An internet platform-based long-distance pipeline network danger intelligent early warning system

Abstract

The application discloses a kind of long pipe network danger intelligent early warning systems based on internet platform, it is related to pipeline early warning technical field, system includes: acquisition module is used: at least one sensor is laid on the pipeline of long pipe network and carries out the acquisition of pipeline operation data;Internet platform is used: the risk score of pipeline operation data collected to acquisition module;Internet platform is used: the risk score of pipeline operation data collected to acquisition module, according to target score result, determine target inspection strategy corresponding to target score result in the corresponding relationship of score result and inspection strategy, according to target inspection strategy, establish target scheduling strategy;Scheduling module is used: according to target scheduling strategy, the inspection robot in any inspection module is scheduled.The application significantly improves the safety and reliability of oil and gas pipeline, can discover and handle potential risk in time, ensures the stable operation of oil and gas pipeline, and has important practical application value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipeline early warning, and in particular to a long-distance pipeline network danger intelligent early warning system based on an Internet platform. BACKGROUND

[0002] In recent years, the third generation of oil and gas pipeline technology has developed rapidly, mainly using advanced technologies such as the Internet, big data, and artificial intelligence to achieve comprehensive monitoring, intelligent optimization, and full-link management of pipelines. These new technologies endow oil and gas pipelines with significant features such as high speed, high efficiency, safety, and environmental protection, effectively improving the operational efficiency and safety level of pipelines.

[0003] The existing early warning pipeline system performs early warning management through real-time online monitoring of relevant monitoring data. Once an abnormal situation occurs, the system can immediately reflect the location and severity of the event and timely notify the responsible personnel through SMS, email, pop-up pages, etc. The responsible person can determine whether to start the corresponding process for review or disposal according to the early warning information. The early warning system also records detailed information of historical early warning events, providing important analysis and diagnosis basis for subsequent prediction, identification, and evaluation of early warning events.

[0004] Although the existing early warning pipeline system has certain early warning capabilities, there are still some deficiencies. First, the current early warning system mostly uses a fixed risk assessment model that cannot accurately assess the dynamic risk of the pipeline. This fixed model cannot be adjusted according to the actual situation of pipeline operation, limiting the accuracy and timeliness of risk assessment. Second, the inspection strategy lacks flexibility and cannot be adjusted according to the changes in the operation of the pipeline section, resulting in low utilization efficiency of the inspection robot. SUMMARY

[0005] The present application aims to solve the technical problems of the prior art and provides a long-distance pipeline network danger intelligent early warning system based on an Internet platform, as follows:

[0006] 1) In a first aspect, the present application provides a long-distance pipeline network danger intelligent early warning system based on an Internet platform, with the following technical solutions:

[0007] a collection module, an Internet platform, at least one inspection module, and a dispatching module;

[0008] The collection module is configured to collect pipeline operation data through at least one sensor arranged on the long-distance pipeline network;

[0009] The Internet platform is used for: performing risk scoring on the pipeline operation data collected by the collection module to obtain a target scoring result, determining a target inspection strategy corresponding to the target scoring result in a scoring result and inspection strategy correspondence relationship according to the target scoring result, and establishing a target scheduling strategy according to the target inspection strategy.

[0010] The scheduling module is used for scheduling the inspection robots in any inspection module according to the target scheduling strategy.

[0011] The long-distance pipeline network danger intelligent early warning system based on the Internet platform has the following beneficial effects:

[0012] Through comprehensive use of the collection module, the Internet platform, the inspection module and the scheduling module, comprehensive monitoring and intelligent management of the oil and gas pipeline are realized. The collection module is distributed on the transportation pipeline and can obtain pipeline operation data in real time and send the data to the Internet platform. The prediction module built in the Internet platform calculates the pipeline risk score according to the real-time monitoring data, ensuring the accuracy of risk assessment. The early warning module dynamically adjusts the inspection strategy according to the risk score, intelligently determines the scheduling strategy, so that the inspection robots can conduct targeted inspection. The scheduling module optimizes the scheduling of the inspection robots according to the scheduling strategy, improving the utilization efficiency of the inspection robots. The system has the ability to intelligently adjust the risk assessment model and the inspection strategy according to the pipeline operation state, effectively reduces unnecessary inspection workload, and ensures the rational allocation of inspection resources. Through the above technical means, the safety and reliability of the oil and gas pipeline are significantly improved, potential risks can be discovered and handled in time, the stable operation of the oil and gas pipeline is ensured, and the system has important practical application value.

[0013] On the basis of the above scheme, the application can be further improved as follows.

[0014] Further, the any inspection module is further used for:

[0015] Through the detection device configured on the inspection robot, image data of the abnormal position in the pipeline is obtained in real time, and the image data is uploaded to the Internet platform.

