Risk perception test system and method for oil and gas pipeline
By setting up distributed fiber sensors in the target area of the oil and gas pipeline, obtaining sample data of abnormal events and training a risk perception model, the problem of low accuracy of the risk perception model in the existing technology is solved, and the safe and efficient operation of the oil and gas pipeline is achieved.
Patent Information
- Application Number
- CN202411269984.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-11
- Publication Date
- 2025-02-11
AI Technical Summary
In the prior art, the risk perception model of oil and gas pipelines is low in accuracy and cannot meet the risk perception requirements of oil and gas pipelines. It is mainly because the amount of abnormal sample data in the training samples is small, and it is impossible to fully and truly reflect abnormal events in the pipeline operation.
By setting up a distributed fiber sensor in the target area, obtaining sample data of different types of abnormal events, and preprocessing and training the data through the processor, a neural network model is established to improve the accuracy of the risk perception model.
It realizes accurate and rapid acquisition of sample data of abnormal events in oil and gas pipelines, improves the accuracy of the risk perception model, meets the risk perception requirements of oil and gas pipelines, and ensures the safe operation of oil and gas pipelines.
Smart Images
Figure CN119416103A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of oil and gas pipeline risk perception, and in particular to a risk perception testing system and method for oil and gas pipelines. Background Art
[0002] The safe and stable operation of oil and gas pipelines is related to the safety of energy transportation. Once a safety accident occurs, it will threaten people's personal safety, cause huge economic losses, and have serious negative impacts. Today, the monitoring and early warning capabilities of oil and gas pipelines are still imperfect, and the risk perception, monitoring and early warning capabilities during pipeline production and operation still need to be further improved.
[0003] At present, sensors are usually used to monitor and warn oil and gas pipelines. Before using sensors to monitor oil and gas pipelines, a corresponding risk perception model needs to be built. The risk perception model is used to make risk judgments based on the data obtained by the sensors. In related technologies, since oil and gas pipelines are usually in operation, some types of abnormal events often cause the oil and gas pipelines to stop operating (such as geological subsidence events). It is difficult to obtain abnormal samples of oil and gas pipelines. Therefore, the amount of abnormal samples in the training samples is small, resulting in the training samples not being able to fully and truly reflect the abnormal events in the pipeline operation, which in turn leads to the low accuracy of the risk perception model obtained through training, which cannot meet the risk perception requirements of oil and gas pipelines. Summary of the invention
[0004] The embodiment of the present invention provides a risk perception testing system and method for an oil and gas pipeline, which can accurately and quickly obtain sample data corresponding to different abnormal events in the oil and gas pipeline, and train the risk perception model through the sample data, thereby improving the accuracy of the risk perception model, meeting the risk perception requirements of the oil and gas pipeline, and realizing the safe operation of the oil and gas pipeline.
[0005] To achieve the above object, the embodiments of the present invention adopt the following technical solutions:
[0006] In a first aspect, a risk perception test system for an oil and gas pipeline is provided, the system comprising a distributed optical fiber sensor and a processor, the distributed optical fiber sensor being connected to the processor, the distributed optical fiber sensor being arranged in a target area, the target area having the same geomorphic features as the area in which the target oil and gas pipeline is arranged; the distributed optical fiber sensor being used for: responding to different types of abnormal events conducted by a user in the target area, acquiring time series data of a target parameter corresponding to each abnormal event, and sending the time series data of the target parameter corresponding to each abnormal event to the processor, the target parameter comprising vibration intensity, temperature or stress; the processor being used for: processing the time series data of the target parameter corresponding to each abnormal event to obtain a training sample set, the training sample set comprising a plurality of training samples; training a neural network model through the training sample set to obtain a trained risk perception model, the risk perception model being used for outputting a risk perception result corresponding to the target oil and gas pipeline according to the input time series data of the target parameter of the target oil and gas pipeline.
[0007] In a possible implementation of the first aspect, the types of abnormal events include manual excavation operations, mechanical excavation operations and geological settlement operations, and the target area also includes a vibration test area and a stress test area; the distributed optical fiber sensor is specifically used to: respond to manual excavation operations or mechanical excavation operations performed by a user in the vibration test area, obtain time series data of target parameters corresponding to the manual excavation operations or mechanical excavation operations; respond to simulated settlement operations performed by a user in the stress test area, obtain time series data of target parameters corresponding to the simulated settlement operations.
