A mechanism-data fusion driven gas field station abnormal early warning and root cause tracing method and system, medium

Abstract

The application provides a mechanism-data fusion driven gas station abnormality early warning and root cause tracing method and system, through collaborative application of a mechanism model and a data driven model, based on a gas station twin digital model in a gas station abnormality early warning scene, an early warning ring network including each possible abnormal node and a data flow relationship thereof is established, a targeted associated node early warning collaborative data chain is set in the early warning network, an early warning information data structure is iteratively configured by the mechanism model abnormality early warning, a root cause tracing of the early warning associated node is performed by the gas data fusion model, while discovering an abnormality and alarming an abnormality, an abnormal root cause is found and discovered through a flow logic of an associated relationship of abnormal data, an alarm and information display of a system management end are triggered by a gas fusion early warning information mode, early warning linkage efficiency and early warning accuracy are improved in a systematic way, and a solid foundation is provided for timely discovery, timely processing and hidden danger elimination of early warning.

Description

Technical Field

[0001] This invention belongs to the field of new-generation information technology, and specifically relates to a computer task scheduling control and regulation system (G05B) and an electrical digital data processing system (G06F) for computer task processing information systems. In particular, it relates to a mechanism-data fusion driven method, system and medium for early warning and root cause tracing of gas station anomalies. Background Technology

[0002] The application of information systems in economic and social development is increasingly trending towards digitalization and virtualization. Data collection based on mechanistic models, combined with comprehensive data processing based on large data models, provides new directions and new impetus for areas such as site safety management and data control.

[0003] Mechanism-data fusion technology is a computational paradigm that combines the inherent laws of physical systems with statistical patterns of observational data. It aims to compensate for the lack of interpretability in purely data-driven methods and the insufficient accuracy of purely mechanistic modeling. Its core architecture comprises two complementary information flows: the mechanistic flow, based on first principles such as mass conservation, energy conservation, and momentum conservation, establishes a system of differential-algebraic equations to describe the causal constraints between system variables, such as the Navier-Stokes simplified form of pipe flow, the Arrhenius kinetics of chemical reactions, and the fundamental laws of heat transfer for heat exchange; and the data flow, which collects time-series records of operational status through sensor networks and utilizes machine learning to extract high-dimensional nonlinear correlations and residual patterns. The fusion layer can be designed with various strategies. At the loss function level, the residuals of the mechanistic equations can be used as regularization terms to penalize predictions that are physically inconsistent. At the network architecture level, differential operator layers can replace some fully connected layers to achieve hard constraint embedding. Alternatively, a residual learning framework can be used to allow the neural network to specifically fit the bias terms that are difficult for mechanistic models to characterize. The parameter estimation stage utilizes data to calibrate uncertainties in the mechanistic model, such as the friction factor and heat transfer coefficient. Simultaneously, mechanistic constraints guide data imputation and anomaly detection, preventing erroneous learning of spurious correlations that violate physics. The solution algorithm needs to handle the coupling between differential equation discretization and gradient backpropagation, often employing an automatic differentiation framework to achieve end-to-end optimization.

[0004] In engineering implementation, this technology faces challenges such as multi-scale coupling, computational complexity, and verification difficulties. The multi-scale problem stems from the fact that mechanistic models are typically established under the assumption of a continuous medium, while data sampling has discrete spatiotemporal granularity, requiring alignment with the neural network input dimension after discretization using finite volume or spectral methods. Some solutions employ physically-informed neural networks, directly using spatiotemporal coordinates as network input, with output field variables automatically satisfying partial differential equation constraints, avoiding explicit mesh generation. Regarding computational complexity, high-fidelity mechanistic simulations can take several hours for a single solution, contradicting the requirements of real-time data stream processing. Reduced-order or alternative models are commonly used for acceleration, with neural networks approximating the mapping from parameterized inputs to key outputs, maintaining the core characteristics of the mechanism while compressing inference to the second level. The verification phase requires dual testing: comparing with a pure mechanistic model to verify whether data fusion introduces non-physical oscillations, and comparing with a pure data model to verify the stability of extrapolation to unseen operating conditions. Simultaneously, sensitivity analysis is used to identify the mechanistic parameters and data features that contribute most to the prediction variance, guiding subsequent measurement resource allocation. This technology has been applied in fields such as energy systems, aerospace, and environmental science to address strongly nonlinear, partially observed, and multi-physics coupled problems that are difficult to solve using traditional single methods.

[0005] In the field of gas station anomaly management, mechanism-data fusion technology has been first used to construct high-precision digital process images. Gas stations contain multiple functional units such as filtration, metering, pressure regulation, and odorization. Traditional steady-state calculations based on the ideal gas law and empirical coefficients struggle to capture transient conditions such as compressor start-up / shutdown and pressure wave propagation caused by rapid valve closure. The fusion scheme uses a one-dimensional compressible flow equation as its backbone to describe the conservation of mass and momentum in the pipeline. Simultaneously, a neural network is introduced at key boundaries, such as the regulator valve core, to replace complex flow characteristic curves. This network takes valve opening, upstream and downstream pressure difference, and fluid Reynolds number as inputs and outputs an equivalent flow coefficient. It is trained using historical operating data to closely reflect the wear and viscosity characteristics of actual equipment. For internal states that are difficult to measure directly, such as the degree of filter element blockage, a hidden state estimator is trained using differential pressure sensor readings and the residual sequence of the mechanism model. This compresses high-dimensional observations into low-dimensional health indicators, enabling continuous tracking of blockage levels rather than relying solely on discrete judgments from periodic disassembly and inspection.