[0016] Further, when the target inspection strategy is to adjust the inspection frequency, the process of establishing the target scheduling strategy according to the target inspection strategy is:

[0017] According to the current inspection frequency, the minimum number of required inspection robots is calculated, and the scheduling strategy is determined according to the minimum number of required inspection robots and a preset demand amount, wherein the preset demand amount is a predicted number of required inspection robots determined according to the historical target inspection strategy.

[0018] Further, the process of determining the scheduling strategy according to the minimum number of inspection robots and the preset number of robots is specifically:

[0019] When the minimum number of inspection robots is greater than the preset number of robots, robots with a number equal to the difference between the minimum number of inspection robots and the preset number of robots are called from the target inspection module closest to the inspection module.

[0020] 2) In a second aspect, the present application further provides an intelligent early warning method for long-distance pipeline network based on an Internet platform, and the specific technical solutions are as follows:

[0021] The pipeline operation data are collected through at least one sensor arranged on the pipeline of the long-distance pipeline network;

[0022] The pipeline operation data collected by the collection module are scored to obtain a target score result, the target inspection strategy corresponding to the target score result is determined in a corresponding relationship between score results and inspection strategies according to the target score result, and a target scheduling strategy is established according to the target inspection strategy.

[0023] The inspection robots in any inspection module are scheduled according to the target scheduling strategy.

[0024] On the basis of the above-mentioned solutions, the present application can be further improved as follows.

[0025] Further, the method further comprises:

[0026] The image data of the abnormal position in the pipeline are obtained in real time through the detection device arranged on the inspection robot, and the image data are uploaded to the Internet platform.

[0027] Further, when the target inspection strategy is to adjust the inspection frequency, the process of establishing the target scheduling strategy according to the target inspection strategy is:

[0028] The minimum number of inspection robots is calculated according to the current inspection frequency, and the scheduling strategy is determined according to the minimum number of inspection robots and a preset number of robots, wherein the preset number of robots is a predicted number of inspection robots determined according to a historical target inspection strategy.

[0029] Further, the process of determining the scheduling strategy according to the minimum number of inspection robots and the preset number of robots is specifically:

[0030] When the minimum number of inspection robots is greater than the preset number of robots, robots with a number equal to the difference between the minimum number of inspection robots and the preset number of robots are called from the target inspection module closest to the inspection module.

[0031] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor, wherein the processor is coupled to a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor so that the electronic device implements any of the above methods.

[0032] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor to enable a computer to implement any of the above methods.

[0033] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0035] Figure 1 This is one of the structural framework diagrams of an Internet-based long-distance pipeline network hazard intelligent early warning system according to an embodiment of the present invention;

[0036] Figure 2 This is the second structural framework diagram of an Internet-based long-distance pipeline network hazard intelligent early warning system according to an embodiment of the present invention;

[0037] Figure 3 This is a flow chart of an intelligent early warning method for dangers in a long-distance pipeline network based on an Internet platform according to an embodiment of the present invention;

[0038] Figure 4 This is a structural framework diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0039] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0040] like Figure 1 as well as Figure 2 As shown, an intelligent early warning system for long-distance pipeline network dangers based on an Internet platform according to an embodiment of the present invention includes the following devices:

[0041] Collection module, Internet platform, at least one inspection module and scheduling module;

[0042] The collection module is used for collecting pipeline operation data through at least one sensor arranged on the pipeline of the long-distance pipeline network.

[0043] The internet platform is used for performing risk scoring on the pipeline operation data collected by the collection module to obtain a target scoring result, determining a target inspection strategy corresponding to the target scoring result in a scoring result-inspection strategy correspondence relationship according to the target scoring result, and establishing a target scheduling strategy according to the target inspection strategy.

[0044] The scheduling module is used for scheduling the inspection robot in any inspection module according to the target scheduling strategy.

[0045] The long-distance pipeline network danger intelligent early warning system based on the internet platform has the following beneficial effects:

[0046] The collection module, the internet platform, the inspection module and the scheduling module are comprehensively used to realize comprehensive monitoring and intelligent management of the oil and gas pipeline. The collection module is arranged on the transportation pipeline and can obtain pipeline operation data in real time and send the data to the internet platform. The prediction module built in the internet platform calculates the pipeline risk score according to the real-time monitoring data, ensuring the accuracy of risk assessment. The early warning module dynamically adjusts the inspection strategy according to the risk score, intelligently determines the scheduling strategy, so that the inspection robot can be targeted for inspection. The scheduling module optimizes the scheduling of the inspection robot according to the scheduling strategy, improving the utilization efficiency of the inspection robot. The system has the ability to intelligently adjust the risk assessment model and the inspection strategy according to the pipeline operation state, effectively reduces unnecessary inspection workload, and ensures the rational allocation of inspection resources. Through the above technical means, the safety and reliability of the oil and gas pipeline are significantly improved, potential risks can be discovered and handled in time, the stable operation of the oil and gas pipeline is ensured, and the system has important practical application value.

