of iterations, the parameter combination with the highest fitness function is finally selected as the optimal parameters of the regional model.

[0111] By combining quantum game optimization and genetic algorithm, the present invention ensures that resource allocation and model optimization in each region are consistent with the global life prediction goal. The optimized regional model not only improves the local prediction accuracy, but also reduces the cumulative effect of local prediction errors through the globally consistent fitness function.

[0112] The quantum game optimization algorithm ensures that high-loss areas are given priority to obtain more resources, such as reducing operating pressure or adding protective measures, thereby significantly delaying the loss of high-risk areas. The genetic algorithm improves the performance of the regional loss prediction model through parameter optimization, making the local life prediction results more accurate. The prediction error of the regional model is globally evaluated and optimized through the fitness function to ensure the reliability and consistency of the global life prediction results. The combination of quantum optimization and genetic algorithm not only improves the prediction accuracy, but also significantly reduces the optimization calculation time.

[0113] Example: In a certain oil transportation project, the oil transfer hose is divided into 10 local areas (each section is 10 meters long), and the loss prediction model for each area is optimized: (1) Quantum game optimization: Taking operating pressure as the optimization resource, the resource allocation ratio is determined through the quantum game optimization algorithm. Ultimately, the third area and the eighth area (high-loss area) obtain 20% and 15% of the resources respectively, and the remaining areas share the remaining resources equally.

[0114] (2) Genetic algorithm optimization: Using the historical operating data of the region, the genetic algorithm optimizes the parameters of each regional model (such as learning rate and weight), and ultimately reduces the prediction error of each regional model to below 1%.

[0115] (3) Fitness evaluation: through fitness function The global prediction performance was evaluated and the final fitness value was 0.05, indicating that the deviation between the prediction results and the actual data was extremely small.

[0116] (4) Global life prediction: The optimized regional model generates a global life prediction result, showing that the overall remaining life of the hose is 80 days, and points out that the remaining life of the high-loss area is 50 days.

[0117] Based on the global life prediction data and real-time collected operating status data, a digital twin system is constructed to correct the regional loss prediction model and form a closed-loop feedback optimization process, which outputs optimization data that dynamically reflects the operating status and remaining life prediction of the oil transfer hose.

[0118] Preferably, the digital twin system includes a difference analysis module, which generates a difference analysis result by comparing the real-time collected operating status data of the oil transfer hose with the global life prediction data to correct the parameters of the regional loss prediction model and update the status of the digital twin system.

[0119] The core function of the difference analysis module is to generate quantitative results reflecting the difference between the real-time collected data and the global life prediction data, and feed the difference back to the regional loss prediction model for correction. The main task of the difference analysis is to dynamically adjust the prediction capability of the digital twin system to adapt to changes in the real-time operating status.

[0120] The operating status data collected in real time from the multi-modal sensors of the hose include physical, chemical and environmental characteristic data such as stress, temperature and corrosion diffusion rate. These data represent the current operating status of the hose.

[0121] The global life prediction data generated from the regional loss prediction model is based on historical operation data and multi-field coupled simulation results, including life dissipation trends and remaining life predictions.

[0122] The difference analysis module generates difference analysis results by calculating the residuals between real-time data and predicted data. The residuals are calculated in the form of time series to characterize the degree to which the predicted results deviate from the actual operating status.

[0123] The difference analysis module takes the operation status data and the global life prediction data as input, and generates the difference analysis results by comparing the corresponding data points in the time series. Implementation steps: (1) Data synchronization and alignment: To ensure the comparability of real-time data and predicted data, the two sets of time series are first synchronized using the dynamic time warping (DTW) method to align data at different time steps.

[0124] (2) Residual calculation: The difference analysis module calculates the residual at each time step , the formula is as follows: in, Indicates The residual of the time step; Indicates the running status data collected in real time; Represents forecast data.

[0125] (3) Difference assessment: By analyzing the mean, variance, and trend changes of the statistical residuals, the difference analysis results are generated, such as whether there is a systematic deviation or a large local error in a specific area.

