Intelligent agent-based mass energy network multi-source data alignment and fusion method and device

Abstract

The invention discloses a mass energy network multi-source data alignment and fusion method and device based on an intelligent agent. The method is characterized by comprising the following steps: initializing pipe network parameters of the pipeline mass energy network, and loading multi-source heterogeneous original internal detection data of the pipeline mass energy network; calling a standardized data analysis interface to analyze and standardize the original internal detection data, and determining a pipeline internal state reference model; and loading external detection data of the pipeline mass energy network, carrying out internal and external alignment on the external detection data and the internal state reference model of the pipeline, and determining internal and external total-factor digital twin bodies of the pipeline. According to the method, automation and intelligentization of the whole process can be achieved, adaptability and high expansibility are achieved, internal detection microdefects and external macroscopic environment data are associated under the unified space-time reference, and the efficiency of pipeline risk assessment and automation, precision and intelligentization of pipeline integrity management are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of pipeline management technology, and in particular to a method and apparatus for aligning and fusing multi-source data in a mass-energy network based on intelligent agents. Background Technology

[0002] Pipelines are a crucial component of the five major modes of transportation and nine major infrastructure networks. As the primary means of transporting crude oil and natural gas, oil and gas pipeline networks are vital lifelines for energy security. Traditionally, the safe operation of pipeline networks relies on maintenance by personnel to ensure network management and risk safety. However, with the development of pipeline networks into new energy quality networks, and the widespread adoption of various monitoring methods such as internal and external pipeline inspections, satellite remote sensing, drone inspections, video surveillance, and cathodic protection, a wealth of data resources has been generated. However, these data suffer from problems such as different collection times, heterogeneous sources, inconsistent spatial benchmarks, and significant differences in detection scales, making effective data fusion difficult and affecting the accuracy of risk assessment and digital twin construction. In existing technologies, traditional data digital twin methods are mostly based on digital reconstruction from a single data source. These methods are computationally expensive, have long modeling cycles, and cannot achieve "co-development" with the actual operation of the energy quality network. Some studies have attempted to introduce multi-source data fusion, but most of them remain at the level of data overlay and visualization, lacking intelligent alignment mechanisms for complex scenarios of mass-energy equivalence networks, especially in the matching of internal and external detection and the correlation between microscopic damage information and macroscopic environmental risks. Summary of the Invention

[0003] This invention provides a method and apparatus for aligning and fusing multi-source data in mass-energy equivalence networks based on intelligent agents, in order to solve the technical problem that existing technologies cannot intelligently and quickly process the alignment and fusion of multi-source data in mass-energy equivalence networks.

[0004] According to one aspect of the present invention, a method for aligning and fusing multi-source data of a pipeline mass-energy network based on an intelligent agent is provided, comprising: initializing the pipeline parameters of the pipeline mass-energy network, and loading the original internal detection data of the multi-source heterogeneous pipeline mass-energy network;

[0005] The raw internal detection data is parsed and standardized by calling the standardized data parsing interface to determine the pipeline internal state benchmark model.

[0006] Load the external inspection data of the pipeline quality and energy network, align the external inspection data with the internal state benchmark model of the pipeline, and determine the digital twin of all elements inside and outside the pipeline.

[0007] According to another aspect of the present invention, a multi-source data alignment and fusion device for mass-energy equivalence networks based on intelligent agents is provided, comprising:

[0008] The data module is used to initialize the pipeline network parameters of the pipeline quality and energy network and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network.

[0009] The internal detection alignment module is used to call the standardized data parsing interface to parse and standardize the original internal detection data and determine the pipeline internal state benchmark model.

[0010] The internal and external detection alignment module loads the external detection data of the pipeline quality and energy network, aligns the external detection data with the internal state benchmark model of the pipeline, and determines the digital twin of all elements inside and outside the pipeline.

[0011] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0012] At least one processor; and

[0013] A memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the agent-based mass-energy network multi-source data alignment and fusion method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the agent-based mass-energy network multi-source data alignment and fusion method described in any embodiment of the present invention.

[0016] The technical solution of this invention initializes the pipeline quality and energy network parameters and loads the multi-source heterogeneous original internal inspection data of the pipeline quality and energy network; it calls a standardized data parsing interface to parse and standardize the original internal inspection data to determine the pipeline internal state benchmark model; it loads the external inspection data of the pipeline quality and energy network and aligns the external inspection data with the pipeline internal state benchmark model to determine a digital twin of all elements inside and outside the pipeline. This invention can achieve full-process automation and intelligence, has adaptability and strong scalability, and correlates internal inspection micro-defects with external macro-environmental data under a unified spatiotemporal benchmark, effectively improving the efficiency of pipeline risk assessment and the automation, accuracy and intelligence of pipeline integrity management.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart of a method for aligning and fusing multi-source data in a mass-energy equivalence network based on an intelligent agent is provided in this embodiment of the invention.

[0020] Figure 2 A flowchart illustrating another agent-based method for aligning and fusing multi-source data in a mass-energy equivalence network, as provided in this embodiment of the invention;

[0021] Figure 3 A flowchart illustrating another agent-based method for aligning and fusing multi-source data in a mass-energy equivalence network, as provided in this embodiment of the invention;

[0022] Figure 4 This is a schematic diagram of a multi-source data alignment and fusion device for mass-energy equivalence networks based on intelligent agents, provided in an embodiment of the present invention.

[0023] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Figure 1 This invention provides a flowchart of a method for aligning and fusing multi-source data in a mass-energy equivalence network based on an intelligent agent. This embodiment is applicable to situations where multi-source data in a mass-energy equivalence network is aligned and fused using an intelligent agent. This method can be executed by an intelligent agent-based multi-source data alignment and fusion device for a mass-energy equivalence network. This intelligent agent-based multi-source data alignment and fusion device for a mass-energy equivalence network can be implemented in hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0027] S110. Initialize the pipeline network parameters of the pipeline quality and energy network, and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network.

[0028] Optionally, the pipeline quality and energy network is a complex pipeline management system integrating multiple levels of technologies. The implementation of this invention relies on a layered software system architecture. This architecture uses an intelligent agent as the core scheduling unit for functional implementation, integrates external tools and data sources based on the Model Context Protocol (MCP), and injects relevant knowledge of the pipeline quality and energy network using Retrieval-Augmented Generation (RAG) technology to obtain a pipeline domain knowledge base. Before processing multi-source data, the pipeline network parameters need to be initialized.