[0008] In a possible implementation of the first aspect, when the processor is used to process the time series data of the target parameter corresponding to each abnormal event to obtain a training sample set, the processor is specifically used to: determine the abnormal event identifier corresponding to the time series data of the target parameter corresponding to each abnormal event; delete the abnormal values in the time series data of the target parameter corresponding to each abnormal event based on the Gaussian distribution 3σ law; perform noise filtering on the time series data of the target parameter corresponding to each abnormal event; perform zero-mean normalization on the time series data of the target parameter corresponding to each abnormal event to obtain preprocessed data; determine the frequency domain data of the target parameter corresponding to each abnormal event based on the preprocessed data; determine the waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event; obtain multiple training samples based on the waterfall chart of the target parameter corresponding to each abnormal event and the abnormal event identifier; and obtain a training sample set based on the multiple training samples.
[0009] In a possible implementation of the first aspect, when the processor is used to determine a waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event, the processor is specifically used to: stack the frequency domain data of the target parameter corresponding to each abnormal event to obtain a two-dimensional matrix for displaying time progression; map the two-dimensional matrix to a preset range through a maximum-minimum normalization method to obtain a waterfall chart of the target parameter corresponding to each abnormal event.
[0010] In a possible implementation of the first aspect, the target area also includes multiple ball drop test areas, each of which is at a different distance from the distributed optical fiber sensor; the distributed optical fiber sensor is also used to: respond to the ball drop operation performed by the user in each ball drop test area, obtain vibration data corresponding to each ball drop operation, the vibration data including time series data of vibration intensity; send the vibration data corresponding to each ball drop operation to the processor; the processor is also used to determine the vibration sensitivity of the distributed optical fiber sensor based on the vibration data corresponding to each ball drop operation.
[0011] In a possible implementation of the first aspect, the target area also includes a temperature test area, the temperature test area is provided with a heating device and a plurality of soil temperature sensors, and the plurality of soil temperature sensors are connected to a processor; the distributed optical fiber sensor is further used to: when the heating device is started, obtain first temperature data corresponding to the temperature test area, the first temperature data including time series data of the temperature; send the first temperature data to the processor; the processor is further used to: obtain second temperature data, the second temperature data being time series data of the temperature corresponding to the temperature test area obtained by each of the plurality of soil temperature sensors; and determine the temperature sensitivity, structural temperature conduction distance, maximum monitoring distance and positioning accuracy of the distributed optical fiber sensor according to the first temperature data and the second temperature data.
[0012] The beneficial effects of the present invention are as follows: the present invention uses distributed optical fiber sensors set in the target area. Since the geomorphic features of the target area are the same as the geomorphic features of the area where the oil and gas pipeline is set in operation, the distributed optical fiber sensors are used to obtain abnormal events in the target area, and the sample data corresponding to different abnormal events of the oil and gas pipeline in operation can be accurately and quickly obtained. The risk perception model is trained through the sample data, thereby improving the accuracy of the risk perception model, meeting the risk perception requirements of the oil and gas pipeline, and realizing the safe operation of the oil and gas pipeline. And the process of obtaining sample data will not affect the normal operation of the oil and gas pipeline. That is to say, the system provided by the present invention can test the performance indicators of the abnormal event perception system of the oil and gas pipeline, and can also simulate abnormal events such as artificial excavation, mechanical damage, geological disasters, etc., develop a risk perception model for the oil and gas pipeline, and guide the identification and control of abnormal events in the oil and gas pipeline.
[0013] In a second aspect, an embodiment of the present invention provides a risk perception test method for an oil and gas pipeline, which is applied to a risk perception test system, wherein the system includes a distributed optical fiber sensor and a processor, wherein the distributed optical fiber sensor is connected to the processor, and the distributed optical fiber sensor is arranged in a target area, and the target area and the setting area of the target oil and gas pipeline have the same geomorphic features; the above method includes: the distributed optical fiber sensor responds to different types of abnormal events performed by the user in the target area, and obtains time series data of target parameters corresponding to each abnormal event; the distributed optical fiber sensor sends the time series data of the target parameters corresponding to each abnormal event to the processor, and the target parameters include vibration intensity, temperature or stress; the processor processes the time series data of the target parameters corresponding to each abnormal event to obtain a training sample set, and the training sample set includes multiple training samples; the processor trains a neural network model through the training sample set to obtain a trained risk perception model, and the risk perception model is used to output the risk perception result corresponding to the target oil and gas pipeline according to the input time series data of the target parameters of the target oil and gas pipeline.