[0126] The difference analysis results are used to dynamically correct the parameters of the regional loss prediction model, so that the model can adapt to changes in operating conditions in real time, thereby improving the accuracy and timeliness of the prediction. Specific correction method: (1) Parameter adjustment: Adjust the key parameters of the regional model (such as weights and learning rates) based on the results of the difference analysis. For example, when the residuals show a certain trend, the model's ability to respond to new data can be improved by increasing the learning rate.

[0127] (2) Model retraining: For some regional models with large differences, the model is locally retrained by introducing real-time data to eliminate significant deviations.

[0128] (3) Multi-region consistency optimization: The modified regional model will be evaluated for its global consistency through the fitness function to ensure that the synergistic effect of the prediction results between regions is not affected.

[0129] The revised regional loss prediction model generates new global life prediction data and updates the status of the digital twin system. This status update includes: real-time operation status: the updated digital twin system accurately reflects the current hose loss, including local loss distribution and global life dissipation trend; remaining life prediction: based on the revised model, a new remaining life prediction result is output to guide the operation decision and maintenance plan of the hose.

[0130] By correcting the parameters of the regional loss prediction model in real time through the difference analysis module, the digital twin system can quickly adapt to changes in the hose operating status, significantly improving the system's dynamic response capabilities. By eliminating the difference between real-time data and predicted data, the global life prediction data generated by the corrected digital twin system is more accurate, providing a more reliable basis for operation and maintenance. The difference analysis module realizes real-time optimization and iterative updates, allowing the digital twin system to continuously improve performance and maintain a high-fidelity mapping of the hose operating status.

[0131] In an example, in a certain oil transportation project, the real-time operation data of the oil transfer hose includes: Stress data: The stress fluctuation range at the bending part is 10~15 MPa; temperature data: The temperature gradient is 30~70 ℃; Corrosion diffusion rate: 0.05~0.15 mm / day.

[0132] The predicted data generated by the regional loss prediction model shows that the stress fluctuation range of the bending part is 8~12MPa, which deviates from the actual data. The difference analysis module corrects the model through the following steps: (1) Residual calculation: Calculate stress residual The results show that the mean residual of the bending part is 2.5 MPa. (2) Model parameter adjustment: Based on the residual, the learning rate of the regional model is adjusted from 0.01 to 0.05 to improve the model's sensitivity to stress changes. (3) Model retraining: The latest real-time data is introduced to retrain the regional model. The prediction accuracy of the updated model is improved by 20%.

[0133] The updated digital twin system status shows that the accuracy of the total loss distribution in the bending parts has increased to 95%, and the global remaining life prediction result is more accurate, showing that the overall remaining life of the hose is 85 days.

[0134] Preferably, the closed-loop feedback optimization process includes the following steps: dynamically adjusting the input parameters of the multi-field collaborative simulation environment according to the difference analysis results, and recalculating the loss distribution data of the oil transfer hose; inputting the updated loss distribution data into the digital twin system, and updating the real-time operating status and remaining life prediction data of the oil transfer hose until the prediction error converges within the set range.

[0135] The starting point of closed-loop feedback optimization is the difference analysis result generated by the difference analysis module, which quantitatively reflects the difference between the real-time collected operating status data and the global life prediction data of the current digital twin system. The difference analysis result is provided in the form of time series residuals or local deviation distribution to guide the dynamic adjustment of the multi-field collaborative simulation environment.

[0136] The core of the multi-field collaborative simulation environment is to simulate the coupling of force field, thermal field and chemical field. Its input parameters include pressure gradient, temperature gradient, corrosion diffusion rate, etc. According to the difference analysis results, the simulation input parameters are dynamically adjusted to ensure that the simulation model can better match the real-time operating status. Specific adjustment methods: (1) Identify the key input parameters that cause deviations from the difference analysis results. For example, if the actual loss data in a certain area is significantly higher than the simulation results, it can be identified that the pressure gradient may be the main source of deviation. (2) Adjust the identified key parameters. The adjustment range is dynamically set according to the degree of deviation of the difference analysis results. For example, increase the pressure gradient to simulate the actual stress conditions, or increase the temperature gradient to match the high-temperature operating state. (3) Re-input the corrected input parameters into the multi-field collaborative simulation environment to generate new loss distribution data. These data reflect the updated description of the hose operating state by the adjusted simulation environment by re-coupling the force field, thermal field and chemical field.

