Pipeline safety detection method and device, electronic equipment and storage medium

Abstract

The application discloses a pipeline safety detection method and device, electronic equipment and storage medium, and relates to the technical field of intelligent detection or other related technical fields, wherein the method comprises the following steps: acquiring a position influence correction factor of a plurality of collection points in a three-dimensional pipeline model; receiving multi-source sensing data transmitted by a flow meter, spatially weighting the multi-source sensing data by using the position influence correction factor, and calculating a pipeline self safety index and an internal environment safety index of each collection point; fusing the pipeline self safety index and the internal environment safety index to obtain a comprehensive safety index of each collection point, and constructing a comprehensive safety index distribution based on the comprehensive safety index of each collection point; and positioning a pipeline hidden danger area by using a clustering algorithm based on the comprehensive safety index distribution, and generating a repair strategy. The application solves the technical problems of a pipeline safety detection mode in related technologies, such as low detection efficiency and low risk identification accuracy, which depends on manual inspection and experience judgment.

Description

Technical Field

[0001] This invention relates to the field of intelligent detection technology, and more specifically, to a pipeline safety detection method and apparatus, electronic equipment, and storage medium. Background Technology

[0002] As a core infrastructure for energy transmission, urban water supply and drainage, chemical production, and long-distance pipeline systems, the operational safety of pipelines is directly related to public safety, the ecological environment, and industrial continuity. With the acceleration of urbanization and the expansion of industrial scale, pipeline systems face increasingly complex operating environments, including but not limited to multiple coupled risk factors such as internal wall corrosion, sediment accumulation, leakage of toxic media, severe pressure fluctuations, and sudden changes in fluid conditions.

[0003] In related technologies, to ensure the long-term stable operation of pipelines, the traditional approach relies on a combination of regular manual inspections and experience-based judgment. However, this inspection method has drawbacks in terms of response timeliness, data comprehensiveness, and risk identification accuracy, and can no longer meet the needs of modern intelligent operation and maintenance.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a pipeline safety inspection method, apparatus, electronic device, and storage medium to at least solve the technical problems of low inspection efficiency and low risk identification accuracy in pipeline safety inspection methods that rely on manual inspection and experience judgment in related technologies.

[0006] According to one aspect of the present invention, a pipeline safety inspection method is provided, comprising: acquiring position influence correction factors for multiple acquisition points in a three-dimensional pipeline model, wherein the three-dimensional pipeline model is constructed based on a target pipeline; receiving multi-source sensor data transmitted by a flow meter, spatially weighting the multi-source sensor data using the position influence correction factors, and calculating a pipeline safety index and an internal environment safety index for each acquisition point; fusing the pipeline safety index and the internal environment safety index to obtain a comprehensive safety index for each acquisition point, and constructing a comprehensive safety index distribution based on the comprehensive safety index for each acquisition point; locating pipeline hazard areas using a clustering algorithm based on the comprehensive safety index distribution, and generating a repair strategy based on the pipeline hazard areas.

[0007] Furthermore, before obtaining the spatial position vectors of multiple acquisition points within each monitoring unit in the three-dimensional pipeline model, the method further includes: constructing the three-dimensional pipeline model based on the pipeline entity of the target pipeline; dividing the three-dimensional pipeline model into N equidistant monitoring units along the pipeline axis, where N is a positive integer; and deploying M acquisition points within each equidistant monitoring unit, where M is a positive integer.

[0008] Further, the step of obtaining the position influence correction factor of multiple acquisition points in the three-dimensional pipeline model includes: establishing a three-dimensional rectangular coordinate system for the three-dimensional pipeline model, quantizing the position data of each acquisition point according to the three-dimensional rectangular coordinate system to obtain a position vector; extracting the risk position feature vector of the three-dimensional pipeline model; calculating the cosine value between the position vector of each acquisition point and the risk position feature vector to obtain the position influence correction factor of each acquisition point in each risk dimension.

[0009] Further, the multi-source sensing data includes at least one of the following: sludge thickness, sludge density, corrosion depth, and pressure change data. The step of calculating the pipeline safety index for each of the acquisition points includes: calculating a sludge accumulation influence coefficient based on the sludge thickness and the sludge density; calculating a corrosion influence coefficient based on the corrosion depth; calculating a pressure change influence coefficient based on the pressure change data; constructing a first influence coefficient vector for pipeline safety by combining the sludge accumulation influence coefficient, the corrosion influence coefficient, and the pressure change influence coefficient; and calculating the pipeline safety index for each of the acquisition points based on the first influence coefficient vector, the pipeline safety weight vector, and a first position influence correction factor matrix constructed by the position influence correction factor.

[0010] Further, the multi-source sensing data includes at least one of the following: concentration of the analyte and flow rate. The step of calculating the internal environmental safety index of each of the collection points includes: calculating the analyte influence coefficient based on the analyte concentration; calculating the flow rate change influence coefficient based on the flow rate; constructing a second influence coefficient vector for pipeline internal environmental safety by combining the analyte influence coefficient and the flow rate change influence coefficient; and calculating the internal environmental safety index of each of the collection points based on the second influence coefficient vector, the internal environmental safety weight vector, and the second position influence correction factor matrix constructed by the position influence correction factor.

[0011] Furthermore, the step of generating a remediation strategy based on the pipeline hazard area includes: extracting the hazard level of the pipeline hazard area from the clustering results obtained by the clustering algorithm; identifying the hazard type of the pipeline hazard area; and generating the remediation strategy based on the matching results of the hazard level and the hazard type against a knowledge base.

[0012] Furthermore, after generating a repair strategy based on the pipeline hazard area, the method further includes: Step 1, for the repaired target pipeline, collecting multi-source sensor data from all collection points in the pipeline hazard area and its two adjacent equidistant monitoring units; Step 2, calculating the comprehensive safety index distribution of each selected collection point based on the multi-source sensor data; repeating Step 1 to Step 2 until the comprehensive safety index of each selected collection point in the comprehensive safety index distribution is less than or equal to the comprehensive safety index threshold, thus obtaining the repaired target pipeline.

[0013] According to another aspect of the present invention, a pipeline safety detection device is also provided, comprising: an acquisition unit, configured to acquire position influence correction factors for multiple acquisition points in a three-dimensional pipeline model, wherein the three-dimensional pipeline model is constructed based on a target pipeline; a calculation unit, configured to receive multi-source sensor data transmitted by a flow meter, spatially weight the multi-source sensor data using the position influence correction factors, and calculate the pipeline's own safety index and the internal environment safety index for each acquisition point; a fusion unit, configured to fuse the pipeline's own safety index and the internal environment safety index to obtain a comprehensive safety index for each acquisition point, and construct a comprehensive safety index distribution based on the comprehensive safety index for each acquisition point; and a positioning unit, configured to locate pipeline hazard areas using a clustering algorithm based on the comprehensive safety index distribution, and generate a repair strategy based on the pipeline hazard areas.

[0014] Furthermore, the pipeline safety detection device further includes: a first construction module, used to construct the three-dimensional pipeline model based on the pipeline entity of the target pipeline; a first division module, used to divide the three-dimensional pipeline model into N equidistant monitoring units along the pipeline axis, where N is a positive integer; and a first deployment module, used to deploy M collection points in each equidistant monitoring unit, where M is a positive integer.

[0015] Further, the acquisition unit includes: a first establishment module, used to establish a three-dimensional rectangular coordinate system for the three-dimensional pipeline model, quantize the position data of each acquisition point according to the three-dimensional rectangular coordinate system, and obtain a position vector; a first extraction module, used to extract the risk position feature vector of the three-dimensional pipeline model; and a first calculation module, used to calculate the cosine value between the position vector of each acquisition point and the risk position feature vector, and obtain the position influence correction factor of each acquisition point in each risk dimension.

[0016] Further, the multi-source sensing data includes at least one of the following: sludge thickness, sludge density, corrosion depth, and pressure change data. The calculation unit includes: a second calculation module for calculating a sludge accumulation influence coefficient based on the sludge thickness and the sludge density; a third calculation module for calculating a corrosion influence coefficient based on the corrosion depth; a fourth calculation module for calculating a pressure change influence coefficient based on the pressure change data; a first construction module for constructing a first influence coefficient vector for pipeline safety by combining the sludge accumulation influence coefficient, the corrosion influence coefficient, and the pressure change influence coefficient; and a fifth calculation module for calculating the pipeline safety index for each of the acquisition points based on the first influence coefficient vector, the pipeline safety weight vector, and a first position influence correction factor matrix constructed by the position influence correction factor.