[0047] The collection module collects pipeline operation data through sensors arranged at key positions of each pipeline of the long-distance pipeline network, wherein the key positions include but are not limited to the starting point, the intermediate point, the terminal point and the station of the pipeline. The sensors include but are not limited to pressure sensors, temperature sensors, vibration sensors and flow sensors. The pipeline operation data includes but is not limited to the pressure value, the temperature value, the vibration frequency and the flow value of the station entrance and exit, the pressure value, the temperature value and the flow value of a certain section of the pipeline, etc. The collected pipeline operation data is transmitted to the internet platform through wired or wireless network data transmission.

[0048] The internet platform scores the pipeline operation data collected by the collection module through a built-in prediction module, and outputs a target score result to the scheduling module. The early warning module also determines an inspection strategy according to the pipeline risk score, and determines a scheduling strategy according to the inspection strategy; that is, the inspection strategy and the scheduling strategy are determined according to the risk score.

[0049] Specifically, the pipeline risk score is calculated, specifically including:

[0050] Suppose two adjacent collection modules M i and M i+1 collect the following data respectively:

[0051] P i , T i , V i , F i respectively represent the pressure, temperature, vibration, and flow data of module M i ;

[0052] P i+1 , T i+1 , V i+1 , F i+1 respectively represent the pressure, temperature, vibration, and flow data of module M i+1 ;

[0053] The absolute value of the difference value of the same type of data of the two adjacent collection modules is calculated, and the absolute value of the difference value reflects the change of the pipeline in this section:

[0054] ΔP = |P i -P i+1 |

[0055] ΔT = |T i -T i+1 |

[0056] ΔV = |V i -V i+1 |

[0057] ΔF = |F i -F i+1 |

[0058] The absolute value of the difference value is standardized:

[0059]

[0060] Wherein, P max , T max , V max , F max respectively represent the maximum value of the normal range of pipeline pressure, temperature, vibration, and flow;

[0061] Set the weight ω P ,ω T ,ω V ,ω F respectively represent the contribution weight of pressure, temperature, vibration, flow to the risk of failure, then the risk score R i,i+1 is calculated as follows:

[0062] R i,i+1 = K(ω P ·ΔP'+ω T ·ΔT'+ω V ·ΔV'+ω F ·ΔF')

[0063] Where K represents an adjustment factor, used to correct the calculation of the risk score according to the actual historical risk of failure.

[0064] The warning module divides the risk score into different levels:

[0065] The first risk level (low risk), the pipeline is running normally, no obvious abnormality. Take the strategy of adjusting the inspection frequency, increase or decrease the number of inspections to ensure the safety of the pipeline;

[0066] The second risk level (high risk), there is potential risk in the pipeline, which needs to be quickly inspected. Take the strategy of quick inspection, immediately arrange the inspection robot to conduct detailed inspection.

[0067] For example: select a long pipeline for field test. The pipeline is 100 kilometers long, and there are 10 collection modules set every 10 kilometers. Each collection module collects pipeline operation data in real time and transmits it to the Internet platform.

[0068] The collection module is installed on the pipeline and collects 120 data per minute. The collected data includes pressure, temperature, vibration and flow, and is transmitted to the Internet platform through wireless network. After receiving the data, the Internet platform calculates the pipeline risk score according to the above formula. Assume that at a certain time, the data collected by collection modules M1 and M2 are as follows:

[0069] P1 = 50 MPa, T1 = 30℃, V1 = 0.2 m / s, F1 = 100 m 3 / s

[0070] P2 = 48 MPa, T2 = 32℃, V2 = 0.25 m / s, F2 = 95 m 3 / s

[0071] Calculate the absolute value of the data difference:

[0072] ΔP = |50-48| = 2 MPa

[0073] ΔT = |30 - 32| = 2 °C

[0074] ΔV = |0.2 - 0.25| = 0.05 m / s

[0075] ΔF = |100 - 95| = 5 m 3 / s

[0076] Suppose the maximum values of the normal ranges of pressure, temperature, vibration, and flow rate are as follows:

[0077] P max = 100 MPa, T max = 100 °C, V max = 1 m / s, F max = 200 m 3 / s

[0078] Standardized difference:

[0079]

[0080] Set weights:

[0081] ω P = 0.4, ω T = 0.3, ω V = 0.2, ω F = 0.1

[0082] Adjustment factor K = 1.5;

[0083] Then the risk score is calculated as follows:

[0084] R 1,2 = 1.5 (0.4 · 0.02 + 0.3 · 0.02 + 0.2 · 0.05 + 0.1 · 0.025) = 0.046875.