[0014] In a possible implementation of the second aspect, the types of abnormal events include manual excavation operations, mechanical excavation operations, and geological settlement operations, and the target area also includes a vibration test area and a stress test area; the distributed optical fiber sensor responds to different types of abnormal events performed by the user in the target area, and obtains time series data of target parameters corresponding to each abnormal event, including: the distributed optical fiber sensor responds to the manual excavation operation or mechanical excavation operation performed by the user in the vibration test area, and obtains time series data of target parameters corresponding to the manual excavation operation or mechanical excavation operation; the distributed optical fiber sensor responds to the simulated settlement operation performed by the user in the stress test area, and obtains time series data of target parameters corresponding to the simulated settlement operation.
[0015] In a possible implementation of the second aspect, the processor processes the time series data of the target parameter corresponding to each abnormal event to obtain a training sample set, including: the processor determines the abnormal event identifier corresponding to the time series data of the target parameter corresponding to each abnormal event; the processor deletes the abnormal values in the time series data of the target parameter corresponding to each abnormal event based on the Gaussian distribution 3σ law; the processor performs noise filtering on the time series data of the target parameter corresponding to each abnormal event; the processor performs zero-mean normalization processing on the time series data of the target parameter corresponding to each abnormal event to obtain preprocessed data; the processor determines the frequency domain data of the target parameter corresponding to each abnormal event based on the preprocessed data; the processor determines the waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event; the processor obtains multiple training samples based on the waterfall chart of the target parameter corresponding to each abnormal event and the abnormal event identifier; the processor obtains a training sample set based on the multiple training samples.
[0016] In a possible implementation of the second aspect, the processor determines a waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event, including: the processor stacks the frequency domain data of the target parameter corresponding to each abnormal event to obtain a two-dimensional matrix for displaying time progression; the processor maps the two-dimensional matrix to a preset range through a maximum-minimum normalization method to obtain a waterfall chart of the target parameter corresponding to each abnormal event.
[0017] It can be understood that the beneficial effects that can be achieved by the risk perception testing method for oil and gas pipelines of the second aspect provided above can be referred to the beneficial effects in the first aspect and any possible design thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 A schematic diagram of setting a risk perception test system provided by an embodiment of the present invention is shown;
[0019] Figure 2 A schematic diagram showing the configuration of another risk perception testing system provided by an embodiment of the present invention is shown;
[0020] Figure 3 A schematic diagram showing the configuration of another risk perception testing system provided by an embodiment of the present invention is shown;
[0021] Figure 4 A schematic diagram of setting a temperature test area according to an embodiment of the present invention;
[0022] Figure 5 The present invention is a flowchart of a risk perception testing method for an oil and gas pipeline shown in an embodiment of the present invention. DETAILED DESCRIPTION
[0023] The technical solution in the embodiment of the present invention will be described below in conjunction with the accompanying drawings in the embodiment of the present invention. Among them, in the description of the present invention, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the present invention is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. And, in the description of the present invention, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items.
[0024] In addition, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.
[0025] Meanwhile, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way for easy understanding.
[0026] The safe and stable operation of oil and gas pipelines is related to the safety of energy transportation. Once a safety accident occurs, it will threaten people's personal safety, cause huge economic losses, and have serious negative impacts. At present, the monitoring and early warning capabilities of oil and gas pipelines are still imperfect, and the risk perception, monitoring and early warning capabilities during pipeline production and operation still need to be further improved.
[0027] At present, sensors are usually used to monitor and warn oil and gas pipelines. Before using sensors to monitor oil and gas pipelines, a corresponding risk perception model needs to be built. The risk perception model is used to make risk judgments based on the data obtained by the sensors. In related technologies, due to the limited ways to obtain training samples and the fact that training samples cannot fully and truly reflect abnormal events in pipeline operation, the accuracy of the risk perception model obtained through training is low and cannot meet the risk perception requirements of oil and gas pipelines.