[0017] Furthermore, the multi-source sensing data includes at least one of the following: concentration of the analyte and flow rate. The calculation unit further includes: a sixth calculation module for calculating the influence coefficient of the analyte based on the concentration of the analyte; a seventh calculation module for calculating the influence coefficient of flow rate change based on the flow rate; a second construction module for constructing a second influence coefficient vector for pipeline internal environmental safety by combining the influence coefficient of the analyte and the influence coefficient of flow rate change; and an eighth calculation module for calculating the internal environmental safety index of each collection point based on the second influence coefficient vector, the internal environmental safety weight vector, and a second position influence correction factor matrix constructed by the position influence correction factor.

[0018] Furthermore, the positioning unit includes: a second extraction module, used to extract the degree of hazard in the pipeline hazard area from the clustering results obtained by the clustering algorithm; a first identification module, used to identify the type of hazard in the pipeline hazard area; and a first matching module, used to generate the repair strategy based on the matching results by matching the degree of hazard and the type of hazard with a knowledge base.

[0019] Furthermore, the pipeline safety detection device further includes: a first acquisition module, used in step one, for the repaired target pipeline, to acquire multi-source sensor data of all acquisition points in the pipeline hazard area and the two adjacent equidistant monitoring units; a ninth calculation module, used in step two, to calculate the comprehensive safety index distribution of each selected acquisition point based on the multi-source sensor data; and a first repetition module, used to repeat steps one to two above until the comprehensive safety index of each selected acquisition point in the comprehensive safety index distribution is less than or equal to the comprehensive safety index threshold, thereby obtaining the repaired target pipeline.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform any of the above-described pipeline safety detection methods.

[0021] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any of the above-described pipeline safety detection methods.

[0022] In this application, the following steps are performed: obtaining position influence correction factors for multiple acquisition points in a 3D pipeline model, wherein the 3D pipeline model is constructed based on the target pipeline, receiving multi-source sensor data transmitted by a flow meter, spatially weighting the multi-source sensor data using the position influence correction factors, calculating the pipeline's own safety index and internal environment safety index for each acquisition point, fusing the pipeline's own safety index and internal environment safety index to obtain the comprehensive safety index for each acquisition point, constructing a comprehensive safety index distribution based on the comprehensive safety index for each acquisition point, locating pipeline hazard areas using a clustering algorithm based on the comprehensive safety index distribution, and generating repair strategies based on the pipeline hazard areas.

[0023] In this application, a three-dimensional pipeline model is used for discretized sampling to form a coordinate system of multiple acquisition points with a clear spatial distribution, thereby providing a unified and objective spatial benchmark for risk assessment. Subsequently, multi-source sensor data such as sludge thickness, corrosion depth, toxic substance concentration, pressure fluctuations, and flow velocity, transmitted in real time by a flow meter detection device integrating multiple sensors, are received. A location influence correction factor is introduced, and by analyzing the correlation between the geometric position of the acquisition points in the three-dimensional space of the pipeline and historical risk characteristics, a dynamic calculation is performed to achieve quantitative weighting of the risk sensitivity of different spatial positions. This allows the multi-source sensor data to undergo spatial adaptive correction based on its actual risk contribution to the pipeline structure. Simultaneously, based on linear algebra... By employing calculus algorithms, a pipeline safety index and an internal environment safety index are constructed to quantify structural integrity and media stability risks, respectively. This approach breaks through the traditional crude mode of single-threshold alarms, enabling multi-dimensional detection and calculation of pipeline safety and forming a comprehensive safety index distribution. This quantifies the safety status of each sampling point within the pipeline and identifies risk and hazard areas based on clustering algorithms, thus completing the pipeline safety inspection. The safety inspection method of this application eliminates the need for manual inspections, improving detection efficiency and risk identification accuracy. This solves the technical problem of low detection efficiency and low risk identification accuracy in pipeline safety inspection methods that rely on manual inspections and experience-based judgments. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0025] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a pipeline safety inspection method is shown.

[0026] Figure 2 This is a flowchart of an optional pipeline safety inspection method according to an embodiment of the present invention;

[0027] Figure 3 This is an optional pipeline safety inspection system architecture diagram according to an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram of an optional detection element and mounting bracket according to an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram of the overall structure of an optional hardware acquisition device according to an embodiment of the present invention;

[0030] Figure 6 This is a schematic diagram of an optional pipeline safety inspection process according to an embodiment of the present invention;

[0031] Figure 7 This is a schematic diagram of an optional pipeline safety inspection device according to an embodiment of the present invention;

[0032] Figure 8 This is a hardware structure block diagram of an electronic device (or mobile device) for performing an optional pipeline safety detection method according to an embodiment of the present invention. Detailed Implementation

[0033] 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.

[0034] 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.

[0035] It should be noted that the pipeline safety inspection method and apparatus in this application can be used in the field of intelligent inspection technology for pipeline safety inspection based on flow meters, and can also be used in any field other than the field of intelligent inspection technology. In the case of pipeline safety inspection based on flow meters, this application does not limit the application field of the pipeline safety inspection method and apparatus.

[0036] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding access points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding access points to choose to agree to or refuse automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0037] The following embodiments of the present invention can be applied to various pipeline safety inspection systems / applications / equipment. The present invention integrates multiple sensor groups through a hardware acquisition layer to simultaneously collect core parameters such as sludge accumulation, internal wall corrosion, toxic substance concentration, pressure changes, and flow rate. Simultaneously, it constructs a hardware acquisition-software analysis linkage mechanism, enabling collaborative analysis of pipeline structural safety and internal environmental parameters, thereby improving detection efficiency and accuracy.

[0038] This invention constructs a 3D model of the pipeline using a 3D positioning and acquisition module, designs a normalized position weight matrix and a position influence correction factor to quantify the risk contribution of different spatial locations, and employs advanced algorithms such as linear algebra matrix operations and calculus / derivative analysis to construct a multi-parameter fusion sub-index and comprehensive index calculation model. Combined with data preprocessing and cross-correction modules, the data quality is improved, ultimately enabling the assessment results to accurately reflect the risk differences of different spatial locations and improve the accuracy of pipeline safety inspection results.

[0039] This invention also designs a closed-loop dynamic correction mechanism of three-dimensional positioning assessment - precise maintenance - data re-sampling - iterative calculation. Through algorithm-like methods, it accurately locates the hidden danger area, formulates targeted maintenance plans, re-sampling data after maintenance to recalculate the assessment index, and sets termination conditions to achieve iterative optimization. This mechanism can continuously adapt to changes in pipeline safety status and effectively reduce the accident rate.

[0040] The present invention will now be described in detail with reference to various embodiments.

[0041] Example 1

[0042] According to an embodiment of the present invention, an embodiment of a pipeline safety inspection method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0043] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a pipeline safety inspection method is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0044] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0045] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the pipeline safety detection method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the pipeline safety detection method described above. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0046] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0047] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0048] Under the aforementioned operating environment, this application provides the following: Figure 2 The pipeline safety inspection method shown is implemented by a pipeline safety inspection system.

[0049] Figure 2 This is a flowchart of an optional pipeline safety inspection method according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0050] Furthermore, before obtaining the spatial position vectors of multiple acquisition points within each monitoring unit in the three-dimensional pipeline model, the process includes: constructing a three-dimensional pipeline model based on the pipeline entity of the target pipeline; dividing the three-dimensional pipeline model into N equidistant monitoring units along the pipeline axis, where N is a positive integer; and deploying M acquisition points within each equidistant monitoring unit, where M is a positive integer.

[0051] It should be noted that before conducting a safety inspection of the target pipeline, due to the complexity of the pipeline's internal structure, data collection needs to be carried out in sections. Therefore, multiple discrete collection points need to be set up first. First, a three-dimensional pipeline model is constructed based on the physical structure and geometric parameters of the target pipeline. This model is generated based on pipeline design drawings or on-site laser scanning data, accurately reproducing key structural features such as the pipeline's axis direction, bends, diameter changes, valves, and welds.

[0052] After the 3D pipeline model is constructed, N monitoring units are divided at fixed intervals along the pipeline axis within the 3D model, where N is a positive integer. Each unit length corresponds to an independent analysis unit. The purpose is to discretize the continuous pipeline structure into quantifiable and independently calculable spatial units, providing a structured basis for the subsequent spatial aggregation and distribution analysis of multi-point data. Subsequently, M collection points are uniformly arranged along a ring within the cross-section of each equidistant monitoring unit, where M is a positive integer and not less than 8, to ensure that the data sampling density within the cross-section meets the spatial coverage requirements. The angular interval between adjacent collection points is 360° / M. This arrangement can effectively avoid local blind spots caused by uneven distribution of collection points, especially under conditions where parameters such as pressure, corrosion, and silt are not uniformly distributed, ensuring the representativeness of data in each direction within the cross-section.