[0085] More specifically, a scoring correction model is established by combining multiple deep learning models, and the adjustment factor K is adjusted according to the data output of the acquisition module as follows:

[0086] Collect historical failure data, including specific circumstances of failure occurrence and various types of data from the acquisition module. Preprocess and extract features from the collected data. Normalize or standardize the data to ensure that the numerical range of the input data is suitable for deep learning models. Select multiple deep learning models, including convolutional neural networks, recurrent neural networks, and feedforward neural networks, to establish a scoring correction model. Combine the strengths of different models to improve the accuracy of the prediction. Convolutional Neural Network (CNN): Extract local features from the data, suitable for processing local patterns in time series data. Recurrent Neural Network (RNN): Process sequential data and capture temporal dependencies in the data. Feedforward Neural Network (FNN): Combine features from CNN and RNN for comprehensive processing and output the final adjustment factor K.

[0087] Specific steps:

[0088] Input layer: Input various types of data from the acquisition module (pressure, temperature, vibration, flow, etc.).

[0089] Convolutional layer (CNN): Perform convolution operations on input data using multiple convolution kernels to extract local features.

[0090] Pooling layer (CNN): Reduce the dimensionality of the data through max pooling or average pooling to retain important features.

[0091] Recurrent layer (RNN): Process pooled features using RNN (such as LSTM or GRU) to capture temporal dependencies.

[0092] Fully connected layer (FNN): Connect features from CNN and RNN to the fully connected layer for further feature extraction and processing.

[0093] Output layer: Output the adjustment factor K.

[0094] The introduction of the adjustment factor K significantly improves the accuracy and practicality of risk score prediction. This adjustment factor is modified based on actual historical failure risk data, mainly in the following aspects: First, the adjustment factor K can dynamically adjust the algorithm for calculating the risk score in the prediction module according to the specific operation of the pipeline and historical failure records. By considering the actual operation data and past failure experience of the pipeline, the introduction of the adjustment factor K makes the risk assessment more accurate and real-time, and can more accurately reflect the current safety status of the pipeline. Second, the adjustment factor K can also balance the influence weight of different factors during risk assessment, and adjust the importance of each parameter according to the specific situation. This dynamic adjustment capability makes the system more flexible and adaptable, and can cope with different pipeline conditions and environmental changes, improving the applicability and universality of the prediction model. In addition, the introduction of the adjustment factor K also improves the warning accuracy and timeliness of the system. By real-time monitoring and analysis of historical data, the system can timely discover potential risk points and problems, and take effective measures for prevention and repair in advance, thereby effectively reducing the possibility of pipeline accidents and ensuring the safety and stability of pipeline operation. Therefore, the application of the adjustment factor K in the long-distance pipeline network risk intelligent early warning system based on the Internet platform not only optimizes the risk assessment algorithm and model, but also improves the response speed and decision-making accuracy of the system, providing important technical support and guarantee for pipeline operation management.

[0095] Assume that the risk level is divided into two levels:

[0096] First risk level (score <0.08): the inspection strategy is to adjust the inspection frequency.

[0097] Second risk level (score ≥0.08): the inspection strategy is rapid inspection.

[0098] Further subdivide the risk level, and determine the inspection strategy according to the pipeline risk score:

[0099] If the risk score is greater than 0.07, increase the inspection frequency.

[0100] If the risk score is between 0.05 and 0.07, maintain the original inspection frequency.

[0101] If the risk score is less than or equal to 0.05, reduce the inspection frequency.

[0102] In this example, the risk score is 0.046875, which belongs to the first risk level, but since the score is less than 0.05, the inspection strategy is to reduce the inspection frequency.

[0103] More specifically, in this embodiment, the system triggers the rapid inspection strategy when the pipeline's risk score reaches or exceeds the second risk level (score ≥ 0.08). To improve inspection efficiency, the Internet platform will further predict the fault location, and the inspection robot will directly go to the predicted fault location for inspection. Rapid inspection strategy trigger: Assuming that at a certain moment, the pipeline operation data received by the Internet platform is analyzed, and the calculated risk score is 0.09, which exceeds the trigger threshold of rapid inspection 0.08. At this time, the system automatically starts the rapid inspection strategy. Fault location prediction: The prediction module of the Internet platform predicts the fault location. Assume that the model predicts the fault location to be the 45th kilometer of the pipeline. Inspection robot scheduling: Once the prediction module determines the fault location, the scheduling module of the Internet platform directs the inspection robot to the predicted fault location according to the inspection strategy. Robot selection: Select available inspection robots from the nearest inspection modules. For example, the inspection modules at the 40th kilometer and the 55th kilometer each have two inspection robots, and the system selects the closest robot to the 45th kilometer for scheduling. Path planning: The system calculates the optimal path to enable the inspection robot to quickly and safely reach the predicted fault location. Task assignment: The scheduling module sends task instructions to the selected inspection robot, and the robot receives the instructions and immediately goes to the target location. After the inspection robot arrives at the predicted fault location, it performs the following tasks: On-site detection: Use a variety of sensors (such as ultrasonic, infrared imaging, high-definition camera, etc.) for detailed on-site detection to collect more environmental and state data. Fault confirmation: Further confirm whether there is a fault through the data of on-site detection. If there is indeed a fault, record the specific type, severity and location of the fault. Data upload: The inspection robot uploads the detection data and fault report to the Internet platform in real time for subsequent processing and decision-making reference. After receiving the report of the inspection robot, the Internet platform analyzes and confirms the fault condition, and generates a detailed fault report containing information such as the specific location, fault type and severity. According to the fault report, the system automatically triggers the corresponding emergency response measures, such as notifying the maintenance team and starting the emergency repair procedure, to ensure the rapid repair and safe operation of the pipeline.