[0029] Optionally, the initialization parameters for the pipeline quality and energy network include the basic parameters of the corresponding pipelines, such as total pipeline length, diameter, and material; and an MCP server endpoint is provided to connect to data parsing, data calculation, and coordinate calculation tools, loading a pre-built pipeline domain knowledge base. This pipeline domain knowledge base contains industry standards, expert experience cases, historical matching patterns, and other data related to the pipeline quality and energy network.

[0030] Optionally, the raw internal inspection data can be internal inspection data from multiple different inspection parties for the corresponding pipelines in the mass energy network. Since the raw internal inspection data comes from multiple data sources, it has different data formats. For example, the data formats can be XML, PDF, and CSV formats, etc.

[0031] Optionally, in this invention, a system core control agent is set up. The system core control agent calls a data connection tool based on the MCP protocol to communicate with multiple data sources and load multi-source heterogeneous raw internal detection data. After the system core control agent completes the initialization process and self-test, the system core control agent will sequentially schedule each agent to process the multi-source heterogeneous raw internal detection data according to the preset workflow. During the operation, it is event-driven, and each agent coordinates and exchanges data through a message passing mechanism.

[0032] Specifically, initialize the pipeline parameters of the pipeline quality and energy network, and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network.

[0033] S120. Call the standardized data parsing interface to parse and standardize the original internal detection data to determine the pipeline internal state benchmark model.

[0034] The standardized data parsing interface can be a pre-configured functional interface for parsing and standardizing data from intelligent networks. It should be noted that the standardized data parsing interface connects to the standardized data parsing tool and is invoked via the MCP protocol.

[0035] Optionally, the standardized data parsing interface can identify the data format used when collecting raw internal detection data from different data sources, and then parse the raw internal detection data from each data source, standardize the raw internal detection data, and perform data alignment within the pipeline network.

[0036] Optionally, the pipeline internal state benchmark model can be a data information model describing the internal state of pipelines in the pipeline quality and energy network. In the pipeline internal state benchmark model, the circumferential welds and pipeline defects inside each pipeline in the pipeline quality and energy network are displayed in a visual form, showing the identifiers of the circumferential welds and pipeline defects. The internal state information of the circumferential welds and pipeline defects corresponding to each identifier is displayed in a dynamic and visual form, and the relevant indicators of the circumferential welds and pipeline defects during the internal alignment process are statistically displayed.

[0037] Optionally, after collecting data from different data sources inside the pipeline, in order to link the different original internal detection data with the comparative data stored in the pipeline quality and energy network or collected in historical periods, the relevant data inside the pipeline can be compared and matched through pipeline alignment, which can effectively improve the efficiency of pipeline data processing and the accuracy of pipeline data.

[0038] Specifically, the raw internal detection data is parsed and standardized by calling the standardized data parsing interface to determine the baseline model of the pipeline's internal state.

[0039] S130. Load the external detection data of the pipeline quality and energy network, align the external detection data with the internal state benchmark model of the pipeline, and determine the digital twin of all elements inside and outside the pipeline.

[0040] Optionally, external inspection data can be obtained by collecting data on the external environment, surface conditions, and ancillary facilities of the pipeline quality and energy network through external data acquisition methods. It should be noted that data on the external environment, surface conditions, and ancillary facilities of the pipeline quality and energy network can be collected through methods such as drone inspections, ground surveys, and video surveillance.

[0041] Optionally, after collecting external inspection data, the external inspection data can be spatially correlated with the pipeline internal state benchmark model to achieve synchronous monitoring of the pipeline internal state and external environment state for each circumferential weld and pipeline defect.

[0042] Optionally, the full-element digital twin of the pipeline can be a data information model that spatially and synchronously describes the internal state of the pipeline and the external environment within the pipeline quality and energy network. The full-element digital twin of the pipeline achieves the fusion of internal and external data within a unified spatial framework. It not only includes information on circumferential welds and pipeline defects inside the pipeline, but also links high-definition images of the external environment, facility status photos, and geographic information to the corresponding spatial locations. This provides a unified data view of internal and external information for subsequent pipeline risk assessment and integrity management, achieving automated, precise, and intelligent cross-modal data alignment.

[0043] Specifically, the external inspection data of the pipeline quality and energy network is loaded, and the external inspection data and the internal state benchmark model of the pipeline are aligned internally and externally to determine the digital twin of all elements inside and outside the pipeline.

[0044] The technical solution of this invention initializes the pipeline quality and energy network parameters and loads the multi-source heterogeneous original internal inspection data of the pipeline quality and energy network; it calls a standardized data parsing interface to parse and standardize the original internal inspection data to determine the pipeline internal state benchmark model; it loads the external inspection data of the pipeline quality and energy network and aligns the external inspection data with the pipeline internal state benchmark model to determine a digital twin of all elements inside and outside the pipeline. This invention can achieve full-process automation and intelligence, has adaptability and strong scalability, and correlates internal inspection micro-defects with external macro-environmental data under a unified spatiotemporal benchmark, effectively improving the efficiency of pipeline risk assessment and the automation, accuracy and intelligence of pipeline integrity management.

[0045] Figure 2This is a flowchart illustrating another agent-based method for aligning and fusing multi-source data in a mass-energy equivalence network, provided by an embodiment of the present invention. The relationship between this embodiment and the previous embodiments is to specifically explain the data alignment of detection data within a pipeline. For example... Figure 2 As shown, the method includes:

[0046] S210. Initialize the pipeline network parameters of the pipeline quality and energy network, and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network.

[0047] S220. Based on the data processing intelligent agent calling the standardized data parsing interface, the original internal detection data is parsed and standardized to determine the standardized dataset.

[0048] Optionally, the standardized dataset can be pipeline inspection data in a uniform standard unit system.

[0049] Optionally, the system's core control agent invokes the data processing agent. The data processing agent uses the MCP protocol to call a standardized data parsing interface to identify raw internal detection data from different data sources, parses the raw internal detection data, and unifies the key physical quantities of the raw internal detection data to a standard unit system. For example, the measured value S in the standardized dataset in the standard unit system... std The conversion formula is as follows:

[0050]

[0051] Among them, S raw The measured values ​​in the original internal detection data, O src U represents the offset of the measured values ​​in the original internal detection data. src and U std These are conversion factors for the original and standard units of the raw internal inspection data. For example, converting wall thickness values ​​in inches to millimeters.