[0053] Through the above steps, the three-dimensional pipeline model is constructed as a regular grid structure consisting of N monitoring units, each containing M spatial discrete acquisition points. This provides a structured and computable spatial coordinate framework for the subsequent definition of spatial location vectors and the calculation of location influence correction factors, ensuring that multi-source sensor data can be accurately mapped to their corresponding physical spatial locations, thus laying the geometric foundation for subsequent spatial weighting and risk distribution modeling.

[0054] Step S201: Obtain the position influence correction factor of multiple acquisition points in the three-dimensional pipeline model, wherein the three-dimensional pipeline model is constructed based on the target pipeline.

[0055] In step S201 above, the position influence correction factor of multiple acquisition points in the three-dimensional pipeline model is obtained. First, a three-dimensional pipeline model is established based on the physical structure and engineering parameters of the target pipeline. This model is constructed based on three-dimensional modeling technology, which fully restores the key structural features of the pipeline axis, elbows, diameter changes, valves, welds and other key structural features. The model coordinate system takes the center of the pipeline starting section as the origin O, the x-axis along the pipeline axis, and the y-axis and z-axis form an orthogonal plane of the cross section, ensuring that the spatial positioning has a clear physical reference benchmark. Based on this three-dimensional model, for the spatial coordinates of each acquisition point, the feature vectors that affect the risk distribution in the pipeline structure are extracted by the linear algebraic eigenvalue decomposition method. These feature vectors respectively represent the typical spatial distribution patterns of high stress concentration areas, fluid disturbance areas and structural weak areas in the pipeline, and the position influence correction factor is calculated based on this, thereby assigning the relative importance of the structural features at different locations to the risk contribution.

[0056] Through the above steps, each acquisition point obtains a correction factor closely related to its spatial location and structural environment, instead of using a uniform default weight. The purpose is to transform the non-uniformity of the pipeline structure into a quantifiable spatial correction parameter, providing a structural sensitivity basis for the spatial weighting of subsequent multi-source sensing data, avoiding risk assessment distortion caused by ignoring geometric position differences, and improving the accuracy of safety detection and risk identification.

[0057] Furthermore, the steps for obtaining the position influence correction factors of multiple acquisition points in the 3D pipeline model include: establishing a 3D Cartesian coordinate system for the 3D pipeline model, quantifying the position data of each acquisition point based on the 3D Cartesian coordinate system to obtain the position vector; extracting the risk position feature vector of the 3D pipeline model; calculating the cosine value between the position vector of each acquisition point and the risk position feature vector to obtain the position influence correction factor of each acquisition point in each risk dimension.

[0058] Specifically, when constructing the positional influence correction factors for each acquisition point, a three-dimensional Cartesian coordinate system Oxyz is first established for the three-dimensional pipeline model. Its origin O is located at the geometric center of the pipeline's initial cross-section. The x-axis extends positively along the pipeline's axis, and the y-axis and z-axis form a cross-sectional coordinate plane perpendicular to the x-axis. The z-axis direction is defined as the pipeline pointing vertically upwards. The establishment of this coordinate system ensures that the spatial positions of all acquisition points have a unified and computable mathematical basis. Based on this coordinate system, the physical position of each acquisition point is quantified, obtaining its coordinate values ​​in three-dimensional space. Where i is the monitoring unit number along the axis direction, The numbers represent the circumferential sampling point numbers (i=1,2,...,N; j=1,2,...,M).

[0059] Subsequently, feature vectors of risk locations are extracted from the 3D pipeline model. These feature vectors, through principal component analysis or structural stress simulation analysis, extract three of the most representative spatial risk distribution patterns from the pipeline geometry model, corresponding to high stress concentration areas (e.g., elbows), areas of significant fluid disturbance (e.g., diameter changes), and structurally weak and sensitive areas (e.g., welds). Each risk location feature vector... (k=1,2,3) is a unit vector describing the dominant extension direction of the risk in three-dimensional space. Next, the position vector of each sampling point is calculated. With risk location feature vector cosine value of the angle between The cosine value reflects the degree of alignment between the sampling point and a certain risk feature in a spatial direction. The closer the value is to 1, the more the point is located in the dominant influence area of ​​the risk model; the closer the value is to 0, the weaker the influence, indicating that it is orthogonal to the risk model. Therefore, the location influence correction factor for each sampling point is expressed as:

[0060]

[0061] in For feature weights, satisfying .

[0062] Through the above steps, the risk characteristics of complex pipeline structures are abstracted into computable geometric vectors. The spatial correlation strength between data collection points and high-risk structures is quantified based on the cosine relationship of the angle between these vectors, thus achieving a transformation from qualitative description to quantitative mapping. This significantly enhances the adaptability of risk assessment to complex pipeline topologies.

[0063] Step S202: Receive multi-source sensor data transmitted by the flow meter, spatially weight the multi-source sensor data using the position influence correction factor, and calculate the pipeline's own safety index and internal environment safety index at each collection point.

[0064] In step S202 above, the flow meter is a detection device deployed on the pipe wall. This device integrates multi-dimensional sensors to collect source sensor data, specifically including: sludge thickness, sludge density, corrosion depth, pressure change data, concentration of the analyte, and flow rate. This data has already undergone calculus sliding window filtering and linear algebra standardization by the device's internal preprocessing module, ensuring noise suppression and dimensional uniformity of the input data. Subsequently, using the acquired location influence correction factors for each acquisition point, the multi-source sensor data is spatially weighted. This enhances and amplifies data from high-risk structural areas (such as elbows and diameter changes) while appropriately attenuating data from straight pipe sections. This ensures that the data weights are strictly matched to the risk sensitivity of their respective spaces, avoiding evaluation distortion caused by ignoring structural location differences.

[0065] Based on spatial weighting, the pipeline's inherent safety index and internal environmental safety index are calculated separately for each collection point. The former, based on structural integrity parameters such as sludge mass distribution gradient, corrosion area and depth, and pressure fluctuation frequency, constructs a nonlinear fusion model through linear algebraic matrix operations and calculus gradient analysis. The formula incorporates mass gradient, corrosion rate, and mean and root mean square fluctuation terms of pressure, ultimately outputting a weighted inner product to characterize the probability of pipeline structural failure. The latter, based on the temporal fluctuation rate of toxic substances and the instantaneous change rate of flow, combines the covariance trace value and flow integral volume, constructing an environmental stability index through calculus time integration and spatial weighted averaging. This reflects the degree of threat to operational safety posed by medium toxicity fluctuations and flow anomalies. This significantly improves the accuracy and spatial specificity of pipeline structural integrity and internal environmental stability assessments.

[0066] Furthermore, the multi-source sensing data includes at least one of the following: sludge thickness, sludge density, corrosion depth, and pressure change data. The steps for calculating the pipeline safety index at each collection point include: calculating the sludge accumulation influence coefficient based on sludge thickness and sludge density; calculating the corrosion influence coefficient based on corrosion depth; calculating the pressure change influence coefficient based on pressure change data; constructing a first influence coefficient vector for pipeline safety by combining the sludge accumulation influence coefficient, corrosion influence coefficient, and pressure change influence coefficient; and calculating the pipeline safety index at each collection point based on the first influence coefficient vector, the pipeline safety weight vector, and a first position influence correction factor matrix constructed from the position influence correction factor.

[0067] Specifically, when calculating the pipeline's own safety index, the focus is on the pipeline's structural integrity, integrating parameters such as silt accumulation, internal wall corrosion, and pressure changes. First, based on the product of silt thickness and silt density, the silt mass per unit area at each sampling point is calculated. ,in, Considering the mass distribution gradient, construct the silt accumulation influence coefficient for the cross-sectional area of ​​a single monitoring unit: ,in , , For quality gradient, The average mass per unit area after incorporating location weights: , The location vector is set based on the risk level of each location within each pipeline. The silt accumulation influence coefficient reflects the dual weakening effect of the total amount of silt and its distribution gradient on the pressure-bearing capacity of the pipe wall.

[0068] Subsequently, a corrosion influence coefficient was constructed by considering the proportion of corroded area, corrosion depth, and corrosion propagation rate. ,in , , This represents the total surface area of ​​the pipe's inner wall. , , ( (As an indicator function), the corrosion influence coefficient comprehensively reflects the impact of corrosion area, depth, and expansion trend on structural integrity.