[0137] The updated loss distribution data contains the results calculated by the simulation environment under the latest input parameters, which characterizes the local loss distribution of the hose material under the combined effects of force field, thermal field and chemical field. These data are input into the digital twin system through closed-loop feedback, replacing the original prediction data and further updating the system status.

[0138] Updates include: local loss distribution, reflecting the latest loss situation in each area of ​​the hose, especially the dynamic changes in high-loss areas. Global life prediction data, updated global life dissipation trends and remaining life predictions to guide operational decisions.

[0139] The closed-loop feedback optimization process gradually reduces the prediction error through multiple rounds of simulation iterations and digital twin system updates. When the prediction error converges to a set range (for example, the mean and variance of the residual are below a certain threshold), the closed-loop process ends and the final optimization result is output. Convergence conditions: Residual Requirements: in, represents the mean of the residuals; represents the standard deviation of the residual; and is the set convergence threshold.

[0140] By dynamically adjusting the input parameters of the simulation environment, the closed-loop feedback optimization process can quickly respond to changes in the hose's operating status and ensure that the prediction results are consistent with the actual operating status. Through iterative updates, the prediction error of the optimized digital twin system is significantly reduced, and the generated loss distribution data and life prediction results have higher accuracy. The iterative mechanism of closed-loop feedback ensures that the system's prediction results reach a stable state after multiple rounds of updates and are not affected by initial errors or environmental changes. The optimized digital twin system provides real-time guidance for the operation and maintenance of the hose, such as identifying high-risk areas in advance or adjusting operating parameters to extend service life.

[0141] Example: In a certain oil transportation project, the hose operating environment is complex, with a pressure gradient of 10 MPa / m, a temperature gradient of 50°C, and a corrosion diffusion rate of 0.1 mm / day. By comparing the initial loss distribution data generated by the multi-field collaborative simulation environment with the real-time operating status data, it is found that the loss prediction deviation in some areas is large.

[0142] The closed-loop feedback optimization process is implemented as follows: (1) The residuals between the real-time data and the predicted data were calculated, and it was found that the loss prediction at the bend was underestimated, with a residual mean of 1.5 MPa. (2) Based on the results of the difference analysis, the input parameters of the multi-field collaborative simulation environment were dynamically adjusted, increasing the pressure gradient at the bend from 10 MPa / m to 12 MPa / m, and the temperature gradient to 60°C. (3) The loss distribution data was recalculated to generate new data reflecting the adjusted environment, showing that the loss value at the bend was closer to the real-time data. (4) The updated loss distribution data was input into the digital twin system to generate new global life prediction data. After the update, the overall prediction error of the hose was reduced to 0.5 MPa, and the remaining life prediction in the high-loss area was adjusted from 60 days to 50 days.

[0143] After multiple rounds of iterations, the prediction error converges to the set range, the closed-loop process ends, and the final optimization result is generated, providing real-time decision support for the operation and maintenance of the hose.

[0144] like Figure 4 As shown, a system for implementing the method for predicting the life loss of the petroleum transfer hose comprises: The multimodal data acquisition module is used to collect data on the physical, chemical and environmental characteristics of the oil transfer hose during operation, and process the collected data to generate fused feature data; collect data on the physical characteristics (such as stress and vibration), chemical characteristics (such as corrosion diffusion rate) and environmental characteristics (such as temperature and humidity) of the oil transfer hose during operation. Through data cleaning and feature extraction, fused feature data is generated as the core input for subsequent modeling.