[0104] Through this rapid inspection strategy and fault location prediction, the system can quickly respond to high-risk situations, accurately locate potential fault points, and significantly improve inspection efficiency and pipeline safety. The inspection robot directly goes to the predicted fault location, not only shortening the response time, but also reducing the workload of comprehensive inspection, optimizing resource use, and improving the overall maintenance and management level of the long-distance pipeline network.

[0105] The scheduling strategy is determined according to the inspection strategy, and the specific process further includes:

[0106] If the inspection strategy is to adjust the inspection frequency, calculate the minimum demand quantity of the inspection robot of the inspection module according to the inspection frequency, and determine the scheduling strategy according to the minimum demand quantity and the preset quantity.

[0107] In another embodiment of the present scheme, the scheduling strategy is determined according to the minimum demand quantity and the preset quantity, and the specific process further comprises:

[0108] If the minimum demand quantity is greater than the preset quantity, calculate the difference between the minimum demand quantity and the preset quantity, and the scheduling strategy is to schedule the difference quantity of inspection robots from the inspection module closest to the inspection module and the preset quantity greater than the minimum demand quantity.

[0109] The scheduling module schedules the inspection robots according to the inspection strategy. Assuming that 2 inspection robots are configured per 10 kilometers, if the score is greater than 0.07, the inspection frequency will be increased and additional robots will be scheduled to the high-risk area.

[0110] Specifically, in order to effectively manage and schedule inspection robots to meet the facility inspection demand, the following specific embodiments are designed to cope with demand changes and strategy execution under different circumstances:

[0111] 1. Preliminary determination of inspection strategy and scheduling strategy

[0112] First, according to the characteristics and inspection demand of the facility, the inspection strategy is formulated. The core of the inspection strategy includes determining the inspection frequency and the distribution of the inspection module. While determining the inspection frequency, the minimum number of inspection robots required for each inspection module (hereinafter referred to as the minimum demand quantity) needs to be calculated.

[0113] 2. Calculate the minimum demand quantity and the preset quantity

[0114] For each inspection module, according to the set inspection frequency, the minimum number of inspection robots required for the module is calculated. This step involves determining the specific number according to the size of the facility, the inspection target, and the expected inspection efficiency. Assuming there are several inspection modules, the minimum demand quantity of each module has been calculated.

[0115] At the same time, the preset quantity of each inspection module is set, i.e. the ideal number of inspection robots each module should have.

[0116] 3. Determine the scheduling strategy

[0117] Case 1: Minimum demand quantity is less than or equal to preset quantity

[0118] In this case, the scheduling strategy is relatively simple, only need to keep the number of inspection robots of each inspection module equal to the preset quantity. This can ensure the normal operation of each module under the inspection frequency.

[0119] Case Two: Minimum demand quantity is greater than preset quantity

[0120] When the minimum demand quantity is greater than the preset quantity, it indicates that the inspection demand of some inspection modules exceeds the expectation. In this case, the following specific measures need to be taken:

[0121] Calculate the difference: For each inspection module, calculate the difference between the minimum demand quantity and the preset quantity.

[0122] Prioritize scheduling: From those inspection modules closest to the inspection module and with a preset quantity greater than the minimum demand quantity, prioritize scheduling the difference quantity of inspection robots.

[0123] For example, assume that in module A, the minimum demand quantity is 5 robots and the preset quantity is 3. Then the difference is 2 robots. And in module B, the minimum demand quantity is 4 robots and the preset quantity is 6, which can schedule 2 robots to other inspection modules.

[0124] Therefore, according to the above case, 2 additional robots will be scheduled from module B to module A to ensure that the module can be inspected as required. No additional robots are needed in module B because its preset quantity is sufficient to meet the minimum demand quantity.

[0125] Specifically, after receiving the scheduling instruction, the scheduling drone quickly loads the inspection robot and flies from module B to module A. The scheduling drone uses automatic flight path planning technology to avoid obstacles and reach the destination as quickly as possible. Upon arrival at the high-risk area, the scheduling drone safely lands at the designated location, and the inspection robot immediately begins work, conducting a comprehensive inspection.