[0069] A pressure change influence coefficient is constructed based on average pressure change and fluctuation frequency. ,in (Pipe pressure rating) , , , , ( (where is the instantaneous fluctuation frequency), the pressure change influence coefficient reflects the synergistic effect of pressure mean deviation and high-frequency fluctuation on pipe wall fatigue damage.

[0070] Finally, construct the column vector of the first influence coefficient. Introduce its corresponding pipeline safety weight vector and position correction factor matrix To obtain the pipeline's own safety index .

[0071] Furthermore, the multi-source sensing data includes at least one of the following: concentration of the analyte and flow rate. The steps for calculating the internal environmental safety index of each collection point include: calculating the influence coefficient of the analyte based on the concentration of the analyte; calculating the influence coefficient of flow rate change based on the flow rate; constructing a second influence coefficient vector for the internal environmental safety of the pipeline by combining the influence coefficient of the analyte and the influence coefficient of flow rate change; and calculating the internal environmental safety index of each collection point based on the second influence coefficient vector, the internal environmental safety weight vector, and the second position influence correction factor matrix constructed by the position influence correction factor.

[0072] Specifically, the pipeline internal environment safety index focuses on media stability, integrating parameters such as fluctuations in toxic substances (i.e., the substance under test) and flow rate changes. It first considers the spatial consistency of fluctuations to construct the toxic substance fluctuation impact coefficient. ,in (Theoretical collection value) , (Covariance trace value) (T=1 hour), this coefficient comprehensively reflects the impact of corrosion area, depth and expansion trend on structural integrity.

[0073] Subsequently, the influence coefficient of flow change is constructed by combining the magnitude and rate of flow change. ,in, (Rated flow rate) , (Theoretical collection value) , , , ( (where the unit volume is 1), this coefficient reflects the synergistic effect of pressure mean deviation and high-frequency fluctuations on pipe wall fatigue damage.

[0074] Finally, construct the column vector of the second influence coefficient. Introducing an internal environment safety weight vector and the second position influence correction factor matrix constructed from the position influence correction factor. The internal environmental safety index of each sampling point was calculated. By converting the fluctuations of the analyte and the dynamic changes in flow rate into nonlinear influence coefficients and introducing a matrix weighting mechanism based on spatial location, a multi-dimensional collaborative quantification of internal environmental risk was achieved, avoiding the one-sided judgment that relies solely on a single concentration or flow rate threshold.

[0075] Step S203: The pipeline's own safety index and the internal environment safety index are integrated to obtain the comprehensive safety index of each collection point, and the comprehensive safety index distribution is constructed based on the comprehensive safety index of each collection point.

[0076] In step S203 above, a sub-index column vector is constructed based on the pipeline's own safety index and the internal environment safety index. Introducing a global weight matrix and system error correction vector A comprehensive security index is generated using a nonlinear weighted fusion method. In the three-dimensional Cartesian coordinate system of the pipeline, each data collection point is associated with its corresponding comprehensive safety index. The binding forms a three-dimensional spatial scalar field, which is presented in the form of heat map, isosurface or voxel density, intuitively reflecting the distribution pattern, accumulation area and gradient change trend of risks in the entire pipeline system; this distribution not only identifies high-risk points, but also reveals the spatial spread path and associated structure of risks, providing a visual decision basis for systemic risk assessment.

[0077] Step S204: Based on the comprehensive safety index distribution, the pipeline hidden danger area is located by clustering algorithm, and a repair strategy is generated based on the pipeline hidden danger area.

[0078] In step S204 above, the three-dimensional spatial scalar field constructed in step S203—that is, the comprehensive security index corresponding to each acquisition point—is used. Using the spatial coordinates of the data points as input, a clustering algorithm is employed to partition the entire pipeline area into risk profiles. This algorithm uses the comprehensive safety index as the primary clustering feature, supplemented by spatial proximity constraints, to divide all data points into several clusters. One cluster is defined as a "high-risk hazard area," determined by the number of points within that cluster. All values ​​are below the preset threshold and are spatially continuous, satisfying the condition of minimizing the Euclidean distance between the cluster center and its neighbors. During the clustering process, the three-dimensional spatial coordinates of each point are used as auxiliary features to ensure the spatial structure of the hazard area and avoid misjudgment due to noise from isolated sampling points. Finally, a remediation strategy is generated based on the hazard area Ω, and this strategy is differentiated according to the dominant risk dimension corresponding to the hazard area.

[0079] Furthermore, the steps for generating a remediation strategy based on pipeline hazard areas include: extracting the hazard level of the pipeline hazard area from the clustering results obtained through clustering algorithms; identifying the hazard type of the pipeline hazard area; matching the hazard level and hazard type with a knowledge base; and generating a remediation strategy based on the matching results.

[0080] Specifically, after identifying the potential hazard area, the comprehensive safety index of all collection points within the high-risk cluster Ω output by clustering is statistically analyzed to calculate its deviation from the safety threshold, thus determining the degree of hazard. Next, the hazard type of the pipeline hazard area is identified based on the distribution characteristics of the dominant sub-indices in that area: when the pipeline's own safety index is lower than the internal environment safety index, it is classified as a structural hazard, corresponding to structural integrity issues such as sludge accumulation, internal wall corrosion, or pressure fatigue; when the internal environment safety index is significantly lower than the pipeline's own safety index, it is classified as an environmental hazard, corresponding to media stability issues such as excessive concentrations of toxic substances or abnormal flow fluctuations; if both are lower than the preset safety threshold, it is classified as a "compound hazard." This identification mechanism, based on the relative contribution of sub-indices within the hazard area, achieves automatic attribution of risk causes, avoiding subjective human misjudgment.

[0081] Subsequently, based on the extracted hazard severity and identified hazard type, a pre-set engineering knowledge base is matched. This knowledge base is a structured lookup table containing hazard type (structural / environmental / combined), hazard severity level, and the mapping relationship with corresponding remediation strategies. For example, for moderate structural hazards, the matching strategy could be local dredging or laser cladding repair of corrosion points; for severe environmental hazards, the matching strategy could be initiating high-pressure water flushing, installing a gas adsorption device, or adjusting the flow rate to a safe range. The matching process is a lookup-based logical judgment, outputting a unique optimal strategy combination. Finally, a remediation strategy is generated based on the matching results. This strategy includes operation instructions, execution priority, required equipment, and suggested man-hours, and is output to the maintenance scheduling system in the form of a structured data packet to ensure that the strategy can be directly executed.

[0082] Furthermore, after generating a repair strategy based on the pipeline hazard area, the process also includes: Step 1, for the repaired target pipeline, collecting multi-source sensor data from all collection points in the pipeline hazard area and its two adjacent equidistant monitoring units; Step 2, calculating the comprehensive safety index distribution of each selected collection point based on the multi-source sensor data; repeating Step 1 to Step 2 until the comprehensive safety index of each selected collection point in the comprehensive safety index distribution is less than or equal to the comprehensive safety index threshold, thus obtaining the repaired target pipeline.

[0083] Specifically, this embodiment of the invention introduces a closed-loop iterative mechanism of repair-re-sampling-verification. After the maintenance work is completed, the detection component 1 in the hardware acquisition layer restarts the high-precision synchronous acquisition process. For the hidden danger area Ω identified by the clustering algorithm and all acquisition points in the monitoring units adjacent to it along the pipeline axis, multi-source sensor data including the concentration of the substance to be measured, flow rate, sludge thickness, corrosion depth, pressure change, etc. are reacquired. This range is set to cover the hidden danger itself and the adjacent area that may be affected by maintenance disturbance, so as to prevent stress transfer or secondary deposition caused by local repair. The acquisition frequency can be set to 1 time / hour. After the data is filtered, standardized and cross-corrected by the preprocessing module, the output is a highly consistent intermediate variable to ensure the quality of subsequent calculation input. Subsequently, the pipeline's own safety index and internal environment safety index are recalculated for each collection point within the aforementioned monitoring units, and a new comprehensive safety index is generated based on this. Then, the spatial scalar field distribution of this local area is constructed, i.e., the comprehensive safety index distribution after repair. This distribution is compared with the distribution before repair to objectively evaluate the spatial effectiveness of the repair. Then, it is determined whether the comprehensive safety index is greater than or equal to the comprehensive safety index threshold. If not, strategy generation and pipeline repair continue, and the evaluation is iterated until the comprehensive safety index of all collection points in the repaired pipeline is greater than or equal to the comprehensive safety index threshold, at which point the iteration stops.