[0145] The multi-field collaborative simulation module is used to build a multi-field collaborative simulation environment for oil transfer hoses based on fused feature data, couple the force field, thermal field and chemical field, and use the finite element analysis method and multi-feature tensor decomposition algorithm to simulate the multi-field interaction, and generate loss distribution data that characterizes the local loss distribution of the oil transfer hose material; build a multi-field collaborative simulation environment for force field, thermal field and chemical field based on fused feature data. The finite element analysis (FEA) method and multi-feature tensor decomposition algorithm are used to model the multi-field interaction and generate loss distribution data that characterizes the local loss distribution of the hose material.

[0146] The regional loss prediction module is used to divide the loss distribution data into multiple local areas of the oil hose, and build a regional loss prediction model. It uses quantum optimization and genetic algorithms to achieve inter-regional collaboration and resource allocation, and generates global life prediction data including life dissipation trends and remaining life predictions; divide the loss distribution data into multiple local areas and build a regional loss prediction model. It uses quantum optimization algorithms to achieve efficient allocation of resources between regions, and combines genetic algorithms to optimize model parameters to generate global life prediction data, including life dissipation trends and remaining life.

[0147] The digital twin system module is used to correct the regional loss prediction model and form a closed-loop feedback optimization process based on the global life prediction data and the real-time collected operating status data, and output the optimization data that dynamically reflects the operating status and remaining life prediction of the oil transfer hose. The digital twin model is constructed based on the global life prediction data and the real-time collected operating status data. The regional prediction model is dynamically corrected through difference analysis, and the simulation parameters are updated in combination with the closed-loop feedback optimization process to achieve real-time mapping of the hose operating status and iterative optimization of life prediction.

[0148] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for predicting the life loss of a petroleum transfer hose, characterized in that: The following steps are involved: Collect the physical, chemical and environmental characteristics data of the oil transfer hose during operation, and process the data to generate fused feature data; Based on the fusion feature data, a multi-field collaborative simulation environment for oil transfer hoses is constructed, and coupled modeling of force field, thermal field and chemical field is performed. The finite element analysis method and multi-feature tensor decomposition algorithm are used to simulate the multi-field interaction, and the loss distribution data that characterizes the local loss distribution of oil transfer hose materials is generated. The loss distribution data is divided into multiple local areas of the oil transfer hose, and a regional loss prediction model is constructed. Through quantum optimization and genetic algorithms, inter-regional collaboration and resource allocation are achieved, and global life prediction data including life dissipation trends and remaining life predictions are generated; Based on the global life prediction data and real-time collected operating status data, a digital twin system is constructed to correct the regional loss prediction model and form a closed-loop feedback optimization process, which outputs optimization data that dynamically reflects the operating status and remaining life prediction of the oil transfer hose.

2. The method for predicting the life loss of a petroleum transfer hose according to claim 1, characterized in that: The processing of the physical, chemical and environmental characteristics data collected during the operation of the oil transfer hose includes the following steps: identifying and removing abnormal values ​​in the oil transfer hose operation data through a noise filtering algorithm; using a dynamic time alignment method to perform time offset correction based on the time series of the oil transfer hose operation data; using a feature extraction algorithm to extract the stress vibration frequency, corrosion diffusion rate and temperature change rate in the oil transfer hose operation data, and generate dynamic feature data after cleaning.

3. The method for predicting the life loss of a petroleum transfer hose according to claim 2, characterized in that: The cleaned dynamic feature data is compressed by a feature compression model, which includes a variational autoencoder. The variational autoencoder performs latent space mapping on the cleaned dynamic feature data, removes low-contribution features, and generates fused feature data with retained key dynamic features.