[0126] Through the above specific examples of scheduling strategies, the allocation of inspection robots can be effectively managed to ensure the safety and efficiency of the facility. This strategy not only meets the changing inspection needs, but also optimizes the allocation and utilization of resources in the case of limited resources.

[0127] The scheduling module is used to schedule the inspection robots according to the scheduling strategy.

[0128] Specifically, the scheduling module schedules and manages the work of the inspection robots according to the scheduling strategy generated by the warning module. The scheduling module considers the location, state and work tasks of the inspection robots, and reasonably allocates inspection tasks to ensure efficient inspection work.

[0129] The inspection module is provided with a preset number of inspection robots for inspection according to the inspection strategy;

[0130] Specifically, the inspection module is provided with a plurality of inspection robots, which have autonomous navigation and intelligent detection functions. The inspection robots perform inspection work according to the inspection strategy provided by the early warning module. The robots are equipped with high-definition cameras, ultrasonic detectors and infrared thermal imagers, which can detect defects in the appearance of the pipeline, internal corrosion and leakage and other problems. The inspection data is uploaded to the Internet platform in real time for further analysis and processing.

[0131] According to the inspection strategy, a scheduling strategy is determined, and the specific process further includes:

[0132] If the inspection strategy is to adjust the inspection frequency, the minimum demand quantity of the inspection robots of the inspection module is calculated according to the inspection frequency, and the scheduling strategy is determined according to the minimum demand quantity and the preset quantity.

[0133] According to the minimum demand quantity and the preset quantity, a scheduling strategy is determined, and the specific process further includes:

[0134] If the minimum demand quantity is greater than the preset quantity, the difference between the minimum demand quantity and the preset quantity is calculated, and the scheduling strategy is to dispatch the difference quantity of inspection robots from the inspection module closest to the inspection module and having the preset quantity greater than the minimum demand quantity.

[0135] Specifically, according to the inspection strategy, the early warning module formulates a scheduling strategy:

[0136] If the inspection strategy is to adjust the inspection frequency, the early warning module calculates the minimum demand quantity of the inspection robots, and determines the scheduling strategy according to the preset quantity.

[0137] If the minimum demand quantity is greater than the preset quantity, the early warning module calculates the difference, and dispatches robots from the inspection module closest to the inspection module and having sufficient robot quantity to make up the demand quantity.

[0138] The scheduling module reasonably allocates the inspection tasks according to the scheduling strategy. The inspection robots perform autonomous navigation and detection work according to the scheduling instructions. The robots are equipped with high-definition cameras, ultrasonic detectors and infrared thermal imagers, which can detect defects in the appearance of the pipeline, internal corrosion and leakage and other problems. During the inspection process, the robots upload the detected data to the Internet platform in real time. The Internet platform analyzes and processes the inspection data, and if an abnormality is found, updates the risk score in time and formulates new inspection and scheduling strategies. The entire system ensures the safe operation of the pipeline through continuous data collection, analysis and feedback.

[0139] The internet platform-based long-distance pipeline network danger intelligent early warning system of the embodiment can realize real-time monitoring and risk assessment of the pipeline operation state. Through closed-loop management of data acquisition, analysis and inspection, the system can timely discover and warn potential pipeline risks and prevent accidents. The intelligent scheduling and autonomous inspection functions of the system improve the efficiency and accuracy of inspection work, reduce labor input and management cost, and ensure the safe operation of long-distance pipelines.

[0140] Further, the inspection module is further configured to:

[0141] The detection device configured on the inspection robot is used to acquire image data of the abnormal position in the pipeline in real time, and upload the image data to the internet platform.

[0142] Further, when the target inspection strategy is to adjust the inspection frequency, the process of establishing a target scheduling strategy according to the target inspection strategy is:

[0143] According to the current inspection frequency, the minimum number of required inspection robots is calculated, and a scheduling strategy is determined according to the minimum number of required inspection robots and a preset demand amount, wherein the preset demand amount is a predicted number of required inspection robots determined according to historical target inspection strategies.

[0144] Further, the process of determining a scheduling strategy according to the minimum number of required inspection robots and the preset demand amount is specifically:

[0145] When the minimum number of required inspection robots is greater than the preset demand amount, the number of robots corresponding to the difference between the minimum number of required inspection robots and the preset demand amount is called from the target inspection module closest to the inspection module.

[0146] As shown in Figure 3 The present application also provides an internet platform-based long-distance pipeline network danger intelligent early warning method, and the specific technical solutions are as follows:

[0147] S1, collecting pipeline operation data through at least one sensor arranged on the pipeline of the long-distance pipeline network;

[0148] S2, performing risk scoring on the pipeline operation data collected by the collection module to obtain a target scoring result, determining a target inspection strategy corresponding to the target scoring result in a scoring result-inspection strategy correspondence relationship according to the target scoring result, and establishing a target scheduling strategy according to the target inspection strategy;

[0149] S3, scheduling the inspection robots in any inspection module according to the target scheduling strategy.