[0052] Specifically, the data processing agent calls a standardized data parsing interface to parse and standardize the original internal detection data to determine a standardized dataset.

[0053] S230. Based on the data processing intelligent agent, calculate the key quality indicators of the standardized dataset and extract the pipeline dataset corresponding to the pipeline quality and energy network.

[0054] Optionally, the pipeline dataset can be a dataset that records key quality indicators from a standardized dataset. The pipeline dataset records various circumferential welds and pipeline defects within the pipeline quality and energy network.

[0055] Optionally, in the pipeline dataset, identifiers, pipeline mileage locations, wall thicknesses, defect depths, and stress values ​​can be set for each circumferential weld and pipeline defect inside the pipeline.

[0056] Optionally, the data processing agent processes the standardized dataset, accurately identifies and quantifies various pipeline feature parameters, and sorts and organizes them according to pipeline mileage position to form a structured feature sequence, thus obtaining the pipeline dataset. For example, the mathematical representation of the feature sequence is: with the pipeline centerline coordinates as S(I), and I as the mileage position, then the feature sequence... This can be expressed as:

[0057]

[0058] Where WT represents the wall thickness and D represents the defect depth. This indicates the stress value.

[0059] Specifically, based on the data processing intelligent agent, key quality indicators are calculated on the standardized dataset to extract the pipeline dataset corresponding to the pipeline quality and energy network.

[0060] S240. Load the comparison dataset of the pipeline quality and energy network, align at least one circumferential weld and pipeline defect in the pipeline dataset based on the comparison dataset, and construct the pipeline internal state benchmark model.

[0061] Optionally, the comparison dataset consists of pipeline inspection data stored in the pipeline quality and energy network or collected from historical periods. For the comparison dataset, to improve processing efficiency, stable and significant feature points are extracted as matching primitives. These matching primitives can be circumferential welds and pipeline defects. For example, the circumferential welds could be circumferential welds and characteristic welds, and the pipeline defects could be metal loss defects.

[0062] Optionally, for each matching primitive in the comparison dataset, the matching primitive is converted into a weld feature vector or a defect feature vector to represent the mileage position, circumferential angle, and geometry of the matching primitive.

[0063] Optionally, the feature vectors of the matching primitives can also be converted into mileage location vectors, circumferential angle vectors, and geometric shape vectors.

[0064] Specifically, the comparative dataset of the pipeline mass energy network is loaded, and at least one circumferential weld and pipeline defect in the pipeline dataset are aligned based on the comparative dataset to construct a benchmark model of the pipeline's internal state.

[0065] Optionally, in another optional embodiment of the present invention, the step of aligning at least one circumferential weld and pipe defect in the pipe dataset based on the comparison dataset to construct the pipe internal state benchmark model includes:

[0066] The circumferential weld alignment agent aligns the circumferential weld with the comparison dataset to construct a circumferential weld matching pair list; the pipeline defect alignment agent aligns the pipeline defect with the comparison dataset to construct a defect matching pair list; and the pipeline internal state benchmark model is constructed based on the circumferential weld matching pair list and the defect matching pair list.

[0067] The circumferential weld matching pair list can be composed of each pair of circumferential welds, which are the matching primitives corresponding to each circumferential weld in the comparison dataset. It should be noted that for each pair of circumferential welds, there are corresponding data such as the identifier of the circumferential weld and the matching primitive, the pipeline mileage, the circumferential angle, and the deviation.

[0068] Optionally, the system core control agent invokes the circumferential weld alignment agent to align the circumferential weld with the comparison dataset to obtain a list of circumferential weld matching pairs. The circumferential weld alignment agent can be a pre-set agent used for circumferential weld alignment.

[0069] Optionally, in another optional embodiment of the present invention, the circumferential weld alignment agent performs circumferential weld alignment on the circumferential weld and the comparison dataset to construct a circumferential weld matching pair list, including:

[0070] The circumferential weld alignment agent constructs a circumferential weld feature description vector for each circumferential weld.

[0071] For each of the circumferential weld feature description vectors, the circumferential weld feature description vectors are aligned with the comparison dataset by the circumferential weld alignment agent to construct the circumferential weld matching pair list.

[0072] Optionally, the feature description vector of the circumferential weld can distinguish the feature description vectors of different circumferential welds. It should be noted that the feature description vector of the circumferential weld comprehensively expresses the local context information of the circumferential weld; the feature description vector of the circumferential weld is constructed separately by the circumferential weld alignment agent, and the feature description vector of the circumferential weld is obtained through... The feature description vector of the circumferential weld can be represented as:

[0073]

[0074] in, and These represent the normalized distances from the i-th circumferential weld to its nearest upstream and downstream circumferential welds, respectively. Let be the circumferential azimuth angle of the i-th circumferential weld, i.e., the circumferential angle. This is the code for the weld type of the i-th circumferential weld, serving as the identifier of the circumferential weld. For example, the weld type can be a straight weld or a spiral weld.

[0075] Optionally, when aligning circumferential welds, the circumferential weld alignment agent calculates the similarity between the circumferential weld feature description vector and each matching primitive for each circumferential weld feature description vector, so as to select the most similar matching primitive and thus form each pair of circumferential welds.

[0076] Optionally, the weld feature vector corresponding to the matching primitive can be represented as: Similarity is calculated using a mileage deviation-robust metric. For example, the circumferential weld alignment agent invokes a high-performance linear algebra tool for similarity calculation. The formula for similarity calculation is expressed as:

[0077]

[0078] in, Represents the Hadamard product. Represents the reciprocal of each element of the vector. It is a vector of all 1s. It is the L2 norm. The similarity is calculated.

[0079] Optionally, the circumferential weld alignment agent uses a greedy algorithm to find the optimal matching pair for each circumferential weld feature description vector. If multiple matching pairs exist for the circumferential weld feature description vectors, the circumferential weld alignment agent will activate the RAG mechanism to query the feature patterns based on the circumferential weld. For example, feature patterns. Represented as:

[0080]

[0081] Among them, C k It is the feature vector of the k-th circumferential weld matching case in the pipeline domain knowledge base.