[0084] Through the above steps, positional influence correction factors for multiple acquisition points in the 3D pipeline model are obtained. The 3D pipeline model is constructed based on the target pipeline and receives multi-source sensor data transmitted from the flow meter. The positional influence correction factors are used to spatially weight the multi-source sensor data to calculate the pipeline's own safety index and internal environment safety index at each acquisition point. The pipeline's own safety index and internal environment safety index are fused to obtain the comprehensive safety index of each acquisition point. A comprehensive safety index distribution is constructed based on the comprehensive safety index of each acquisition point. Based on the comprehensive safety index distribution, a clustering algorithm is used to locate pipeline hazard areas, and a repair strategy is generated based on the pipeline hazard areas.

[0085] In this embodiment, discretized sampling is performed using a three-dimensional pipeline model to form a coordinate system of multiple acquisition points with a clear spatial distribution, thereby providing a unified and objective spatial benchmark for risk assessment. Subsequently, multi-source sensor data, such as sludge thickness, corrosion depth, toxic substance concentration, pressure fluctuations, and flow rate, are received in real time from a flow meter detection device integrating multiple sensors. A location influence correction factor is introduced, and by analyzing the correlation between the geometric position of the acquisition points in the three-dimensional space of the pipeline and historical risk characteristics, a dynamic calculation is performed to achieve quantitative weighting of risk sensitivity at different spatial locations. This allows the multi-source sensor data to undergo spatial adaptive correction based on its actual risk contribution to the pipeline structure. Simultaneously, based on linear algebra... By employing calculus algorithms, a pipeline safety index and an internal environment safety index are constructed to quantify structural integrity and media stability risks, respectively. This approach breaks through the traditional crude mode of single-threshold alarms, enabling multi-dimensional detection and calculation of pipeline safety and forming a comprehensive safety index distribution. This quantifies the safety status of each sampling point within the pipeline and identifies risk and hazard areas based on clustering algorithms, thus completing the pipeline safety inspection. The safety inspection method of this application eliminates the need for manual inspections, improving detection efficiency and risk identification accuracy. This solves the technical problem of low detection efficiency and low risk identification accuracy in pipeline safety inspection methods that rely on manual inspections and experience-based judgments.

[0086] The following describes in detail another optional implementation method.

[0087] Figure 3 This is an optional pipeline safety inspection system architecture diagram according to an embodiment of the present invention, such as... Figure 3 As shown, the pipeline safety monitoring system is divided into a hardware acquisition device (corresponding to the flow meter mentioned above) and a software processing subsystem. The hardware acquisition device includes a detection component and a mechanical support structure, and has data preprocessing capabilities. The multi-source data acquired by the detection component is preprocessed and then wirelessly transmitted to the software processing subsystem for calculation and analysis. The software processing subsystem includes an intelligent output and feedback module, a 3D positioning acquisition module, an algorithm processing module, a comprehensive analysis module, and a dynamic correction module.

[0088] Figure 4 This is a schematic diagram of an optional detection element and mounting bracket according to an embodiment of the present invention, as shown below. Figure 4 As shown, the test piece 1 is a cylindrical structure (diameter...). (80mm in diameter, 200mm in length), IP68 protection rating, suitable for harsh working conditions such as underwater and humid environments, with an integrated multi-module design.

[0089] Mounting bracket 2 is connected to the detection component 1. Mounting bracket 2 is made of aluminum alloy forging and has reserved mounting holes 3 (hole diameter Φ10mm, hole spacing 50mm). The detection component 1 is fixed by bolts, and the installation accuracy is ≤±1mm to ensure that the detection component's acquisition end is accurately aligned with the pipeline monitoring area.

[0090] Figure 5 This is a schematic diagram of the overall structure of an optional hardware acquisition device according to an embodiment of the present invention, such as... Figure 5 As shown, the support base 4 is made of cast iron and has an anti-slip rubber pad on the bottom, providing stable support for the entire device. It has a load-bearing capacity of ≥50kg and is suitable for complex installation environments around pipelines. The testing component 1 is connected to the support base 4 via the mounting bracket 2 and the mounting hole 3.

[0091] The support rod 5 is made of retractable stainless steel and its height is fixed by a threaded knob. The verticality error is ≤ ±0.5°, which enables precise height adaptation of the test piece 1.

[0092] The following functional modules are integrated within the testing component:

[0093] The multi-parameter acquisition module integrates multiple sensor groups to achieve synchronous acquisition of core parameters. The acquisition frequency can be set to once per hour. The sensor group specifically includes: an ultrasonic thickness sensor with a measurement range of 0-50 mm and an accuracy of ±0.1 mm, which acquires the silt thickness at each monitoring point. Density sensor, measuring range 0.2 g / cm³, accuracy ±0.01 g / cm³, for collecting silt density data. Toxic gas / liquid (corresponding to the substances mentioned above) sensor, measurement range 0-1000ppm, accuracy ±5ppm, acquiring toxic substance concentration sequences. (t is time); Electromagnetic flowmeter, measuring range 0-10 m / s, accuracy ±0.5%FS, collects flow velocity distribution in pipeline. Endoscopic inspection sensor, pixel ≥1080P, detection accuracy ±0.01mm, for collecting corrosion depth data of the pipe inner wall. Pressure sensor, measuring range 0.1 MPa, accuracy ±0.1% FS, collects pressure changes on the inner wall of the pipeline. Divide the area into upper and lower semicircles according to the z-axis (z≥0 is the upper semicircle, z<0 is the lower semicircle).

[0094] The preprocessing module uses calculus sliding window integral filtering to remove random noise. The filtering formula is as follows:

[0095]

[0096] in For the preprocessed data, This is the original collected data. Minutes (filter window length); the filtered data is then normalized to the [0,1] interval using linear algebra, as shown in the formula:

[0097]

[0098] in , The parameter represents the historical extreme value.

[0099] The cross-correction module, based on a multi-model iterative algorithm, constructs a sensor error correction model. It corrects the system errors of different sensors through linear algebra matrix operations, outputs standardized core intermediate variables, and adaptively adjusts correction parameters to adapt to different operating conditions.

[0100] The data communication module uses wireless communication technology to transmit pre-processed standardized data to the software processing layer in real time, with a transmission delay of ≤100ms and a data packet loss rate of ≤0.1%.

[0101] The integrated computing module performs preliminary processing of the collected data and outputs basic data such as flow rate value Q and original parameter sequences, providing input for the software processing layer.

[0102] The output module is equipped with a local display screen to show the flow rate, collection status, and communication status in real time, and supports local data storage (storage capacity ≥ 16GB).

[0103] The feedback module receives parameter adjustment instructions from the software processing layer and adaptively optimizes parameters such as sensor acquisition frequency and filter window size.

[0104] The specific functional modules of the software processing subsystem are as follows:

[0105] The 3D positioning and acquisition module includes the following functions:

[0106] 3D model construction: Based on 3D modeling technology, a 3D solid model of the pipeline is constructed to restore key structures such as pipeline axis, elbows, diameter changes, and valves.

[0107] The monitoring units are divided into N equidistant monitoring units along the pipeline axis (the unit length can be adjusted according to the pipeline diameter, with a default of 1m). Within each unit, M collection points are evenly distributed in a ring (M≥8, to ensure full coverage of the cross section).

[0108] Coordinate system construction: Establish a three-dimensional rectangular coordinate system Oxyz for the pipeline, with the origin O being the center of the pipeline's starting section. The x-axis is along the pipeline's axis, while the y-axis and z-axis are orthogonal within the pipeline's cross-section.

[0109] Location quantization, the spatial location of each acquisition point is represented by a location vector. Represent (i=1,2,...,N; j=1,2,...,M); Define the position weight matrix The weight values ​​are set based on the risk level (e.g., 1.2 for elbows and diameter changes, 1.0 for straight pipe sections, and 1.1 near valves), satisfying the normalization constraint:

[0110]

[0111] The location impact correction factor is calculated by extracting the key risk location feature vectors from the pipeline's 3D model through linear algebraic eigenvalue decomposition. (k=1,2,3), calculate the cosine of the angle between the position vector of each acquisition point and the feature vector. The position influence correction factor is obtained as follows:

[0112]

[0113] in For feature weights, satisfying .

[0114] The algorithm processing module, based on the standardized data transmitted from the hardware acquisition layer, uses linear algebra and calculus algorithms to calculate two core sub-indices.

[0115] Pipeline safety index ( Focusing on the integrity of the pipeline structure, it integrates parameters such as silt accumulation, internal wall corrosion, and pressure change, with values ​​ranging from [0,1].

[0116] Silt accumulation influence coefficient ( Considering the mass distribution gradient, the formula is:

[0117]

[0118] in (DN500 steel pipe load-bearing standard) , For quality gradient, The average mass per unit area after incorporating location weights:

[0119]

[0120] in ( (Cross-sectional area of ​​a single monitoring unit) This represents the original unit area mass matrix of the data collection points.