[0006] At the early warning level, this technology supports the evolution from threshold alarms to trend prediction. Purely data-driven anomaly detection often generates false alarms due to operating condition drift, while pure mechanistic models are poorly adaptable to equipment aging and process changes. The fusion system generates expected variable trajectories under normal operating conditions using mechanistic models, calculates the time series of deviations between measured values ​​and expectations, and then uses these residuals to train change point detection or prediction models to identify gradual degradation or sudden failures that deviate from mechanistic constraints. For example, if the pressure fluctuation at the regulator outlet conforms to the mechanistic transfer function with the upstream flow change, it is judged as a normal disturbance; if the residual exhibits specific spectral characteristics and is abnormally coupled with the valve core stroke feedback, an early warning of positioner failure or valve orifice erosion is issued. The early warning threshold is no longer fixed but dynamically adjusted based on real-time estimation of the residual distribution to adapt to seasonal load changes and baseline migration after equipment maintenance. The system output includes the anomaly type, confidence level, expected time window for development to functional failure, and recommended intervention measures such as switching to backup circuits, reducing load, or scheduling maintenance for dispatchers' decision-making reference.

[0007] Over long-term operation, this technology has developed a closed-loop optimization capability encompassing "perception-diagnosis-decision-execution." The diagnosis stage combines fault propagation path analysis from the mechanistic model with pattern recognition from the data model to pinpoint the root cause level of anomalies, distinguishing between sensor drift, actuator failure, and process disturbances, thus avoiding the accidental removal of healthy equipment. The decision-making stage utilizes reinforcement learning to train a policy network in a simplified simulation environment with mechanistic constraints, learning the optimal control sequence under different anomaly scenarios, such as the load redistribution algorithm for a multi-channel pressure regulation system, minimizing the number of switching operations and pressure fluctuations while ensuring downstream pressure compliance. The execution stage uses digital twins to pre-simulate the short-term consequences of control commands, verifying that they will not trigger new mechanistic constraint violations such as overpressure or negative pressure before issuing commands to the PLC for execution, forming a semi-autonomous human-in-the-loop control mode. A continuous learning mechanism periodically feeds back newly occurring anomaly cases and their handling effects to the model update process, ensuring that mechanistic parameters and data models evolve synchronously, adapting to equipment iteration and operational boundary expansion, and maintaining prediction and management accuracy throughout the entire lifecycle.

[0008] During their research into the relevant technologies, the applicant discovered that existing gas station management processes lack a holistic consideration of the information chain transmission and information loop construction for data early warning, meaning there is a lack of coordinated early warning information during the management process. Furthermore, the iteration of early warning information suffers from a deficiency in merely adhering to system upgrade logic, failing to consider the degree of data fusion during root cause analysis.

[0009] This invention proposes a mechanism-data fusion-driven method and system for early warning and root cause tracing of gas station anomalies. Through the synergistic application of a mechanism model and a data-driven model, an early warning ring network is established based on a twin digital model of the gas station in an anomaly early warning scenario. This network includes various possible anomaly nodes and their data flow relationships. Targeted collaborative data chains for related nodes are set up within the early warning network. The mechanism model iteratively configures the early warning information data structure. A gas data fusion model is used to perform root cause tracing of related nodes. While detecting and alarming anomalies, the root cause of the anomaly is found through the flow logic of the abnormal data relationships. The gas fusion early warning information mode triggers alarms and information displays on the system management end. This systematic approach improves the efficiency and accuracy of early warning linkage, providing a solid foundation for timely detection, timely handling, and hazard investigation. Summary of the Invention

[0010] The present invention aims to provide a gas station anomaly early warning and root cause tracing system based on mechanism-data fusion, which is superior to the prior art.

[0011] To achieve the above objectives, the technical solution of the present invention is as follows: A mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system, the system comprising at least a gas station early warning targeting loop, a first gas fusion-driven data chain, a second gas fusion-driven data chain, a gas mechanism model anomaly early warning iteration module, and a gas data fusion model root cause tracing overlay module, wherein: The gas station early warning target loop is based on the twin digital model of the gas station. It establishes an early warning loop for the gas station based on the data flow node relationship of the gas station, and simultaneously establishes the target early warning relationship between each node of the early warning loop. The first gas fusion driving data chain establishes a gas fusion early warning driving data chain for nodes with targeted early warning relationships. The gas fusion early warning driving data chain obtains the early warning relationship node information data structure sent by the gas mechanism model abnormal early warning iteration module, which is associated with node one and node two with targeted early warning relationships. Based on the root cause tracing nodes output by the gas data fusion model root cause tracing overlay module, the first gas fusion early warning information is generated. The second gas fusion-driven data chain stores abnormal alarm information related to node P in the data chain. Based on the processing results of the root cause tracing overlay module of the gas data fusion model, it generates and stores the root cause tracing record and root cause tracing node of node P for the stored abnormal alarm information related to node P. The gas mechanism model anomaly early warning iteration module obtains the real-time operating parameters of each node in the twin digital model of the gas station, configures the data structure of the early warning relationship node information, and transmits it to the first gas fusion driving data chain; When an abnormal alarm occurs at node P, the root cause tracing overlay module of the gas data fusion model registers the abnormality in the second gas fusion driving data chain and assigns an abnormality ID. It records the real-time operating parameters of node Ci that has a targeted early warning relationship with the abnormal node P of the gas station, records the ID of node Ci whose parameters are outside the safe range, and stores the abnormality ID, node P, and node Ci's ID as a root cause tracing record in the second gas fusion driving data chain. Periodically, based on the second gas fusion driving data chain, the root cause tracing records of node P are fused, and the IDs of nodes Ci that appear in multiple historical root cause tracing records of node P with a proportion below the third threshold are deleted. The IDs of the remaining nodes Ci are recorded as the root cause tracing nodes of node P and stored in the second gas fusion driving data chain. Wherein, node Ci can be one or more, the safety range is the range of normal operating parameters for each node preset by the system, and the third threshold is a percentage preset by the system; At the system output end, based on the first gas fusion early warning information and the twin digital model of the gas station, the system output end displays the early warning status of each node of the gas station to the gas station administrator control center and control screen.