[0082] The RAG mechanism returns the most relevant historical cases and their decision-making strategies to guide the circumferential weld alignment agent in selecting the optimal matching pair for each circumferential weld feature description vector.

[0083] Specifically, a circumferential weld seam alignment agent is used to construct a circumferential weld seam feature description vector for each circumferential weld seam; corresponding to each circumferential weld seam feature description vector, the circumferential weld seam alignment agent is used to align the circumferential weld seam feature description vector with the comparison dataset to construct a list of circumferential weld seam matching pairs.

[0084] Optionally, the defect matching pair list can be each pair of pipeline defects consisting of the matching primitives corresponding to each pipeline defect in the comparison dataset; it should be noted that for each pair of pipeline defects, there are corresponding pipeline defect and matching primitive identifiers, spatial locations (pipeline mileage and circumferential angle), feature parameters, matching confidence, and other data.

[0085] Optionally, the system core control agent invokes the pipeline defect alignment agent to align the defect features of the pipeline defect and the comparison dataset, constructing a list of defect matching pairs. The pipeline defect alignment agent can be a pre-set agent used for intra-defect alignment.

[0086] Optionally, in another optional embodiment of the present invention, the pipeline defect alignment agent aligns the defect features of the pipeline defect and the comparison dataset to construct a defect matching pair list, including:

[0087] The pipeline defect alignment agent divides the pipeline mass-energy network into multiple continuous pipeline segments based on the circumferential weld matching pair list.

[0088] The pipeline defect alignment agent is used to align multiple continuous pipeline segments and calculate the average mileage deviation to determine the alignment success rate and average mileage deviation.

[0089] If the alignment success rate and average mileage deviation meet the preset accuracy requirements, the pipeline defect alignment agent constructs a defect feature description vector for each pipeline defect in the pipeline dataset.

[0090] For each continuous pipeline segment, the pipeline defect alignment agent performs defect feature alignment based on the defect feature description vector and the comparison dataset to construct the defect matching pair list.

[0091] Optionally, a continuous pipeline segment can be a continuous individual segment of a pipeline quality and energy network; it should be noted that individual segments are connected by welding to form a pipeline quality and energy network.

[0092] Optionally, the alignment success rate can be the success rate of aligning all continuous pipe network segments with the actual pipeline. It should be noted that for each continuous pipe network segment, it is determined whether the continuous pipe network segment is aligned with the actual pipeline. If aligned, the alignment is considered successful; otherwise, it is considered unsuccessful, and the alignment success rate is calculated. The average mileage deviation can be the average of the mileage deviations between each continuous pipe network segment and the actual pipeline. The mileage deviations between the continuous pipe network segments and the actual pipeline are identified, and the overall average mileage deviation is calculated.

[0093] Optionally, the preset accuracy requirements can be pre-set to meet the conditions for identifying the alignment accuracy of circumferential welds. In this invention, a quality verification agent for quality optimization is also pre-set. The quality verification agent calculates the alignment success rate and average mileage deviation for each individual pipe segment and circumferential weld in the continuous pipeline network. If the alignment success rate and average mileage deviation do not meet the preset accuracy requirements, the optimization process is triggered, parameters are adjusted, re-matching is performed, and the circumferential weld matching pair list is updated.

[0094] Optionally, if the alignment success rate and average mileage deviation meet preset accuracy requirements, a defect feature description vector is constructed for each pipeline defect in the pipeline dataset. This defect feature description vector can be a feature description vector that distinguishes different pipeline defects. For example, the defect feature description vector is constructed through... The defect feature description vector is represented as follows:

[0095]

[0096] Where d is the relative distance from the pipeline defect to the nearest upstream circumferential weld. is the circumferential angle of the pipeline defect, l, w, h are the normalized values ​​of the length, width, and depth of the pipeline defect, and t is the code of the pipeline defect type.

[0097] Optionally, the pipeline defect alignment agent aligns internal defects in the pipeline using a differentiated strategy based on the defect distribution density of each continuous pipeline segment. The defect distribution density is the average spacing between pipeline defects within the continuous pipeline segment. A preset average spacing threshold is used to determine whether the defect distribution is sparse or dense. If the defect distribution density is less than the preset average spacing threshold, the continuous pipeline segment is considered to have a sparse defect distribution; if the defect distribution density is not less than the preset average spacing threshold, the continuous pipeline segment is considered to have a dense defect distribution.

[0098] Optionally, if the defect distribution density is less than a preset average spacing threshold, a similarity score is determined by calculating the similarity between the defect feature description vector and each matching primitive in the comparison dataset using feature distance. The highest similarity score is taken as the defect score for each pair of pipelines. For example, the similarity score is determined by S... ij The similarity score S is represented as follows. ij The calculation method is as follows:

[0099]

[0100] in, Represents the feature description vector of the i-th defect. d i and Let d and d be the corresponding vectors for the i-th defect feature description vector. ; Let i be the feature vector of the pipeline defect corresponding to the i-th matching primitive. This represents the degree of similarity in the geometric features of the defects. w1+w2+w3=1, where w1, w2, and w3 are weighting coefficients.

[0101] Optionally, if the defect distribution density is not less than a preset average spacing threshold, the pipeline defect alignment agent calls the computational geometry tool library via the MCP protocol using a convex hull-based global matching method. This involves matching the defect points of each defect feature description vector and the pipeline defect feature vector separately. Construct a convex hull for the coordinates. For example, the global matching method for the convex hull is expressed as:

[0102]

[0103] Here, H1 represents the convex hull of the defect feature description vector, and H2 represents the convex hull of the pipeline defect feature vector. The optimal global transformation parameters are found through an optimization algorithm. To minimize the difference between the two convex hulls after transformation, the objective function can be defined as:

[0104]

[0105] in, This represents the symmetric difference operator; Area calculates the area. These are translation parameters. The solution process may use iterative nearest point or its variants. The solved global transformation parameters will be... The global transformation parameters are applied to the pipe defects and matching primitives, and the matching primitives and pipe defects are corrected in the coordinate system. In the corrected coordinate system, a distance-based matching method is used to finally pair the defects, resulting in each pair of pipe defects.

[0106] Optionally, for each pair of pipe defects, if a complex situation with similar features but slight spatial deviations is encountered during the matching process, the pipe defect alignment AI will query similar cases in the knowledge base through RAG, and then calculate indicators such as similar case matching rate, average position error and type consistency rate to ensure the reliability of the results.