[0121] Corrosion influence coefficient ( The formula is based on the comprehensive area ratio, depth, and expansion rate:

[0122]

[0123] in (Q235 steel pipe corrosion resistance standard). , This represents the total surface area of ​​the pipe's inner wall. , , ( (For indicator functions).

[0124] Pressure change influence coefficient ( Based on the average pressure change and fluctuation frequency, the formula is:

[0125]

[0126] in (Pipe pressure rating) , , , , ( (Instantaneous fluctuation frequency).

[0127] Based on the calculated influence coefficients of silt accumulation, corrosion, and pressure change, an influence coefficient column vector is constructed. Weight vector Introducing a position influence correction factor matrix The formula is:

[0128]

[0129] Pipeline internal environment safety index ( ): Focusing on media stability, it integrates parameters such as fluctuations in toxic substances and changes in flow rate, with a value range of [0,1].

[0130] Toxic substance fluctuation influence coefficient ( Considering the consistency of volatility space, the formula is:

[0131]

[0132] in (Theoretical collection value) , (Covariance trace value) (T = 1 hour).

[0133] Influence coefficient of flow rate change ( Combining the magnitude and rate of flow change, the formula is:

[0134]

[0135] in (Rated flow rate) , (Theoretical collection value) , , , ( (Unit volume).

[0136] Based on the calculated toxic substance fluctuation impact coefficient and flow rate change impact coefficient, an impact coefficient column vector is constructed. Weight vector Introducing an environmental parameter location correction matrix ( , The formula is:

[0137]

[0138] Construct a sub-index column vector based on the pipeline's own safety index and the internal environment safety index. Introducing a global weight matrix and the system error correction vector The comprehensive safety index is calculated as follows:

[0139]

[0140] The dynamic correction module includes a closed-loop correction mechanism, constructing a closed loop for precise maintenance re-acquisition and iterative calculation based on 3D positioning and assessment. For unsafe conditions, the following process is executed:

[0141] Hazard location and measurement, based on three-dimensional model location vectors Based on the sub-index distribution, the potential hazard areas are divided using clustering algorithms, and the degree of hazard is determined. ( (for the preset target security threshold), through Quantify the severity of potential risks.

[0142] Precise maintenance plans are developed based on the type of potential hazard (sludge buildup / corrosion / abnormal pressure, etc.), and targeted maintenance solutions (such as sludge removal, corrosion repair, pressure adjustment, etc.) are provided.

[0143] After the pipeline is repaired, the hardware acquisition layer re-acquires all parameters of the hazard area and the surrounding adjacent monitoring units, repeating the preprocessing process.

[0144] Iterative computation, secondary computation in the software processing layer , , The iteration termination condition is .

[0145] Intelligent output module, judgment If the standard is met, a safety assessment report will be output (including the original data of each parameter, the index calculation process, the location map of the hidden danger, and maintenance suggestions); if the standard is not met, a manual correction instruction will be sent (including the specific coordinates of the hidden danger and its priority).

[0146] The feedback module adaptively adjusts the hardware acquisition layer parameters (e.g., increasing the acquisition frequency in high-risk areas to once every 30 minutes) and the software algorithm weights (e.g., increasing the corrosion parameter weight in severely corroded areas to 0.6) based on the output results.

[0147] Figure 6 This is a schematic diagram of an optional pipeline safety inspection process according to an embodiment of the present invention, such as... Figure 6 As shown, the pipeline safety inspection process specifically includes:

[0148] Step 1: Device installation and initialization. Fix the detection component using the support base, support rod, and mounting bracket, align it with the pipeline monitoring area, and initialize the three-dimensional coordinate system and position weight matrix.

[0149] Step 2: Multi-parameter synchronous acquisition. The multi-parameter acquisition module inside the detection unit acquires parameters such as sludge thickness, density, toxic substance concentration, flow rate, corrosion depth, and pressure change at a frequency of once per hour.

[0150] Step 3: Data preprocessing and cross-correction. The preprocessing module uses calculus filtering to remove noise and standardization transformation to process the data; the cross-correction module corrects sensor system errors and outputs core intermediate variables.

[0151] Step four: Real-time data transmission, where standardized data is transmitted to the software processing layer via the data communication module;

[0152] Step 5: 3D positioning and parameter quantization. The 3D positioning acquisition module combines the position vector and weight matrix to quantify the spatial distribution and positional influence of each parameter.

[0153] Step Six: Calculate the sub-index using advanced algorithms. The algorithm processing module calculates the pipeline's own safety index using linear algebra and calculus algorithms. With internal environmental safety index ;

[0154] Step 7: Comprehensive security assessment; the comprehensive analysis module calculates the comprehensive security index. Determine the safety status (safe / warning / dangerous);

[0155] Step 8: In unsafe conditions, dynamic correction and iterative calculation are performed. The dynamic correction module locates potential hazards, formulates maintenance plans, re-collects data, and iteratively calculates until... Meets the standards;

[0156] Step 9: Result Output and Parameter Feedback. In a safe state, the intelligent output module outputs a report or command, and the feedback module optimizes the acquisition and algorithm parameters.

[0157] Step 10, End.

[0158] This invention integrates multiple sensor groups in a hardware acquisition layer to simultaneously collect core parameters such as sludge accumulation, internal wall corrosion, toxic substance concentration, pressure changes, and flow rate. It also establishes a hardware acquisition-software analysis linkage mechanism, enabling collaborative analysis of pipeline structural safety and internal environmental parameters, thus improving detection efficiency and accuracy. Furthermore, this invention constructs a 3D pipeline model using a 3D positioning acquisition module, designs a normalized position weight matrix and position influence correction factor to quantify the risk contribution of different spatial locations. It employs advanced algorithms such as linear algebra matrix operations and calculus / derivative analysis to construct multi-parameter fusion sub-index and comprehensive index calculation models. Combined with data preprocessing and cross-correction modules, it improves data quality, ultimately ensuring that the assessment results accurately reflect the risk differences at different spatial locations, improving the accuracy of pipeline safety inspection results. This invention also designs a closed-loop dynamic correction mechanism of 3D positioning assessment - precise maintenance - data re-acquisition - iterative calculation. Through algorithm-like methods, it accurately locates potential hazard areas, formulates targeted maintenance plans, re-acquires data after maintenance for secondary calculation of the assessment index, and sets termination conditions to achieve iterative optimization. This allows for continuous adaptation to changes in pipeline safety status, effectively reducing the accident rate.

[0159] The following is a detailed description with reference to another embodiment.

[0160] Example 2

[0161] The pipeline safety detection device provided in this embodiment includes multiple implementation units, each of which corresponds to a specific implementation step in the above embodiment one. The specific implementation method and beneficial effects can be referred to the aforementioned method embodiment, and will not be repeated here.

[0162] Figure 7 This is a schematic diagram of an optional pipeline safety inspection device according to an embodiment of the present invention, such as... Figure 4 As shown, the pipeline safety detection device may include: an acquisition unit 71, a calculation unit 72, a fusion unit 73, and a positioning unit 74, wherein,

[0163] Acquisition unit 71 is used to acquire the position influence correction factor of multiple acquisition points in the three-dimensional pipeline model, wherein the three-dimensional pipeline model is constructed based on the target pipeline;

[0164] The calculation unit 72 is used to receive multi-source sensor data transmitted by the flow meter, spatially weight the multi-source sensor data using the position influence correction factor, and calculate the pipeline's own safety index and internal environment safety index at each collection point.

[0165] The fusion unit 73 is used to fuse the pipeline's own safety index and the internal environment safety index to obtain the comprehensive safety index of each collection point, and to construct the comprehensive safety index distribution based on the comprehensive safety index of each collection point.

[0166] The positioning unit 74 is used to locate pipeline hazard areas based on the comprehensive safety index distribution and a clustering algorithm, and to generate a repair strategy based on the pipeline hazard areas.

[0167] The aforementioned pipeline safety detection device acquires position influence correction factors for multiple sampling points in a three-dimensional pipeline model through acquisition unit 71, wherein the three-dimensional pipeline model is constructed based on the target pipeline; it receives multi-source sensor data transmitted by a flow meter through calculation unit 72, spatially weights the multi-source sensor data using position influence correction factors, and calculates the pipeline's own safety index and internal environment safety index for each sampling point; it fuses the pipeline's own safety index and internal environment safety index through fusion unit 73 to obtain the comprehensive safety index for each sampling point, and constructs a comprehensive safety index distribution based on the comprehensive safety index of each sampling point; and it locates pipeline hazard areas based on the comprehensive safety index distribution through clustering algorithm by positioning unit 74, and generates repair strategies based on the pipeline hazard areas.