[0012] Preferably, the targeted early warning relationship includes at least a bidirectional one-to-one mapping relationship, used to characterize two nodes whose associated faults of abnormal nodes in a gas station are greater than a preset second threshold.

[0013] Preferably, the second threshold is a percentage preset by the system.

[0014] Preferably, the gas mechanism model anomaly early warning iteration module acquires the real-time operating parameters of each node in the gas station twin digital model, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain, specifically: The gas mechanism model anomaly early warning iteration module dynamically obtains the real-time operating parameters of each node from the twin digital model of the gas station. It constructs and configures an early warning relationship node information data structure containing multiple information fields, using the node ID combination of all nodes K and J with targeted early warning relationships as the class name, and transmits it to the first gas fusion driving data chain. in, The plurality of information fields include at least: The node pair parameter confirmation information includes at least the logical location information pair of nodes K and J with a targeted early warning relationship in the twin digital model of the gas station, which is used to confirm the node information data structure of the early warning relationship by each node during transmission. The node ID combination corresponds to the node ID combination of nodes K and J with a targeted early warning relationship. The two-dimensional information field of gas data flow between nodes represents the relevant parameter information of gas transmission from node K to node J as time changes; The system transmission control signaling flow field between nodes represents the signaling information issued by the system user for setting the data transmission from node K to node J and from node J to node K.

[0015] Preferably, the logical location information pair of nodes K and J with the targeted early warning relationship in the twin digital model of the gas station includes at least: The first information segment is the logical location information of node K in the digital twin model of the gas station. The logical location information of node K in the digital twin model of the gas station is equal to the physical location information of node K or is a mapping information of the physical location information. The second information segment is the logical location information of node J in the twin digital model of the gas station. The logical location information of node J in the twin digital model of the gas station is equal to the physical location information of node J or is a mapping information of the physical location information.

[0016] The first gas fusion-driven data chain establishes a gas fusion early warning-driven data chain for nodes with targeted early warning relationships, and includes at least: The first gas fusion driving data chain establishes a gas fusion early warning driving data chain for nodes with targeted early warning relationships. The gas fusion early warning driving data chain obtains the early warning relationship node information data structure sent by the gas mechanism model abnormal early warning iteration module, which is associated with nodes with targeted early warning relationships. Based on the root cause tracing nodes output by the gas data fusion model root cause tracing overlay module, the first gas fusion early warning information is generated.

[0017] Preferably, the second gas fusion drive data chain, which stores abnormal alarm information related to node P and generates root cause tracing records and root cause tracing nodes for node P, includes at least: The second gas fusion-driven data chain stores abnormal alarm information related to node P in the data chain. Based on the processing results of the root cause tracing overlay module of the gas data fusion model, it generates and stores the root cause tracing record and root cause tracing node of node P for the stored abnormal alarm information of node P.

[0018] Preferably, the gas mechanism model anomaly early warning iteration module obtains the real-time operating parameters of each node in the twin digital model of the gas station, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain; When an abnormal alarm occurs at node P, the root cause tracing overlay module of the gas data fusion model registers the abnormality in the second gas fusion driving data chain and assigns an abnormality ID. It records the real-time operating parameters of node Ci that has a targeted early warning relationship with the abnormal node P of the gas station, records the ID of node Ci whose parameters are outside the safe range, and stores the abnormality ID, node P, and node Ci's ID as a root cause tracing record in the second gas fusion driving data chain. Periodically, based on the second gas fusion driving data chain, the root cause tracing records of node P are fused, and the IDs of nodes Ci that appear in multiple historical root cause tracing records of node P with a proportion below the third threshold are deleted. The IDs of the remaining nodes Ci are recorded as the root cause tracing nodes of node P and stored in the second gas fusion driving data chain. Wherein, node Ci can be one or more, the safety range is the normal operating parameter range of each node preset by the system, and the third threshold is a percentage preset by the system.

[0019] Preferably, the targeted early warning relationship includes at least a bidirectional one-to-one mapping relationship, used to characterize two nodes whose associated faults of abnormal nodes in a gas station are greater than a preset second threshold. The second threshold is a percentage preset by the system.