[0150] Further, it further comprises:

[0151] The detection device configured on the inspection robot acquires image data of an abnormal position in the pipeline in real time, and uploads the image data to the Internet platform.

[0152] Further, when the target inspection strategy is to adjust the inspection frequency, a process of establishing a target scheduling strategy according to the target inspection strategy is:

[0153] According to the current inspection frequency, the minimum inspection robot requirement is calculated, and a scheduling strategy is determined according to the minimum inspection robot requirement and a preset requirement, wherein the preset requirement is a predicted inspection robot requirement determined according to a historical target inspection strategy.

[0154] Further, the process of determining the scheduling strategy according to the minimum inspection robot requirement and the preset requirement is specifically:

[0155] When the minimum inspection robot requirement is greater than the preset requirement, a robot with a difference between the minimum inspection robot requirement and the preset requirement is called from a target inspection module closest to the inspection module.

[0156] In the above embodiments, although the steps are numbered S1, S2, etc., this is only a specific embodiment of the present application, and those skilled in the art can adjust the execution order of S1, S2, etc. according to the actual situation, which is within the protection scope of the present application. It can be understood that in some embodiments, some or all of the above embodiments can be included.

[0157] It should be noted that the beneficial effects of the long-distance pipeline network danger intelligent early warning method provided in the above embodiments are the same as those of the long-distance pipeline network danger intelligent early warning system provided in the above embodiments, and will not be repeated here. In addition, when the system provided in the above embodiments realizes its function, only the division of the above functional modules is exemplified, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the system is divided into different functional modules according to actual conditions to complete all or part of the above described functions. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0158] As shown in FIG. 3, Figure 4 The electronic device 300 according to an embodiment of the present application includes a processor 320 and a memory 310 coupled to the processor 320. The memory 310 stores at least one computer program 330. The at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above methods. Specifically:

[0159] The electronic device 300 can be quite different due to different configurations or performances, and can include one or more processors 320 (Central Processing Units, CPUs) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements the above-mentioned embodiment of the internet platform-based long-distance pipeline network danger intelligent early warning method. Of course, the electronic device 300 can also have a wired or wireless network interface, a keyboard, an input and output interface and the like, so as to perform input and output, and the electronic device 300 can also include other components for realizing device functions, which will not be described here.

[0160] The computer readable storage medium of the embodiment of the application stores at least one computer program, and the at least one computer program is loaded and executed by the processor, so that the computer implements any one of the above-mentioned methods.

[0161] Optionally, the computer readable storage medium can be a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a read-only compact disc (Compact Disc Read-Only Memory, CD-ROM), a magnetic tape, a floppy disk and an optical data storage device, etc.

[0162] In the exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the electronic device executes any one of the above-mentioned methods.

[0163] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application are used to distinguish similar objects, and represent a specific order or sequence. In appropriate cases, the order of use of similar objects can be interchanged, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described.

[0164] Those skilled in the art know that the present application can be implemented as a system, a method, or a computer program product, therefore, the present disclosure can be embodied in the form of a complete hardware, a complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, which is generally referred to as "circuitry", "module" or "system". In addition, in some embodiments, the present application can also be embodied in the form of a computer program product in one or more computer readable media, which contains computer readable program codes.