[0107] Specifically, the pipeline quality and energy network is divided into multiple continuous pipeline segments by a pipeline defect alignment agent based on a list of matching pairs for circumferential welds; the pipeline defect alignment agent calculates the average mileage deviation for multiple continuous pipeline segments to determine the average mileage deviation; if the average mileage deviation meets the preset accuracy requirements, the pipeline defect alignment agent constructs a defect feature description vector for each pipeline defect in the pipeline dataset; for each continuous pipeline segment, the pipeline defect alignment agent aligns defect features based on the defect feature description vector and the comparison dataset to construct a list of defect matching pairs.

[0108] Specifically, the circumferential weld alignment agent aligns the circumferential welds with the comparison dataset to construct a circumferential weld matching pair list; the pipeline defect alignment agent aligns the pipeline defects with the comparison dataset to construct a defect matching pair list; and a pipeline internal state benchmark model is constructed based on the circumferential weld matching pair list and the defect matching pair list.

[0109] Optionally, the pipeline internal condition benchmark model can also display statistical indicators such as circumferential weld alignment rate, defect alignment rate, average position error, and maximum deviation during the internal alignment process of circumferential welds and pipeline defects.

[0110] S250. Load the external detection data of the pipeline quality and energy network, align the external detection data with the internal state benchmark model of the pipeline, and determine the digital twin of all elements inside and outside the pipeline.

[0111] The technical solution of this invention initializes the pipeline quality and energy network parameters and loads the multi-source heterogeneous original internal inspection data of the pipeline quality and energy network; it calls a standardized data parsing interface to parse and standardize the original internal inspection data to determine the pipeline internal state benchmark model; it loads the external inspection data of the pipeline quality and energy network and aligns the external inspection data with the pipeline internal state benchmark model to determine a digital twin of all elements inside and outside the pipeline. This invention can achieve full-process automation and intelligence, has adaptability and strong scalability, and correlates internal inspection micro-defects with external macro-environmental data under a unified spatiotemporal benchmark, effectively improving the efficiency of pipeline risk assessment and the automation, accuracy and intelligence of pipeline integrity management.

[0112] Figure 3 This is a flowchart illustrating another agent-based method for aligning and fusing multi-source data in a mass-energy equivalence network, provided by an embodiment of the present invention. The relationship between this embodiment and the previous embodiments is to specifically explain the data alignment of detection data inside and outside the pipeline. For example... Figure 3 As shown, the method includes:

[0113] S310. Initialize the pipeline network parameters of the pipeline quality and energy network, and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network.

[0114] S320. Call the standardized data parsing interface to parse and standardize the original internal detection data to determine the pipeline internal state benchmark model.

[0115] S330. Based on the data processing intelligent agent, the external detection data is standardized to determine the external data of the pipeline.

[0116] Optionally, the external pipeline data can be standardized external inspection data. For example, distortion correction is performed on UAV imagery in the external inspection data, and point cloud data is filtered and thinned.

[0117] Optionally, the system's core control agent calls the data processing agent, which uses the MCP protocol to call an external data parsing tool to standardize the external detection data and obtain external pipeline data.

[0118] Specifically, based on the data processing intelligent agent, external detection data is standardized to determine the external data of the pipeline.

[0119] S340. Align the external data of the pipeline with the internal state benchmark model of the pipeline to determine the digital twin of all elements inside and outside the pipeline.

[0120] Specifically, the external data of the pipeline and the internal state benchmark model of the pipeline are aligned internally and externally to determine a digital twin of all elements inside and outside the pipeline.

[0121] Optionally, in another optional embodiment of the present invention, the step of aligning the external data of the pipeline and the internal state reference model of the pipeline to determine a digital twin of all elements inside and outside the pipeline includes:

[0122] The visual intelligent agent is used to identify and extract key spatial anchor points and pipeline pile points from the external data of the pipeline.

[0123] By using intelligent agents inside and outside the circumferential weld pipe to align the key spatial anchor points and the circumferential weld matching list with the space inside and outside the pipe, the circumferential weld space mapping lookup table is determined.

[0124] By using intelligent agents inside and outside the pipeline defects to align the pipeline pile points and the defect matching list in the pipeline space, a defect space mapping lookup table is determined.

[0125] The digital twin of all elements inside and outside the pipeline is determined based on the circumferential weld space mapping lookup table and the defect space mapping lookup table.

[0126] Optionally, the visual agent can be a pre-set deep learning-based computer vision model that can automatically identify and extract key spatial anchor points and pipeline markers from external detection data. For example, key spatial anchor points can be artificial landmarks, pipeline ancillary facilities, and natural features; artificial landmarks can be various pipeline markers, such as mileage markers, cathodic protection test markers, and marker posts; pipeline ancillary facilities can be the starting and ending points of valves, elbows, tees, and crossing structures; natural features can be permanent and salient features along the pipeline route, such as road intersections, detached houses, and specific vegetation communities.

[0127] Optionally, the intelligent agents inside and outside the circumferential weld can be pre-set intelligent agents for aligning the circumferential weld inside and outside the pipe; the intelligent agents inside and outside the pipe defect can be pre-set intelligent agents for aligning the pipe defect inside and outside the pipe.

[0128] Optionally, the circumferential weld space mapping lookup table can be a mapping data table between external pipeline data and the corresponding internal circumferential welds; the circumferential weld space mapping lookup table establishes the circumferential coordinates and pipeline mileage from the external pipeline data to the internal circumferential welds. It should be noted that the pipeline centerline coordinate system is a local coordinate system based on the pipeline centerline.

[0129] Optionally, the defect space mapping lookup table can be a mapping data table between external pipeline data and corresponding pipeline defects; the circumferential weld space mapping lookup table establishes the circumferential coordinates and pipeline mileage from external pipeline data to the pipeline defect's internal pipeline coordinates.

[0130] Optionally, the key spatial anchor points and the circumferential weld matching pair list are aligned internally and externally by intelligent agents inside and outside the circumferential weld pipe to determine the circumferential weld spatial mapping lookup table. The specific process is as follows: For each key spatial anchor point, the visual feature descriptor of the key spatial anchor point in external data is identified. The visual feature descriptor is used to represent the numerical vector corresponding to the key visual features of the external key spatial anchor point, serving as the vectorized representation of the key spatial anchor point. For example, the visual feature descriptor is obtained through V... anchor The representation is as follows: The system's core control agent, based on the MCP protocol, invokes GNSS / IMU integrated navigation data to identify the geodetic coordinates of key spatial anchor points in the geodetic coordinate system. For example, the geodetic coordinates are represented as... .