[0020] Preferably, the gas mechanism model anomaly early warning iteration module acquires the real-time operating parameters of each node in the gas station twin digital model, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain, specifically: The gas mechanism model anomaly early warning iteration module dynamically obtains the real-time operating parameters of each node from the twin digital model of the gas station. It constructs and configures an early warning relationship node information data structure containing multiple information fields, using the node ID combination of all nodes K and J with targeted early warning relationships as the class name, and transmits it to the first gas fusion driving data chain. in, The plurality of information fields include at least: The node pair parameter confirmation information includes at least the logical location information pair of nodes K and J with a targeted early warning relationship in the twin digital model of the gas station, which is used to confirm the node information data structure of the early warning relationship by each node during transmission. The node ID combination corresponds to the node ID combination of nodes K and J with a targeted early warning relationship. The two-dimensional information field of gas data flow between nodes represents the relevant parameter information of gas transmission from node K to node J as time changes; The system transmission control signaling flow field between nodes represents the signaling information issued by the system user for setting the data transmission from node K to node J and from node J to node K.

[0021] Preferably, the logical location information pair of nodes K and J with the targeted early warning relationship in the twin digital model of the gas station includes at least: The first information segment is the logical location information of node K in the digital twin model of the gas station. The logical location information of node K in the digital twin model of the gas station is equal to the physical location information of node K or is a mapping information of the physical location information. The second information segment is the logical location information of node J in the twin digital model of the gas station. The logical location information of node J in the twin digital model of the gas station is equal to the physical location information of node J or is a mapping information of the physical location information.

[0022] Simultaneously, this invention also proposes a root cause tracing method for a gas station anomaly early warning and root cause tracing system based on mechanism-data fusion as described in any of the above: Step 1: Based on the twin digital model of the gas station, establish an early warning loop for the gas station based on the data flow node relationship of the gas station, and simultaneously establish targeted early warning relationships between each node of the early warning loop; Step 2: First gas fusion driven data chain, establish gas fusion early warning driven data chain for nodes with targeted early warning relationship; Step 3: Use the second gas fusion drive data chain to store the abnormal alarm information of node P and generate the root cause tracing record and root cause tracing node of node P; Step 4: The gas mechanism model anomaly early warning iteration module acquires real-time operating parameters and configures the data structure of early warning relationship nodes; Step 5: The root cause tracing overlay module of the gas data fusion model performs root cause tracing record and root cause tracing record fusion when node P alarms abnormally.

[0023] Simultaneously, the present invention also proposes a computer-readable storage medium storing a program for electronic data processing, wherein the program causes a terminal to perform the corresponding functions of the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system as described in any of the preceding claims.

[0024] At the same time, the present invention also proposes a computer program product, which includes computer instructions, which execute the corresponding functions of the mechanism-data fusion driven gas station anomaly early warning and root cause tracing system as described above when the processor runs.

[0025] This invention proposes a mechanism-data fusion-driven method and system for early warning and root cause tracing of gas station anomalies. Through the synergistic application of a mechanism model and a data-driven model, an early warning ring network is established based on a twin digital model of the gas station in an anomaly early warning scenario. This network includes various possible anomaly nodes and their data flow relationships. Targeted collaborative data chains for related nodes are set up within the early warning network. The mechanism model iteratively configures the early warning information data structure. A gas data fusion model is used to perform root cause tracing of related nodes. While detecting and alarming anomalies, the root cause of the anomaly is found through the flow logic of the abnormal data relationships. The gas fusion early warning information mode triggers alarms and information displays on the system management end. This systematic approach improves the efficiency and accuracy of early warning linkage, providing a solid foundation for timely detection, timely handling, and hazard investigation. Attached Figure Description

[0026] Figure 1 This is a basic example diagram of the gas station early warning target loop of the mechanism-data fusion driven gas station anomaly early warning and root cause tracing system shown in this invention; Figure 2 This is a basic example diagram illustrating the interconnection relationship between the first gas fusion-driven data chain and various related modules in the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system shown in this invention. Figure 3 This is an example diagram of the second gas fusion-driven data chain and its function in the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system claimed in this invention; Figure 4 This is one of the embodiments of the interconnection between the gas mechanism model anomaly early warning iteration module, the gas data fusion model root cause tracing overlay module, and related modules in the mechanism-data fusion driven gas station anomaly early warning and root cause tracing system claimed in this invention; Figure 5 This is one of the specific embodiments of the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing method claimed in this invention. Detailed Implementation

[0027] The following describes in detail several embodiments and beneficial effects of the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system and method claimed in this invention, in order to facilitate a more detailed examination and breakdown of this invention.

[0028] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0029] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0030] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0031] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0032] It should be understood that although the terms "first," "second," etc., may be used to describe the methods and corresponding apparatus in the embodiments of the present invention, these keywords should not be limited to these terms. These terms are only used to distinguish the keywords from each other. For example, without departing from the scope of the embodiments of the present invention, "first gas fusion drive data chain," "first threshold," etc., may also be referred to as "second gas fusion drive data chain," "second threshold," etc., and "second gas fusion drive data chain," "second threshold," etc., may also be referred to as "first gas fusion drive data chain," "first threshold."