[0165] Any combination of one or more computer readable medium can be employed. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0166] Although the embodiments of the present application have been shown and described above, it should be understood that the above-described embodiments are exemplary, and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. An intelligent early warning system for long-distance pipeline network hazards based on the Internet platform, characterized in that: include: Collection module, Internet platform, at least one inspection module and scheduling module; The acquisition module is used to collect pipeline operation data through at least one sensor arranged on a pipeline of the long-distance pipeline network; wherein the pipeline operation data includes pressure, temperature, vibration and flow data; The Internet platform is used to: perform risk scoring on the pipeline operation data collected by the collection module to obtain a target scoring result; determine, based on the target scoring result, a target inspection strategy corresponding to the target scoring result in a correspondence between the scoring result and the inspection strategy; and establish a target scheduling strategy based on the target inspection strategy; The scheduling module is used to schedule the inspection robot in any inspection module according to the target scheduling strategy; The risk score of the pipeline operation data collected by the acquisition module is calculated, specifically including: calculating the risk score of the pipeline section between two adjacent acquisition modules, where the two adjacent acquisition modules are M i and M i+1 , collect the following data: P i ,T i ,V i ,F i , P i+1 ,T i+1 ,V i+1 ,F i+1 ; P i ,T i ,V i ,F i Respectively represent the acquisition module M i Pressure, temperature, vibration, and flow data; P i+1 ,T i+1 ,V i+1 ,F i+1 Respectively represent adjacent acquisition modules M i+1 Pressure, temperature, vibration, and flow data; Calculate the absolute value of the difference between the same type of data of two adjacent acquisition modules. The absolute value of the difference reflects the data changes in the pipeline section between the two adjacent acquisition modules: ΔP=|P i -P i+1 |; ΔT=|T i -T i+1 |; ΔV=|V i -V i+1 |; ΔF=|F i -F i+1 |; ΔP represents the absolute value of the pressure difference between two adjacent acquisition modules, ΔT represents the absolute value of the temperature difference between two adjacent acquisition modules, ΔV represents the absolute value of the vibration difference between two adjacent acquisition modules, and ΔF represents the absolute value of the flow difference between two adjacent acquisition modules; Normalize the absolute value of the difference: Among them, ΔP′ is the standardized value of the absolute value of the pressure difference, ΔT′ is the standardized value of the absolute value of the temperature difference, ΔV′ is the standardized value of the absolute value of the vibration difference, ΔF′ is the standardized value of the absolute value of the flow difference, P max ,T max ,V max ,F max Respectively represent the maximum values ​​of normal ranges of pipeline pressure, temperature, vibration and flow; Set weight ω P ,ω T ,ω V ,ω F They represent the contribution weights of pressure, temperature, vibration, and flow to the failure risk, respectively. The risk score R i,i+1 The calculation of is as follows: R i,i+1 =K(ω P ·ΔP'+ω T ·ΔT'+ω V ·ΔV'+ω F ·ΔF'); Where K represents the adjustment factor, which is used to correct the calculation of the risk score based on the actual historical failure risk; ω P =0.4ω T =0.3ω V =0.2ω F =0.1, K=1.5; Risk score <0.08: The inspection strategy is to adjust the inspection frequency; Risk score ≥ 0.08: The inspection strategy is fast inspection.

2. The intelligent early warning system for long-distance pipeline network danger based on the Internet platform according to claim 1 is characterized in that: Any of the inspection modules is further configured to: The detection device configured on the inspection robot is used to obtain image data at abnormal positions inside the pipeline in real time, and the image data is uploaded to the Internet platform.

3. The intelligent early warning system for long-distance pipeline network danger based on the Internet platform according to claim 1 is characterized in that: When the target inspection strategy is to adjust the inspection frequency, the process of establishing the target scheduling strategy according to the target inspection strategy is as follows: According to the current inspection frequency, the minimum inspection robot demand is calculated, and the scheduling strategy is determined according to the minimum inspection robot demand and the preset demand, where the preset demand is the estimated inspection robot demand determined according to the historical target inspection strategy.

4. The intelligent early warning system for long-distance pipeline network danger based on the Internet platform according to claim 3 is characterized in that: The process of determining the scheduling strategy based on the minimum inspection robot demand and the preset demand is as follows: When the minimum inspection robot demand is greater than the preset demand, a robot having a difference between the minimum inspection robot demand and the preset demand is retrieved from the target inspection module closest to the inspection module.

5. An intelligent early warning method for long-distance pipeline network danger based on an Internet platform, using the intelligent early warning system for long-distance pipeline network danger based on an Internet platform as claimed in claim 1, characterized in that: The method includes: Collecting pipeline operation data through at least one sensor arranged on a pipeline of a long-distance pipeline network; Performing risk scoring on pipeline operation data to obtain a target scoring result, determining a target inspection strategy corresponding to the target scoring result in a correspondence between the scoring result and the inspection strategy, and establishing a target scheduling strategy based on the target inspection strategy; The inspection robot in any inspection module is scheduled according to the target scheduling strategy.

6. The method for intelligent early warning of danger in long-distance pipeline network based on the Internet platform according to claim 5 is characterized in that: Also includes: The detection device configured on the inspection robot is used to obtain image data at abnormal positions inside the pipeline in real time, and the image data is uploaded to the Internet platform.

7. The method for intelligent early warning of danger in long-distance pipeline network based on the Internet platform according to claim 5 is characterized in that: When the target inspection strategy is to adjust the inspection frequency, the process of establishing the target scheduling strategy according to the target inspection strategy is as follows: According to the current inspection frequency, the minimum inspection robot demand is calculated, and the scheduling strategy is determined according to the minimum inspection robot demand and the preset demand, where the preset demand is the estimated inspection robot demand determined according to the historical target inspection strategy.

8. The method for intelligent early warning of danger in long-distance pipeline network based on the Internet platform according to claim 7 is characterized in that: The process of determining the scheduling strategy based on the minimum inspection robot demand and the preset demand is as follows: When the minimum inspection robot demand is greater than the preset demand, a robot having a difference between the minimum inspection robot demand and the preset demand is retrieved from the target inspection module closest to the inspection module.

9. An electronic device, characterized in that: The electronic device includes a processor coupled to a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the method according to any one of claims 5 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to enable a computer to implement the method according to any one of claims 5 to 8.

Images