[0028] In view of this, an embodiment of the present invention provides a risk perception test system and method for an oil and gas pipeline, the system comprising a distributed optical fiber sensor and a processor, the distributed optical fiber sensor being connected to the processor, the distributed optical fiber sensor being arranged in a target area, the target area having the same geomorphic features as the area in which the target oil and gas pipeline is arranged; the distributed optical fiber sensor being used for: responding to different types of abnormal events conducted by a user in the target area, acquiring time series data of target parameters corresponding to each abnormal event, and sending the time series data of target parameters corresponding to each abnormal event to the processor, the target parameters including vibration intensity, temperature or stress; the processor being used for: processing the time series data of the target parameters corresponding to each abnormal event to obtain a training sample set, the training sample set comprising a plurality of training samples; training a neural network model through the training sample set to obtain a trained risk perception model, the risk perception model being used for outputting the risk perception result corresponding to the target oil and gas pipeline according to the input time series data of the target parameters of the target oil and gas pipeline.
[0029] The embodiment of the present invention uses distributed optical fiber sensors set in the target area. Since the geomorphic features of the target area are the same as the geomorphic features of the area where the oil and gas pipeline is set in operation, the abnormal events in the target area are obtained through the distributed optical fiber sensors, and the sample data corresponding to the different abnormal events of the oil and gas pipeline in operation can be accurately and quickly obtained. The risk perception model is trained through the sample data, thereby improving the accuracy of the risk perception model, meeting the risk perception requirements of the oil and gas pipeline, and realizing the safe operation of the oil and gas pipeline. And the process of obtaining sample data will not affect the normal operation of the oil and gas pipeline. That is to say, the system provided by the present invention can test the performance indicators of the abnormal event perception system of the oil and gas pipeline, and can also simulate abnormal events such as artificial excavation, mechanical damage, geological disasters, etc., develop a risk perception model for the oil and gas pipeline, and guide the identification and control of abnormal events in the oil and gas pipeline.
[0030] See also Figure 1 , Figure 1 The hardware schematic diagram of a risk perception test system provided by an embodiment of the present invention is shown. The risk perception test system 100 includes a distributed optical fiber sensor 110 and a processor 120. The distributed optical fiber sensor 110 is connected to the processor 120. The distributed optical fiber sensor 110 is set in a target area. The target area has the same geomorphic features as the area where the target oil and gas pipeline is set.
[0031] Specifically, the processor 120 may include one or more processing cores. The processor 120 uses various interfaces and lines to connect various parts in the electronic device 200, and executes various functions and processes data of the electronic device 200 by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. Optionally, the processor 120 can be implemented in at least one hardware form of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA).
[0032] In one example, the processor 120 can be set inside any electronic device with data processing capabilities, for example, the processor 120 can be set inside a general-purpose computer, a personal computer, a laptop computer, a switch, or a tablet computer, etc. The specific implementation method of the processor 120 is not limited here.
[0033] In some embodiments, the distributed optical fiber sensor 110 is used to: respond to different types of abnormal events performed by a user in a target area, obtain time series data of target parameters corresponding to each abnormal event, and send the time series data of target parameters corresponding to each abnormal event to the processor 120, where the target parameters include vibration intensity, temperature or stress.
[0034] In a possible implementation, the types of abnormal events include manual excavation operations, mechanical excavation operations, and geological settlement operations, and the target area also includes a vibration test area and a stress test area;
[0035] The distributed optical fiber sensor 110 is specifically used for: responding to manual excavation operations or mechanical excavation operations performed by a user in a vibration test area, obtaining time series data of target parameters corresponding to the manual excavation operations or mechanical excavation operations; responding to simulated settlement operations performed by a user in a stress test area, obtaining time series data of target parameters corresponding to the simulated settlement operations.
[0036] In one example, combining Figure 1 , see Figure 2The target area includes multiple vibration test areas, namely, vibration test area 210, vibration test area 220, vibration test area 230 and vibration test area 240, wherein the size of each vibration test area is 5×5m, vibration test area 210 and vibration test area 220 are used for manual excavation operations, vibration test area 210 and vibration test area 220 are adjacent, vibration test area 230 and vibration test area 240 are used for mechanical excavation operations, the distance between vibration test area 230 and vibration test area 240 is 10m, the distance between vibration test area 210 and distributed optical fiber sensor 110 is 5m, and the distance between vibration test area 240 and distributed optical fiber sensor 110 is 10m.