[0131] Optionally, after obtaining each key spatial anchor point, the intelligent agents inside and outside the circumferential weld pipe call a high-precision coordinate transformation service via the MCP protocol. Based on the coordinate transformation service, the geodetic coordinates of each key spatial anchor point are transformed to the anchor point local coordinates in a local coordinate system based on the pipeline centerline. It should be noted that the coordinate transformation service can call pre-set control point data along the pipeline corresponding to the pipeline quality and energy network, and perform coordinate transformation based on the pre-set control point data. For example, the coordinate transformation service typically uses the Bursa seven-parameter method or a custom projection transformation to solve the transformation function from geodetic coordinates to anchor point local coordinates. The transformation function is obtained through T... coord The conversion process can be represented as follows:

[0132]

[0133] in, The key spatial anchor point transformation is the pipeline mileage in a local coordinate system based on the pipeline centerline. The key spatial anchor point transformation is the circumferential angle in a local coordinate system based on the pipeline centerline. P is the radial distance of the key spatial anchor point transformation in the local coordinate system based on the pipeline centerline; P is the pre-set transformation parameter set of the pipeline mass-energy network.

[0134] Optionally, for each key spatial anchor point, the local coordinates of the anchor point are matched using the pipeline mileage and circumferential angle. That is, the matched coordinates of the key spatial anchor point are... The actual position of each aligned circumferential weld is obtained by using a circumferential weld matching pair list. The matching coordinates of each key spatial anchor point and the actual positions of each aligned circumferential weld between the intelligent agents inside and outside the circumferential weld pipe. A preliminary matching process is performed, calculating the similarity score between the matching coordinates of each key spatial anchor point and the actual position of each aligned circumferential weld. For example, the pipeline mileage for the i-th key spatial anchor point... Pipeline mileage aligned with the j-th circumferential weld The i-th key spatial anchor point is represented by vectorization as The j-aligned circumferential weld is vectorized as follows: ,pass Indicates the similarity score. The calculation formula is:

[0135]

[0136] Where α and β are weighting coefficients, It is the scale parameter of the mileage search range.

[0137] Optionally, if there are numerous ambiguities in the similarity scores or the similarity scores are too low, the agents inside and outside the circumferential weld pipe will initiate the RAG mechanism. The agents will construct a query vector from the geographical environmental features of the current pipe segment, the quality indicators of the external inspection data, and the deviation patterns of the similarity scores, and send a request to the spatial registration knowledge base. The knowledge base can return successful registration strategies for similar scenarios. The quality indicators of the external inspection data can be the quality assessment results of the external inspection data by the agents inside and outside the circumferential weld pipe.

[0138] Optionally, for the local coordinates of each key spatial anchor point, the similarity score of the local coordinates of the anchor point in the list of matching circumferential weld seams is identified. Based on the similarity score, key spatial anchor points with high similarity and aligned circumferential weld seams are obtained as high-confidence spatial anchor point pairs. Then, a more accurate local correction transformation is calculated to eliminate systematic registration errors. The local correction transformation can be a translation correction, an affine transformation, or a thin-plate spline transformation. For example, the local correction transformation uses T...correct Representation; define the optimal correction transform as Depending on the number and distribution of spatial anchor pairs, the optimal correction transformation is: Defined as:

[0139]

[0140] Where T represents the correction transformation between the matching coordinates of the key spatial anchor point and the actual position of the aligned circumferential weld; Let T be the transformation that minimizes the error of the correction transformation. Sum the results of k high-confidence spatial anchor point pairs, where k is the k-th spatial anchor point pair. Represented as the matching coordinates of the key spatial anchor points in the k-th spatial anchor point pair. This represents the actual position of the circumferential weld seam aligned with the k-th spatial anchor point.

[0141] The solution process for the intelligent agents inside and outside the circumferential welded pipe is completed by calling the numerical optimization library via the MCP protocol. The optimal correction transformation is obtained. Then, it is applied to the matching coordinates of all key spatial anchor points to obtain their final mapped positions in the local coordinate system based on the pipe centerline, resulting in the spatial mapping lookup table for the circumferential weld. The mapping formula is as follows:

[0142]

[0143] Optionally, the system's core control agent may call a preset mapping optimization agent to calculate the overall residual of the mapping. If the overall residual of the mapping has significant local clustering errors, it will query the knowledge base again through RAG to find targeted optimization strategies.

[0144] Optionally, the pipeline defect-internal and external intelligent agents perform spatial alignment between pipeline pile points and defect matching pairs to determine a defect spatial mapping lookup table. The specific process is as follows: For each pipeline pile point, the pipeline defect-internal and external intelligent agents normalize the standardized pipeline pile number corresponding to the pipeline pile point, and perform fuzzy matching recognition of the pipeline pile point by calling the visual intelligent agent. The pipeline pile number is bound to the pipeline pile point, and the geodetic coordinates of the pipeline pile point in the geodetic coordinate system are extracted. Based on the coordinate transformation service, the geodetic coordinates are transformed to a local coordinate system with the pipeline centerline as the reference to obtain the matching coordinates of the pipeline pile point. The key spatial anchor points adjacent to the pipeline pile point are identified, and the matching coordinates of the pipeline pile point are transformed based on the optimal correction transformation of the key spatial anchor points to obtain the final mapping position of the pipeline pile point. The final mapping position of the pipeline pile point is then aligned one by one with the actual position of each aligned pipeline defect in the defect matching pair list to obtain the defect spatial mapping lookup table.

[0145] Specifically, a visual intelligent agent is used to identify and extract key spatial anchor points and pipe pile points from the external data of the pipeline; an intelligent agent for the inside and outside of the circumferential weld is used to align the key spatial anchor points and the circumferential weld matching pair list to determine the spatial mapping lookup table for the circumferential weld; an intelligent agent for the inside and outside of the pipeline defects is used to align the pipe pile points and the defect matching pair list to determine the spatial mapping lookup table for the defects; and a digital twin of all elements inside and outside the pipeline is determined based on the spatial mapping lookup table for the circumferential weld and the spatial mapping lookup table for the defects.