4. The method for predicting the life loss of a petroleum transfer hose according to claim 1, characterized in that: The construction of the multi-field collaborative simulation environment includes the following steps: A force field model of the oil transfer hose is established based on the mechanical modeling method to simulate the local stress distribution of the oil transfer hose under different pressure gradients and shear stresses. Based on heat conduction analysis, a thermal field model of oil transfer hose is established to calculate the effect of temperature gradient on the thermal aging rate of oil transfer hose materials; The chemical field model of the oil transfer hose is established through diffusion kinetic modeling to predict the diffusion path of corrosive substances in the oil transfer hose material; The above single-field model is modeled into multi-field coupling by numerical calculation method, where multi-field coupling is calculated by the following formula: in, Represents the total loss distribution of oil transfer hose materials; represents the local loss under the force field; Represents the local loss under the action of thermal field; Represents local losses under the action of chemical fields; are the space coordinates respectively.

5. The method for predicting the life loss of a petroleum transfer hose according to claim 4, characterized in that: The multi-field coupling is achieved by a multi-characteristic tensor decomposition algorithm, which specifically includes the following steps: Constructing a multi-modal tensor of force, thermal and chemical field data for oil hoses ; Use the following formula to transform the tensor To break it down: in, Represents the multi-modal tensor of the oil hose The data point value of , , Respectively represent The decomposition components are Weights on dimensions; represents the rank of tensor decomposition; Coupling loss distribution data is generated based on the decomposed tensor data and used to calculate the sum of local losses in the oil transfer hose.

6. The method for predicting the life loss of a petroleum transfer hose according to claim 1, characterized in that: The establishment of the regional loss prediction model includes the following steps: dividing the loss distribution data into multiple regional data, each regional data represents the loss information of the corresponding sub-region of the oil transfer hose; using the quantum game optimization algorithm to simulate the resource competition and cooperation between regions; combining the genetic algorithm to optimize the parameters of the prediction model of each region, so that the prediction results between regions reach global consistency.

7. The method for predicting the life loss of a petroleum transfer hose according to claim 1, characterized in that: The quantum game optimization algorithm is implemented by the following steps: optimizing the resource allocation between regions through quantum state superposition, simulating the iterative collapse process of quantum states to determine the optimal allocation; the genetic algorithm optimizes the key parameters of the regional loss prediction model through crossover, mutation and selection operations, and evaluates the model performance using the following fitness function: in, Indicates the fitness of the model; Indicates The actual value of samples; Indicates The predicted value of samples; Represents the total number of samples.

8. The method for predicting the life loss of a petroleum transfer hose according to claim 1, characterized in that: The digital twin system includes a difference analysis module, which generates a difference analysis result by comparing the real-time collected operating status data of the oil transfer hose with the global life prediction data to correct the parameters of the regional loss prediction model and update the status of the digital twin system.

9. The method for predicting the life loss of a petroleum transfer hose according to claim 1, characterized in that: The closed-loop feedback optimization process includes the following steps: dynamically adjusting the input parameters of the multi-field collaborative simulation environment according to the difference analysis results, and recalculating the loss distribution data of the oil transfer hose; inputting the updated loss distribution data into the digital twin system, and updating the real-time operating status and remaining life prediction data of the oil transfer hose until the prediction error converges within the set range.

10. A system for implementing the method for predicting the life loss of a petroleum transfer hose according to any one of claims 1 to 9, characterized in that: include: A multimodal data acquisition module is used to collect data on the physical, chemical and environmental characteristics of the oil transfer hose during operation, and process the collected data to generate fused feature data; The multi-field collaborative simulation module is used to build a multi-field collaborative simulation environment for oil transfer hoses based on fusion feature data, conduct coupled modeling of force field, thermal field and chemical field, and use finite element analysis method and multi-feature tensor decomposition algorithm to simulate multi-field interaction, and generate loss distribution data that characterizes the local loss distribution of oil transfer hose materials; The regional loss prediction module is used to divide the loss distribution data into multiple local areas of the oil transfer hose, and build a regional loss prediction model, using quantum optimization and genetic algorithms to achieve inter-regional collaboration and resource allocation, and generate global life prediction data including life dissipation trends and remaining life predictions; The digital twin system module is used to correct the regional loss prediction model and form a closed-loop feedback optimization process based on the global life prediction data and real-time collected operating status data, and output optimization data that dynamically reflects the operating status and remaining life prediction of the oil transfer hose.

Images