[0033] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0034] As per the instruction manual Figure 1 - Appendix Figure 4 The diagram shown is a basic example of a mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system according to the present invention. As a preferred embodiment that can be superimposed, each node or module can preferably interconnect with other nodes or modules for data and command transmission. Of course, as another preferred embodiment that can be superimposed, some nodes may not have interconnection with some other nodes, or may be allowed to disable or enable interconnection with other nodes.

[0035] The gas station anomaly early warning and root cause tracing system based on mechanism-data fusion driven by the present invention, as claimed in this invention, includes at least a gas station early warning targeting loop, a first gas fusion driven data chain, a second gas fusion driven data chain, a gas mechanism model anomaly early warning iteration module, and a gas data fusion model root cause tracing overlay module, wherein: The gas station early warning target loop is based on the twin digital model of the gas station. It establishes an early warning loop for the gas station based on the data flow node relationship of the gas station, and simultaneously establishes the target early warning relationship between each node of the early warning loop. To further differentiate itself from existing technologies, as a preferred embodiment that can be superimposed, the gas station early warning targeting ring is based on a gas station twin digital model. It establishes an early warning ring based on the data flow node relationships of the gas station, and simultaneously establishes targeted early warning relationships between various nodes in the early warning ring. Specifically, the system establishes a twin digital model for the gas station, uploads each data flow node of the gas station to the twin digital model, and, based on the accessibility of system management information and data flow relationships (for example, node K can receive system signaling and system control data, and after local processing, such as adding functional control data or system data update instructions for the next or subsequent nodes), sends the data to the next downstream node J according to the system's preset node data transmission flow settings. Nodes K and J are identified in the gas station twin digital model, and these nodes exist on the gas station early warning targeting ring according to the data flow order. As another preferred embodiment that can be superimposed, the simultaneous establishment of targeted early warning relationships between various nodes in the early warning ring includes at least a bidirectional one-to-one mapping relationship, used to characterize two nodes whose associated faults of abnormal gas station nodes exceed a preset second threshold. That is, based on the system's historical data, if the probability of two nodes K and J synchronizing their faults is greater than a certain number or a certain value, then they are determined to be two nodes whose associated faults in the gas station are greater than a preset second threshold, and a targeted early warning relationship between the above nodes is established in the early warning loop.

[0036] Figure 2 This is a basic example diagram illustrating the interconnection relationship between the first gas fusion-driven data chain and various related modules in the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system shown in this invention.

[0037] The first gas fusion driving data chain establishes a gas fusion early warning driving data chain for nodes with targeted early warning relationships. The gas fusion early warning driving data chain obtains the early warning relationship node information data structure sent by the gas mechanism model abnormal early warning iteration module, which is associated with node one and node two with targeted early warning relationships. Based on the root cause tracing nodes output by the gas data fusion model root cause tracing overlay module, the first gas fusion early warning information is generated. To further differentiate itself from existing technologies, as a preferred, superimposed embodiment, the first gas fusion-driven data chain establishes a gas fusion early warning-driven data chain for nodes with targeted early warning relationships. This gas fusion early warning-driven data chain acquires the early warning relationship node information data structure sent by the gas mechanism model anomaly early warning iteration module, which is associated with nodes having targeted early warning relationships. Based on the root cause tracing nodes output by the gas data fusion model root cause tracing overlay module, it generates first gas fusion early warning information, including at least: the first gas fusion-driven data chain acquires the early warning relationship node information data structure sent by the gas mechanism model anomaly early warning iteration module, which is associated with nodes having targeted early warning relationships, and based on... The two-dimensional information field of gas data flow between nodes monitors in real time whether the relevant parameters representing the change of gas transmission from node K to node J over time reach the critical value of the normal parameter range threshold. When the critical value is reached, an early warning is initiated. Based on the system transmission control signaling flow field between nodes, it is determined whether there is an early warning exemption field or an early warning preprocessing field. If an early warning exemption field is found, the early warning is eliminated; if an early warning preprocessing field is found, preprocessing is performed according to the early warning preprocessing field instruction signaling. The early warning exemption field indicates that the early warning can be exempted from elimination; the early warning preprocessing field contains preprocessing information to indicate one of the system's preset preprocessing methods for the early warning. If no early warning exemption field or early warning preprocessing field is found, the root cause tracing node of node K or node J is searched, and the root cause tracing node early warning information of node K or node J is initiated simultaneously. A first gas fusion early warning information is generated, which includes the monitored dynamic curve of the two-dimensional information field of gas data flow between nodes and the corresponding node K, node J, and their root cause tracing node information, and is sent to the system output terminal.

[0038] Figure 3 This is an example diagram of the second gas fusion-driven data chain and its function in the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system for which the present invention is claimed.

[0039] The second gas fusion-driven data chain stores abnormal alarm information related to node P in the data chain. Based on the processing results of the root cause tracing overlay module of the gas data fusion model, it generates and stores the root cause tracing record and root cause tracing node of node P for the stored abnormal alarm information related to node P. Figure 4 This is one of the embodiments of the interconnection between the gas mechanism model anomaly early warning iteration module, the gas data fusion model root cause tracing overlay module, and related modules in the mechanism-data fusion driven gas station anomaly early warning and root cause tracing system claimed in this invention.