[0146] Optionally, in this invention, a multi-agent collaborative processing mechanism is also introduced among the various intelligent agents, and the decision-making model of the system's core control agent for each intelligent agent is constructed based on a reinforcement learning framework.

[0147] Optionally, in this invention, after completing the data-level alignment and matching, the method further achieves a deep correlation between microscopic pipeline features and macroscopic environmental factors. This stage focuses on addressing the semantic gap between data at different scales, establishing a comprehensive analytical framework from local pipeline damage to global environmental risk. The fusion process is achieved by establishing a cross-scale correlation model, which can simultaneously process microscopic defect data inside the pipeline and external environmental monitoring data. The final output is the pipeline's overall risk distribution and its evolution trend. While considering the spatial characteristics of the data, the model also incorporates temporal dimension analysis, enabling it to capture the dynamic changes in pipeline status over time.

[0148] The technical solution of this invention initializes the pipeline quality and energy network parameters and loads the multi-source heterogeneous original internal inspection data of the pipeline quality and energy network; it calls a standardized data parsing interface to parse and standardize the original internal inspection data to determine the pipeline internal state benchmark model; it loads the external inspection data of the pipeline quality and energy network and aligns the external inspection data with the pipeline internal state benchmark model to determine a digital twin of all elements inside and outside the pipeline. This invention can achieve full-process automation and intelligence, has adaptability and strong scalability, and correlates internal inspection micro-defects with external macro-environmental data under a unified spatiotemporal benchmark, effectively improving the efficiency of pipeline risk assessment and the automation, accuracy and intelligence of pipeline integrity management.

[0149] Figure 4 This is a schematic diagram of a multi-source data alignment and fusion device for mass-energy equivalence networks based on intelligent agents, provided as an embodiment of the present invention. Figure 4 As shown, the device includes: a data module 410, an internal detection and alignment module 420, and an internal and external detection and alignment module 430; wherein,

[0150] Data module 410 is used to initialize the pipeline network parameters of the pipeline quality and energy network and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network.

[0151] The internal detection alignment module 420 is used to call the standardized data parsing interface to parse and standardize the original internal detection data and determine the pipeline internal state benchmark model.

[0152] The internal and external detection alignment module 430 loads the external detection data of the pipeline quality and energy network, aligns the external detection data with the internal state benchmark model of the pipeline, and determines the digital twin of all elements inside and outside the pipeline.

[0153] The technical solution of this invention initializes the pipeline quality and energy network parameters and loads the multi-source heterogeneous original internal inspection data of the pipeline quality and energy network; it calls a standardized data parsing interface to parse and standardize the original internal inspection data to determine the pipeline internal state benchmark model; it loads the external inspection data of the pipeline quality and energy network and aligns the external inspection data with the pipeline internal state benchmark model to determine a digital twin of all elements inside and outside the pipeline. This invention can achieve full-process automation and intelligence, has adaptability and strong scalability, and correlates internal inspection micro-defects with external macro-environmental data under a unified spatiotemporal benchmark, effectively improving the efficiency of pipeline risk assessment and the automation, accuracy and intelligence of pipeline integrity management.

[0154] Optionally, the internal detection alignment module 420 is specifically used for:

[0155] Based on the data processing intelligent agent calling the standardized data parsing interface, the original internal detection data is parsed and standardized to determine the standardized dataset;

[0156] Based on the data processing intelligent agent, key quality indicators are calculated for the standardized dataset, and the pipeline dataset corresponding to the pipeline quality and energy network is extracted.

[0157] Load the comparative dataset of the pipeline quality and energy network, align at least one circumferential weld and pipeline defect in the pipeline dataset based on the comparative dataset, and construct the pipeline internal state benchmark model.

[0158] Optionally, the internal detection alignment module 420 is also specifically used for:

[0159] Based on the circumferential weld alignment agent, the circumferential weld and the comparison dataset are aligned to construct a list of circumferential weld matching pairs.

[0160] Based on the pipeline defect alignment agent, the defect features of the pipeline defect and the comparison dataset are aligned to construct a list of defect matching pairs.

[0161] The internal state benchmark model of the pipeline is constructed based on the circumferential weld matching pair list and the defect matching pair list.

[0162] Optionally, the internal detection alignment module 420 is also specifically used for:

[0163] The circumferential weld alignment agent constructs a circumferential weld feature description vector for each circumferential weld.

[0164] For each of the circumferential weld feature description vectors, the circumferential weld feature description vectors are aligned with the comparison dataset by the circumferential weld alignment agent to construct the circumferential weld matching pair list.

[0165] Optionally, the internal detection alignment module 420 is also specifically used for:

[0166] The pipeline defect alignment agent divides the pipeline mass-energy network into multiple continuous pipeline segments based on the circumferential weld matching pair list.

[0167] The average mileage deviation is determined by calculating the average mileage deviation of multiple continuous pipeline segments using the pipeline defect alignment agent.

[0168] If the alignment success rate and the average mileage deviation meet the preset accuracy requirements, the pipeline defect alignment agent constructs a defect feature description vector for each pipeline defect in the pipeline dataset.

[0169] For each continuous pipeline segment, the pipeline defect alignment agent performs defect feature alignment based on the defect feature description vector and the comparison dataset to construct the defect matching pair list.

[0170] Optionally, the internal and external detection alignment module 430 is specifically used for:

[0171] The external detection data is standardized based on the data processing intelligent agent to determine the external data of the pipeline.

[0172] The external data of the pipeline and the internal state benchmark model of the pipeline are aligned internally and externally to determine a digital twin of all elements inside and outside the pipeline.

[0173] Optionally, the internal and external detection alignment module 430 is also specifically used for:

[0174] The visual intelligent agent is used to identify and extract key spatial anchor points and pipeline pile points from the external data of the pipeline.

[0175] By using intelligent agents inside and outside the circumferential weld pipe to align the key spatial anchor points and the circumferential weld matching list with the space inside and outside the pipe, the circumferential weld space mapping lookup table is determined.

[0176] By using intelligent agents inside and outside the pipeline defects to align the pipeline pile points and the defect matching list in the pipeline space, a defect space mapping lookup table is determined.

[0177] The digital twin of all elements inside and outside the pipeline is determined based on the circumferential weld space mapping lookup table and the defect space mapping lookup table.