[0168] In this embodiment, discretized sampling is performed using a three-dimensional pipeline model to form a coordinate system of multiple acquisition points with a clear spatial distribution, thereby providing a unified and objective spatial benchmark for risk assessment. Subsequently, multi-source sensor data, such as sludge thickness, corrosion depth, toxic substance concentration, pressure fluctuations, and flow rate, are received in real time from a flow meter detection device integrating multiple sensors. A location influence correction factor is introduced, and by analyzing the correlation between the geometric position of the acquisition points in the three-dimensional space of the pipeline and historical risk characteristics, a dynamic calculation is performed to achieve quantitative weighting of risk sensitivity at different spatial locations. This allows the multi-source sensor data to undergo spatial adaptive correction based on its actual risk contribution to the pipeline structure. Simultaneously, based on linear algebra... By employing calculus algorithms, a pipeline safety index and an internal environment safety index are constructed to quantify structural integrity and media stability risks, respectively. This approach breaks through the traditional crude mode of single-threshold alarms, enabling multi-dimensional detection and calculation of pipeline safety and forming a comprehensive safety index distribution. This quantifies the safety status of each sampling point within the pipeline and identifies risk and hazard areas based on clustering algorithms, thus completing the pipeline safety inspection. The safety inspection method of this application eliminates the need for manual inspections, improving detection efficiency and risk identification accuracy. This solves the technical problem of low detection efficiency and low risk identification accuracy in pipeline safety inspection methods that rely on manual inspections and experience-based judgments.

[0169] Furthermore, the pipeline safety inspection device also includes: a first construction module, used to construct a three-dimensional pipeline model based on the pipeline entity of the target pipeline; a first division module, used to divide the three-dimensional pipeline model into N equidistant monitoring units along the pipeline axis, where N is a positive integer; and a first deployment module, used to deploy M collection points in each equidistant monitoring unit, where M is a positive integer.

[0170] Furthermore, the acquisition unit includes: a first establishment module, used to establish a three-dimensional rectangular coordinate system for the three-dimensional pipeline model, quantify the position data of each acquisition point based on the three-dimensional rectangular coordinate system, and obtain a position vector; a first extraction module, used to extract the risk position feature vector of the three-dimensional pipeline model; and a first calculation module, used to calculate the cosine value between the position vector of each acquisition point and the risk position feature vector, and obtain the position influence correction factor of each acquisition point in each risk dimension.

[0171] Furthermore, the multi-source sensing data includes at least one of the following: sludge thickness, sludge density, corrosion depth, and pressure change data. The calculation unit includes: a second calculation module for calculating the sludge accumulation influence coefficient based on sludge thickness and sludge density; a third calculation module for calculating the corrosion influence coefficient based on corrosion depth; a fourth calculation module for calculating the pressure change influence coefficient based on pressure change data; a first construction module for constructing a first influence coefficient vector for pipeline safety by combining the sludge accumulation influence coefficient, corrosion influence coefficient, and pressure change influence coefficient; and a fifth calculation module for calculating the pipeline safety index at each collection point based on the first influence coefficient vector, the pipeline safety weight vector, and a first position influence correction factor matrix constructed from the position influence correction factor.

[0172] Furthermore, the multi-source sensor data includes at least one of the following: concentration of the analyte and flow rate. The calculation unit further includes: a sixth calculation module for calculating the influence coefficient of the analyte based on the concentration of the analyte; a seventh calculation module for calculating the influence coefficient of flow rate change based on the flow rate; a second construction module for constructing a second influence coefficient vector for pipeline internal environmental safety by combining the influence coefficient of the analyte and the influence coefficient of flow rate change; and an eighth calculation module for calculating the internal environmental safety index of each collection point based on the second influence coefficient vector, the internal environmental safety weight vector, and a second position influence correction factor matrix constructed by the position influence correction factor.

[0173] Furthermore, the localization unit includes: a second extraction module, used to extract the degree of hazard in the pipeline hazard area from the clustering results obtained by the clustering algorithm; a first identification module, used to identify the type of hazard in the pipeline hazard area; and a first matching module, used to match the hazard degree and hazard type with a knowledge base and generate a repair strategy based on the matching results.

[0174] Furthermore, the pipeline safety detection device also includes: a first acquisition module, used in step one, for the repaired target pipeline, to acquire multi-source sensor data of all acquisition points in the pipeline hazard area and its two adjacent equidistant monitoring units; a ninth calculation module, used in step two, to calculate the comprehensive safety index distribution of each selected acquisition point based on the multi-source sensor data; and a first repeat module, used to repeat steps one to two above until the comprehensive safety index of each selected acquisition point in the comprehensive safety index distribution is less than or equal to the comprehensive safety index threshold, thus obtaining the repaired target pipeline.

[0175] It should be noted that the acquisition unit 71, calculation unit 72, fusion unit 73, and positioning unit 74 mentioned above correspond to steps S201 to S204 in Embodiment 1. The instances and application scenarios implemented by the above units and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules or units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0176] The invention will now be described in conjunction with another alternative embodiment.

[0177] Example 3

[0178] The present invention can also provide an electronic device. Figure 8 This is a hardware structure block diagram of an electronic device (or mobile device) for performing an optional pipeline safety detection method according to an embodiment of the present invention, such as... Figure 8 As shown, the electronic device may include: one or more ( Figure 8 (Only one is shown) processor 802, memory 804, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0179] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0180] The processor can access information and applications stored in the memory via a transmission device to execute the following steps: acquiring positional influence correction factors for multiple acquisition points in a 3D pipeline model, where the 3D pipeline model is constructed based on the target pipeline; receiving multi-source sensor data transmitted from the flow meter, spatially weighting the multi-source sensor data using the positional influence correction factors, and calculating the pipeline's own safety index and internal environment safety index for each acquisition point; fusing the pipeline's own safety index and internal environment safety index to obtain the comprehensive safety index for each acquisition point, and constructing a comprehensive safety index distribution based on the comprehensive safety index for each acquisition point; and locating pipeline hazard areas using a clustering algorithm based on the comprehensive safety index distribution, and generating remediation strategies based on the pipeline hazard areas.

[0181] The processor can access the information and application programs stored in the memory via the transmission device to execute the following steps: construct a three-dimensional pipeline model based on the pipeline entity of the target pipeline; divide the three-dimensional pipeline model into N equidistant monitoring units along the pipeline axis, where N is a positive integer; and deploy M collection points in each equidistant monitoring unit, where M is a positive integer.

[0182] The processor can access the information and application programs stored in the memory via the transmission device to perform the following steps: establish a three-dimensional rectangular coordinate system for the three-dimensional pipeline model; quantify the position data of each acquisition point based on the three-dimensional rectangular coordinate system to obtain the position vector; extract the risk position feature vector of the three-dimensional pipeline model; calculate the cosine value between the position vector of each acquisition point and the risk position feature vector to obtain the position influence correction factor of each acquisition point in each risk dimension.

[0183] The processor can access information and applications stored in the memory via a transmission device to execute the following steps: The multi-source sensing data includes at least one of the following: sludge thickness, sludge density, corrosion depth, and pressure change data. The steps for calculating the pipeline's own safety index at each acquisition point include: calculating the sludge accumulation influence coefficient based on sludge thickness and sludge density; calculating the corrosion influence coefficient based on corrosion depth; calculating the pressure change influence coefficient based on pressure change data; constructing a first influence coefficient vector for pipeline safety by combining the sludge accumulation influence coefficient, corrosion influence coefficient, and pressure change influence coefficient; and calculating the pipeline's own safety index at each acquisition point based on the first influence coefficient vector, the pipeline safety weight vector, and a first position influence correction factor matrix constructed from the position influence correction factor.

[0184] The processor can access information and applications stored in the memory via a transmission device to execute the following steps: The multi-source sensing data includes at least one of the following: concentration of the analyte and flow rate. The steps for calculating the internal environmental safety index of each collection point include: calculating the influence coefficient of the analyte based on the concentration of the analyte; calculating the influence coefficient of flow rate change based on the flow rate; constructing a second influence coefficient vector for the internal environmental safety of the pipeline by combining the influence coefficient of the analyte and the influence coefficient of flow rate change; and calculating the internal environmental safety index of each collection point based on the second influence coefficient vector, the internal environmental safety weight vector, and a second position influence correction factor matrix constructed by the position influence correction factor.