[0040] The gas mechanism model anomaly early warning iteration module obtains the real-time operating parameters of each node in the twin digital model of the gas station, configures the data structure of the early warning relationship node information, and transmits it to the first gas fusion driving data chain; When an abnormal alarm occurs at node P, the root cause tracing overlay module of the gas data fusion model registers the abnormality in the second gas fusion driving data chain and assigns an abnormality ID. It records the real-time operating parameters of node Ci that has a targeted early warning relationship with the abnormal node P of the gas station, records the ID of node Ci whose parameters are outside the safe range, and stores the abnormality ID, node P, and node Ci's ID as a root cause tracing record in the second gas fusion driving data chain. Periodically, based on the second gas fusion driving data chain, the root cause tracing records of node P are fused, and the IDs of nodes Ci that appear in multiple historical root cause tracing records of node P with a proportion below the third threshold are deleted. The IDs of the remaining nodes Ci are recorded as the root cause tracing nodes of node P and stored in the second gas fusion driving data chain. Wherein, node Ci can be one or more, the safety range is the range of normal operating parameters for each node preset by the system, and the third threshold is a percentage preset by the system; At the system output end, based on the first gas fusion early warning information and the twin digital model of the gas station, the system output end displays the early warning status of each node of the gas station to the gas station administrator control center and control screen.

[0041] As a preferred embodiment that can be superimposed, the targeted early warning relationship includes at least a bidirectional one-to-one mapping relationship, used to characterize two nodes whose associated faults of abnormal nodes in a gas station are greater than a preset second threshold.

[0042] As another preferred embodiment where the threshold can be superimposed, the second threshold is a percentage preset by the system.

[0043] As another preferred embodiment that can be superimposed, the gas mechanism model anomaly early warning iteration module acquires the real-time operating parameters of each node in the twin digital model of the gas station, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain, specifically: The gas mechanism model anomaly early warning iteration module dynamically obtains the real-time operating parameters of each node from the twin digital model of the gas station. It constructs and configures an early warning relationship node information data structure containing multiple information fields, using the node ID combination of all nodes K and J with targeted early warning relationships as the class name, and transmits it to the first gas fusion driving data chain. The plurality of information fields include at least: node pair parameter confirmation information, including at least a pair of logical location information of nodes K and J with targeted early warning relationship in the twin digital model of the gas station, used to confirm the node information data structure of the early warning relationship by each node during transmission, corresponding to the node ID combination of nodes K and J with targeted early warning relationship; The two-dimensional information field of gas data flow between nodes represents the relevant parameter information of gas transmission from node K to node J as time changes; The system transmission control signaling flow field between nodes represents the signaling information issued by the system user for setting the data transmission from node K to node J and from node J to node K.

[0044] As another preferred embodiment that can be superimposed, the logical location information pair of nodes K and J with the targeted early warning relationship in the twin digital model of the gas station includes at least: The first information segment is the logical location information of node K in the digital twin model of the gas station. The logical location information of node K in the digital twin model of the gas station is equal to the physical location information of node K or is a mapping information of the physical location information. The second information segment is the logical location information of node J in the twin digital model of the gas station. The logical location information of node J in the twin digital model of the gas station is equal to the physical location information of node J or is a mapping information of the physical location information.

[0045] The first gas fusion-driven data chain establishes a gas fusion early warning-driven data chain for nodes with targeted early warning relationships, and includes at least: The first gas fusion driving data chain establishes a gas fusion early warning driving data chain for nodes with targeted early warning relationships. The gas fusion early warning driving data chain obtains the early warning relationship node information data structure sent by the gas mechanism model abnormal early warning iteration module, which is associated with nodes with targeted early warning relationships. Based on the root cause tracing nodes output by the gas data fusion model root cause tracing overlay module, the first gas fusion early warning information is generated.

[0046] As another preferred embodiment that can be superimposed, the second gas fusion drive data chain, which stores abnormal alarm information related to node P and generates root cause tracing records and root cause tracing nodes for node P, includes at least: The second gas fusion-driven data chain stores abnormal alarm information related to node P in the data chain. Based on the processing results of the root cause tracing overlay module of the gas data fusion model, it generates and stores the root cause tracing record and root cause tracing node of node P for the stored abnormal alarm information of node P.

[0047] As another preferred embodiment that can be superimposed, the gas mechanism model anomaly early warning iteration module obtains the real-time operating parameters of each node in the twin digital model of the gas station, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain. When an abnormal alarm occurs at node P, the root cause tracing overlay module of the gas data fusion model registers the abnormality in the second gas fusion driving data chain and assigns an abnormality ID. It records the real-time operating parameters of node Ci that has a targeted early warning relationship with the abnormal node P of the gas station, records the ID of node Ci whose parameters are outside the safe range, and stores the abnormality ID, node P, and node Ci's ID as a root cause tracing record in the second gas fusion driving data chain. Periodically, based on the second gas fusion driving data chain, the root cause tracing records of node P are fused, and the IDs of nodes Ci that appear in multiple historical root cause tracing records of node P with a proportion below the third threshold are deleted. The IDs of the remaining nodes Ci are recorded as the root cause tracing nodes of node P and stored in the second gas fusion driving data chain. Wherein, node Ci can be one or more, the safety range is the normal operating parameter range of each node preset by the system, and the third threshold is a percentage preset by the system.