[0178] The agent-based mass-energy network multi-source data alignment and fusion device provided in this embodiment of the invention can execute the agent-based mass-energy network multi-source data alignment and fusion method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0179] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their patterns are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0180] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0181] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer grids such as the Internet and / or various telecommunications grids.

[0182] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the agent-based mass-energy equivalence network multi-source data alignment and fusion method.

[0183] In some embodiments, the agent-based mass-energy equivalence (MEG) multi-source data alignment and fusion method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the agent-based MEG multi-source data alignment and fusion method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the agent-based MEG multi-source data alignment and fusion method by any other suitable means (e.g., by means of firmware).

[0184] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0185] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the patterns / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0186] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0187] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0188] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or grid browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain grids, and the Internet.

[0189] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS servers, such as high management difficulty and weak business scalability.

[0190] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0191] This embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the steps of the agent-based mass-energy equivalence network multi-source data alignment and fusion method provided in any embodiment of the present invention. The method includes:

[0192] Initialize the pipeline network parameters of the pipeline quality and energy network, and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network;

[0193] The raw internal detection data is parsed and standardized by calling the standardized data parsing interface to determine the pipeline internal state benchmark model.

[0194] Load the external inspection data of the pipeline quality and energy network, align the external inspection data with the internal state benchmark model of the pipeline, and determine the digital twin of all elements inside and outside the pipeline.

[0195] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0196] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0197] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0198] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of mesh, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0199] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a grid of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0200] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0201] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for aligning and fusing multi-source data in a mass-energy equivalence network based on intelligent agents, characterized in that, include: Initialize the pipeline network parameters of the pipeline quality and energy network, and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network; The raw internal detection data is parsed and standardized by calling the standardized data parsing interface to determine the pipeline internal state benchmark model. Load the external inspection data of the pipeline quality and energy network, align the external inspection data with the internal state benchmark model of the pipeline, and determine the digital twin of all elements inside and outside the pipeline.

2. The method according to claim 1, characterized in that, The process of calling the standardized data parsing interface to parse and standardize the original internal detection data to determine the pipeline internal state baseline model includes: Based on the data processing intelligent agent calling the standardized data parsing interface, the original internal detection data is parsed and standardized to determine the standardized dataset; Based on the data processing intelligent agent, key quality indicators are calculated for the standardized dataset, and the pipeline dataset corresponding to the pipeline quality and energy network is extracted. Load the comparative dataset of the pipeline quality and energy network, align at least one circumferential weld and pipeline defect in the pipeline dataset based on the comparative dataset, and construct the pipeline internal state benchmark model.

3. The method according to claim 2, characterized in that, The step of aligning at least one circumferential weld and pipe defect in the pipe dataset based on the comparison dataset to construct a benchmark model of the pipe's internal state includes: Based on the circumferential weld alignment agent, the circumferential weld and the comparison dataset are aligned to construct a list of circumferential weld matching pairs. Based on the pipeline defect alignment agent, the defect features of the pipeline defect and the comparison dataset are aligned to construct a list of defect matching pairs. The internal state benchmark model of the pipeline is constructed based on the circumferential weld matching pair list and the defect matching pair list.

4. The method according to claim 3, characterized in that, Based on the circumferential weld alignment agent, the circumferential weld and the comparison dataset are aligned to construct a list of circumferential weld matching pairs, including: The circumferential weld alignment agent constructs a circumferential weld feature description vector for each circumferential weld. For each of the circumferential weld feature description vectors, the circumferential weld feature description vectors are aligned with the comparison dataset by the circumferential weld alignment agent to construct the circumferential weld matching pair list.

5. The method according to claim 3, characterized in that, The pipeline defect alignment agent aligns the defect features of the pipeline defect and the comparison dataset to construct a list of defect matching pairs, including: The pipeline defect alignment agent divides the pipeline mass-energy network into multiple continuous pipeline segments based on the circumferential weld matching pair list. The average mileage deviation is determined by calculating the average mileage deviation of multiple continuous pipeline segments using the pipeline defect alignment agent. If the alignment success rate and the average mileage deviation meet the preset accuracy requirements, the pipeline defect alignment agent constructs a defect feature description vector for each pipeline defect in the pipeline dataset. For each continuous pipeline segment, the pipeline defect alignment agent performs defect feature alignment based on the defect feature description vector and the comparison dataset to construct the defect matching pair list.

6. The method according to claim 1, characterized in that, The step of aligning the external detection data and the internal state benchmark model of the pipeline to determine a digital twin of all elements inside and outside the pipeline includes: The external detection data is standardized based on the data processing intelligent agent to determine the external data of the pipeline. The external data of the pipeline and the internal state benchmark model of the pipeline are aligned internally and externally to determine a digital twin of all elements inside and outside the pipeline.

7. The method according to claim 6, characterized in that, The process of aligning the external data of the pipeline with the internal state baseline model of the pipeline to determine a digital twin of all elements inside and outside the pipeline includes: The visual intelligent agent is used to identify and extract key spatial anchor points and pipeline pile points from the external data of the pipeline. By using intelligent agents inside and outside the circumferential weld pipe to align the key spatial anchor points and the circumferential weld matching list with the space inside and outside the pipe, the circumferential weld space mapping lookup table is determined. By using intelligent agents inside and outside the pipeline defects to align the pipeline pile points and defect matching list with the pipeline space inside and outside the pipeline, a defect space mapping lookup table is determined. The digital twin of all elements inside and outside the pipeline is determined based on the circumferential weld space mapping lookup table and the defect space mapping lookup table.

8. A multi-source data alignment and fusion device for mass-energy equivalence networks based on intelligent agents, characterized in that, include: The data module is used to initialize the pipeline network parameters of the pipeline quality and energy network and load the original internal detection data of the multi-source heterogeneous pipeline quality and energy network. The internal detection alignment module is used to call the standardized data parsing interface to parse and standardize the original internal detection data and determine the pipeline internal state benchmark model. The internal and external detection alignment module loads the external detection data of the pipeline quality and energy network, aligns the external detection data with the internal state benchmark model of the pipeline, and determines the digital twin of all elements inside and outside the pipeline.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the agent-based mass-energy equivalence network multi-source data alignment and fusion method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the agent-based mass-energy equivalence network multi-source data alignment and fusion method as described in any one of claims 1-7.

Images