[0185] The processor can access information and applications stored in the memory via a transmission device to execute the following steps: The steps for generating a remediation strategy based on pipeline hazard areas include: extracting the hazard level of the pipeline hazard area from the clustering results obtained through a clustering algorithm; identifying the hazard type of the pipeline hazard area; matching the hazard level and hazard type with a knowledge base; and generating a remediation strategy based on the matching results.

[0186] The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: After generating a repair strategy based on the pipeline hazard area, the steps also include: Step 1, for the repaired target pipeline, collecting multi-source sensor data from all collection points in the pipeline hazard area and its two adjacent equidistant monitoring units; Step 2, calculating the comprehensive safety index distribution of each selected collection point based on the multi-source sensor data; repeating Step 1 to Step 2 until the comprehensive safety index of each selected collection point in the comprehensive safety index distribution is less than or equal to the comprehensive safety index threshold, thus obtaining the repaired target pipeline.

[0187] This invention provides a pipeline safety inspection scheme. By discretizing a three-dimensional pipeline model, a multi-collection point coordinate system with a clear spatial distribution is formed, providing a unified and objective spatial benchmark for risk assessment. Subsequently, multi-source sensor data, such as sludge thickness, corrosion depth, toxic substance concentration, pressure fluctuations, and flow velocity, are received in real-time from a flow meter detection device integrating multiple sensors. A location influence correction factor is introduced, and by dynamically calculating the correlation between the geometric position of the collection points in the three-dimensional space of the pipeline and historical risk characteristics, a quantitative weighting of the risk sensitivity of different spatial locations is achieved. This allows the multi-source sensor data to undergo spatial adaptive correction based on its actual risk contribution to the pipeline structure. Furthermore, based on linear algebra and calculus... The proposed algorithm constructs a pipeline safety index and an internal environment safety index, respectively quantifying structural integrity and media stability risks. This breaks through the traditional crude mode of single-threshold alarms, realizing multi-dimensional detection and calculation of pipeline safety, and forming a comprehensive safety index distribution. This quantifies the safety status of each sampling point within the pipeline, and identifies risk and hazard areas based on clustering algorithms, thus completing the pipeline safety inspection. The safety inspection method of this application does not rely on manual inspection, improving detection efficiency and risk identification accuracy. It also solves the technical problems of low detection efficiency and low risk identification accuracy in pipeline safety inspection methods that rely on manual inspection and experience judgment in related technologies.

[0188] Those skilled in the art will understand that Figure 8 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 8 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 8 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 8 The different configurations shown.

[0189] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0190] The invention will now be described in conjunction with another alternative embodiment.

[0191] Example 4

[0192] This invention also provides a computer-readable storage medium. Optionally, in this invention, the computer-readable storage medium can be used to store the program code executed by the pipeline safety inspection method provided in Embodiment 1.

[0193] Optionally, in this embodiment of the invention, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0194] This invention also provides a computer program product, which, when executed on a data processing device, is suitable for performing the steps of a pipeline safety inspection method: acquiring position influence correction factors for multiple acquisition points in a three-dimensional pipeline model, wherein the three-dimensional pipeline model is constructed based on the target pipeline; receiving multi-source sensor data transmitted by a flow meter, spatially weighting the multi-source sensor data using the position influence correction factors, and calculating the pipeline's own safety index and internal environment safety index for each acquisition point; fusing the pipeline's own safety index and internal environment safety index to obtain a comprehensive safety index for each acquisition point, and constructing a comprehensive safety index distribution based on the comprehensive safety index of each acquisition point; based on the comprehensive safety index distribution, locating pipeline hazard areas using a clustering algorithm, and generating repair strategies based on the pipeline hazard areas.

[0195] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0196] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0197] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0198] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0199] Furthermore, 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 can be implemented in hardware or as a software functional unit.

[0200] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the 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, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0201] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A pipeline safety inspection method, characterized in that, include: Obtain positional influence correction factors for multiple acquisition points in a 3D pipeline model, wherein the 3D pipeline model is constructed based on the target pipeline; Receive multi-source sensor data transmitted by the flow meter, use the location influence correction factor to spatially weight the multi-source sensor data, and calculate the pipeline's own safety index and internal environment safety index for each of the collection points; The comprehensive safety index of each collection point is obtained by integrating the pipeline's own safety index and the internal environment safety index, and a comprehensive safety index distribution is constructed based on the comprehensive safety index of each collection point. Based on the comprehensive safety index distribution, a clustering algorithm is used to locate pipeline hazard areas, and a repair strategy is generated based on these hazard areas.

2. The method according to claim 1, characterized in that, Before obtaining the spatial location vectors of multiple acquisition points within each monitoring unit in the 3D pipeline model, the following steps are also included: The three-dimensional pipeline model is constructed based on the pipeline entity of the target pipeline; Within the three-dimensional pipeline model, N equidistant monitoring units are divided along the pipeline axis, where N is a positive integer; M collection points are set up in each of the equidistant monitoring units, where M is a positive integer.

3. The method according to claim 1, characterized in that, The steps to obtain the position influence correction factor of multiple acquisition points in a 3D pipeline model include: A three-dimensional Cartesian coordinate system is established for the three-dimensional pipeline model, and the position data of each acquisition point is quantified based on the three-dimensional Cartesian coordinate system to obtain a position vector; Extract the risk location feature vector from the three-dimensional pipeline model; Calculate the cosine value between the location vector of each collection point and the risk location feature vector to obtain the location influence correction factor of each collection point in each risk dimension.

4. The method according to claim 1, characterized in that, The multi-source sensing data includes at least one of the following: silt thickness, silt density, corrosion depth, and pressure change data. The steps for calculating the pipeline's own safety index at each of the collection points include: The silt accumulation influence coefficient is calculated based on the silt thickness and the silt density. The corrosion influence coefficient is calculated based on the corrosion depth. Calculate the pressure change influence coefficient based on pressure change data; A first influence coefficient vector for pipeline safety is constructed by combining the silt accumulation influence coefficient, the corrosion influence coefficient, and the pressure change influence coefficient. Based on the first influence coefficient vector, the pipeline safety weight vector, and the first position influence correction factor matrix constructed from the position influence correction factor, the pipeline safety index of each collection point is calculated.

5. The method according to claim 1, characterized in that, The multi-source sensing data includes at least one of the following: concentration of the analyte, flow rate, and the step of calculating the internal environmental safety index of each of the collection points includes: Calculate the influence coefficient of the analyte based on its concentration. Calculate the flow rate change impact coefficient based on the flow rate velocity; By combining the influence coefficient of the substance to be measured and the influence coefficient of the flow rate change, a second influence coefficient vector for the safety of the pipeline internal environment is constructed. Based on the second influence coefficient vector, the internal environment safety weight vector, and the second position influence correction factor matrix constructed from the position influence correction factor, the internal environment safety index of each of the collection points is calculated.

6. The method according to claim 1, characterized in that, The steps for generating a repair strategy based on the pipeline hazard area include: Extract the degree of hazard from the clustering results obtained through the clustering algorithm for the pipeline hazard area; Identify the types of hazards in the pipeline hazard area; Based on the knowledge base matching the degree of the hazard and the type of the hazard, the remediation strategy is generated based on the matching results.

7. The method according to claim 2, characterized in that, After generating a repair strategy based on the pipeline hazard area, the following is also included: Step 1: For the repaired target pipeline, collect multi-source sensor data from all collection points in the pipeline hazard area and the two adjacent equidistant monitoring units; Step 2: Calculate the comprehensive security index distribution of each selected collection point based on the multi-source sensor data; Repeat steps one and two above until the comprehensive safety index of each selected collection point in the comprehensive safety index distribution is less than or equal to the comprehensive safety index threshold, and the target pipeline is repaired.

8. A pipeline safety detection device, characterized in that, include: An acquisition unit is used to acquire position influence correction factors of multiple acquisition points in a three-dimensional pipeline model, wherein the three-dimensional pipeline model is constructed based on the target pipeline; The calculation unit is used to receive multi-source sensor data transmitted by the flow meter, spatially weight the multi-source sensor data using the position influence correction factor, and calculate the pipeline safety index and internal environment safety index of each collection point. The fusion unit is used to fuse the pipeline's own safety index and the internal environment safety index to obtain the comprehensive safety index of each collection point, and to construct a comprehensive safety index distribution based on the comprehensive safety index of each collection point. The positioning unit is used to locate pipeline hazard areas based on the comprehensive safety index distribution using a clustering algorithm, and to generate a repair strategy based on the pipeline hazard areas.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the pipeline safety inspection method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the pipeline safety detection method according to any one of claims 1 to 7.

Images