[0048] As another preferred embodiment that can be superimposed, the targeted early warning relationship includes at least a bidirectional one-to-one mapping relationship, used to characterize two nodes whose associated faults of abnormal nodes in a gas station are greater than a preset second threshold. The second threshold is a percentage preset by the system.

[0049] As another preferred embodiment that can be superimposed, the gas mechanism model anomaly early warning iteration module acquires the real-time operating parameters of each node in the twin digital model of the gas station, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain, specifically: The gas mechanism model anomaly early warning iteration module dynamically obtains the real-time operating parameters of each node from the twin digital model of the gas station. It constructs and configures an early warning relationship node information data structure containing multiple information fields, using the node ID combination of all nodes K and J with targeted early warning relationships as the class name, and transmits it to the first gas fusion driving data chain. in, The plurality of information fields include at least: The node pair parameter confirmation information includes at least the logical location information pair of nodes K and J with a targeted early warning relationship in the twin digital model of the gas station, which is used to confirm the node information data structure of the early warning relationship by each node during transmission. The node ID combination corresponds to the node ID combination of nodes K and J with a targeted early warning relationship. The two-dimensional information field of gas data flow between nodes represents the relevant parameter information of gas transmission from node K to node J as time changes; The system transmission control signaling flow field between nodes represents the signaling information issued by the system user for setting the data transmission from node K to node J and from node J to node K.

[0050] As another preferred embodiment that can be superimposed, the logical location information pair of nodes K and J with the targeted early warning relationship in the twin digital model of the gas station includes at least: The first information segment is the logical location information of node K in the digital twin model of the gas station. The logical location information of node K in the digital twin model of the gas station is equal to the physical location information of node K or is a mapping information of the physical location information. The second information segment is the logical location information of node J in the twin digital model of the gas station. The logical location information of node J in the twin digital model of the gas station is equal to the physical location information of node J or is a mapping information of the physical location information.

[0051] Figure 5 This is one specific embodiment of the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing method claimed in this invention. Simultaneously, this invention also proposes a root cause tracing method applied to the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system as described in any of the above claims: Step S102: Based on the twin digital model of the gas station, establish a gas station early warning loop based on the data flow node relationship of the gas station, and simultaneously establish targeted early warning relationships between each node of the early warning loop; Step S104: First gas fusion driven data chain, establish gas fusion early warning driven data chain for nodes with targeted early warning relationship; Step S106: Use the second gas fusion drive data chain to store the abnormal alarm information of node P and generate the root cause tracing record and root cause tracing node of node P; Step S108: The gas mechanism model anomaly early warning iteration module obtains real-time operating parameters and configures the early warning relationship node information data structure; Step S110: The root cause tracing overlay module of the gas data fusion model performs root cause tracing record and root cause tracing record fusion when node P alarms abnormally.

[0052] Simultaneously, the present invention also proposes a computer-readable storage medium storing a program for electronic data processing, wherein the program causes a terminal to perform the corresponding functions of the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system as described in any of the preceding claims.

[0053] At the same time, the present invention also proposes a computer program product, which includes computer instructions, which execute the corresponding functions of the mechanism-data fusion driven gas station anomaly early warning and root cause tracing system as described above when the processor runs.

[0054] This invention proposes a mechanism-data fusion-driven method and system for early warning and root cause tracing of gas station anomalies. Through the synergistic application of a mechanism model and a data-driven model, an early warning ring network is established based on a twin digital model of the gas station in an anomaly early warning scenario. This network includes various possible anomaly nodes and their data flow relationships. Targeted collaborative data chains for related nodes are set up within the early warning network. The mechanism model iteratively configures the early warning information data structure. A gas data fusion model is used to perform root cause tracing of related nodes. While detecting and alarming anomalies, the root cause of the anomaly is found through the flow logic of the abnormal data relationships. The gas fusion early warning information mode triggers alarms and information displays on the system management end. This systematic approach improves the efficiency and accuracy of early warning linkage, providing a solid foundation for timely detection, timely handling, and hazard investigation.

[0055] In all the above embodiments, in order to achieve certain requirements for data transmission and read / write functions, the above methods and corresponding devices can be expanded by adding devices, modules, components, hardware, pin connections, or differences in memory and processor during operation.

[0056] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the methods, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0057] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of method steps is only a logical or functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, apparatuses, or units, and may be electrical, mechanical, or other forms.

[0058] The units described as separate components of the method and apparatus may or may not be logically or physically separate, and may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0059] Furthermore, the method steps and their implementations, as well as the functional units, in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0060] The aforementioned methods and apparatus can be implemented as integrated units in the form of software functional units, which can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), NVRAM, magnetic disks, or optical disks.

[0061] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0062] It should be noted that the above embodiments are only used to more clearly explain and illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A mechanism-data fusion-driven early warning and root cause tracing system for gas station anomalies, characterized in that, The system includes at least: a gas station early warning target ring, which is based on a gas station twin digital model, establishes a gas station early warning ring based on the data flow node relationship of the gas station, and simultaneously establishes the target early warning relationship between each node of the early warning ring; The first gas fusion driving data chain establishes a gas fusion early warning driving data chain for nodes with targeted early warning relationships; the gas fusion early warning driving data chain acquires the early warning relationship node information data structure sent by the gas mechanism model abnormal early warning iteration module, which is associated with nodes with targeted early warning relationships, and generates the first gas fusion early warning information based on the root cause tracing nodes output by the gas data fusion model root cause tracing overlay module. The second gas fusion-driven data chain stores abnormal alarm information related to node P and generates root cause tracing records and root cause tracing nodes for node P; it includes at least: storing abnormal alarm information related to node P in the data chain, and generating and storing root cause tracing records and root cause tracing nodes for node P based on the processing results of the root cause tracing overlay module of the gas data fusion model for the stored abnormal alarm information of node P. The gas mechanism model anomaly early warning iteration module acquires real-time operating parameters and configures the data structure of early warning relationship node information; The root cause tracing overlay module of the gas data fusion model performs root cause tracing records and root cause tracing record fusion when node P alarms abnormally; Among them, the gas mechanism model anomaly early warning iteration module obtains the real-time operating parameters of each node in the twin digital model of the gas station, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain; When an abnormal alarm occurs at node P, the root cause tracing overlay module of the gas data fusion model registers the abnormality in the second gas fusion driving data chain and assigns an abnormality ID. It records the real-time operating parameters of node Ci that has a targeted early warning relationship with the abnormal node P of the gas station, records the ID of node Ci whose parameters are outside the safe range, and stores the abnormality ID, node P, and node Ci's ID as a root cause tracing record in the second gas fusion driving data chain. Periodically, based on the second gas fusion driving data chain, the root cause tracing records of node P are fused, and the IDs of nodes Ci that appear in multiple historical root cause tracing records of node P with a proportion below the third threshold are deleted. The IDs of the remaining nodes Ci are recorded as the root cause tracing nodes of node P and stored in the second gas fusion driving data chain. Wherein, node Ci can be one or more, the safety range is the normal operating parameter range of each node preset by the system, and the third threshold is a percentage preset by the system.

2. The gas station anomaly early warning and root cause tracing system based on mechanism-data fusion as described in claim 1, characterized in that: It also includes a system output terminal, which displays the early warning status of each node of the gas station to the gas station administrator's control center and control screen based on the first gas fusion early warning information and the gas station twin digital model.

3. The gas station anomaly early warning and root cause tracing system based on mechanism-data fusion as described in claim 2, characterized in that: The targeted early warning relationship includes at least a bidirectional one-to-one mapping relationship, used to characterize two nodes whose associated faults at abnormal nodes of a gas station are greater than a preset second threshold. The second threshold is a percentage preset by the system.

4. The gas station anomaly early warning and root cause tracing system based on mechanism-data fusion as described in claim 3, characterized in that: The gas mechanism model anomaly early warning iteration module acquires the real-time operating parameters of each node in the gas station twin digital model, configures the early warning relationship node information data structure, and transmits it to the first gas fusion driving data chain, specifically: The gas mechanism model anomaly early warning iteration module dynamically obtains the real-time operating parameters of each node from the twin digital model of the gas station. It constructs and configures an early warning relationship node information data structure containing multiple information fields, using the node ID combination of all nodes K and J with targeted early warning relationships as the class name, and transmits it to the first gas fusion driving data chain. in, The plurality of information fields include at least: The node pair parameter confirmation information includes at least the logical location information pair of nodes K and J with a targeted early warning relationship in the twin digital model of the gas station, which is used by each node to confirm the node information data structure of the early warning relationship during transmission, corresponding to the node ID combination of nodes K and J with a targeted early warning relationship. The two-dimensional information field of gas data flow between nodes represents the relevant parameter information of gas transmission from node K to node J as time changes; The system transmission control signaling flow field between nodes represents the signaling information issued by the system user for setting the data transmission from node K to node J and from node J to node K.

5. The gas station anomaly early warning and root cause tracing system based on mechanism-data fusion as described in claim 4, characterized in that: The logical location information pair of nodes K and J with the targeted early warning relationship in the twin digital model of the gas station includes at least: The first information segment is the logical location information of node K in the digital twin model of the gas station. The logical location information of node K in the digital twin model of the gas station is equal to the physical location information of node K or is a mapping information of the physical location information. The second information segment is the logical location information of node J in the twin digital model of the gas station. The logical location information of node J in the twin digital model of the gas station is equal to the physical location information of node J or is a mapping information of the physical location information.

6. A root cause tracing method applied to the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system as described in any one of claims 1-5, characterized in that, It should include at least the following steps: Step 1: Based on the twin digital model of the gas station, establish an early warning loop for the gas station based on the data flow node relationship of the gas station, and simultaneously establish targeted early warning relationships between each node of the early warning loop; Step 2: First gas fusion driven data chain, establish gas fusion early warning driven data chain for nodes with targeted early warning relationship; Step 3: Use the second gas fusion drive data chain to store abnormal alarm information of node P and generate root cause tracing record and root cause tracing node of node P; Step 4: The gas mechanism model anomaly early warning iteration module acquires real-time operating parameters and configures the data structure of early warning relationship nodes; Step 5: The root cause tracing overlay module of the gas data fusion model performs root cause tracing record and root cause tracing record fusion when node P alarms abnormally.

7. A computer-readable storage medium storing a program for electronic data processing, characterized in that, The program enables the terminal to perform the corresponding functions of the mechanism-data fusion-driven gas station anomaly early warning and root cause tracing system as described in any one of claims 1-5.

Images