[0037] Further, the manual excavation operation provided by the embodiment of the present invention is explained below in combination with the above examples. User A performs manual excavation in the vibration test area 210 according to the standard process of manual excavation operation, and lasts for 2 minutes. User B records the start and end time points of the excavation action of user A. After the action stops, user A slowly moves to the vibration test area 220 and remains silent for 2 minutes. After the silence ends, user A performs manual excavation again according to the standard process of manual excavation operation, and lasts for 2 minutes. User B records the start and end time points of the excavation action of user A. Among them, the standard process of manual excavation operation is: user A (adult male with a height of 170-180cm and a weight of about 60-80kg) holds a garden shovel (pointed shovel, shovel head material manganese steel, handle material steel pipe, weight 0.86kg, total length 77.5cm, shovel head length 20cm, shovel head width 14.5cm), and performs the action of digging soil in the specified vibration test area. The specific action is: User A holds the lower end of the shovel handle with his left hand and the upper end of the shovel handle with his right hand, with the shovel head facing downward, and the angle between the shovel face and the ground is 70° to 80°, and the shovel face is inserted downward into the soil surface with force, and the insertion depth is about 10 to 20 cm. Then, lift up with your left hand and press down with your right hand to lift the shovel face forward, shovel up the soil above the shovel face, shake off the soil after shoveling, and return the shovel to the initial state. Then repeat the above steps for the next excavation.
[0038] Furthermore, the mechanical excavation operation provided by the embodiment of the present invention is explained below in combination with the above example. User A drives the excavator to perform mechanical excavation in the vibration test area 230 according to the standard process of mechanical excavation operation, and the process lasts for 2 minutes. User B records the start and end time points of the excavation action of user A. After the action stops, user A drives the excavator slowly to the vibration test area 240 and remains silent for 5 minutes. After the silence ends, user A performs mechanical excavation again according to the standard process of mechanical excavation operation, and the process lasts for 2 minutes. User B records the start and end time points of the excavation action of user A. Among them, the standard process of mechanical excavation operation is: use a small and medium-sized crawler general-purpose excavator (bucket capacity <0.5m 3 ). User A operates the excavator to dig the surface soil in the vibration test area. The bucket digging range should be controlled within 5×5㎡, and the digging depth should be controlled within 1.5m. The interval between two adjacent digging actions should be more than 30 seconds. User B records the exact time when the bucket digs. During the excavation process, the movement of the machine body should be minimized. The loose soil should be unloaded outside the excavation area to avoid repeated excavation of loose soil. User A should not use the outer surface of the bucket to hit the ground, and the excavation action should be as close to the actual construction situation as possible. After the excavation is completed, User A should operate the excavator to fill the pit and compact it appropriately.
[0039] In another example, the target area also includes a stress test area, which can simulate abnormal events corresponding to surface settlement caused by geological disasters such as frost heave and thaw settlement through a settlement simulation device. The stress test area includes a 10m×1m×0.5(0.6)m earthen pond built with a concrete structure, which includes a fixed area and a simulated settlement area, wherein the fixed area is used to provide a reliable reference horizontal plane; the simulated settlement area uses a wooden settlement plate to carry the distributed optical fiber sensor 110, and simulates settlement by controlling the water volume of the water bag under the wooden settlement plate, and the vertical drop between the reference horizontal plane of the simulated settlement area and the fixed area is 0.1m. The size of the water bag is 2m×1m×0.1m, and the capacity is 200L. A concrete cushion foundation is poured under the earthen pond to ensure that the fixed area and the simulated settlement area are on the same horizontal reference. One optical cable clamp is installed on the horizontal plane of the fixed area and the wooden settlement plate to fix the distributed optical fiber sensor 110, and the distance between the two optical cable clamps is 1m.
[0040] Further, the simulated settlement operation provided by the embodiment of the present invention is explained below in combination with the above-mentioned stress test area. More specifically, 20 meters of strain sensing optical cable (distributed optical fiber sensor) to be tested is taken, and the optical cable is laid in the middle 10 meters, leaving 5 meters above the ground at the beginning and the end. Two corresponding fiber cores are selected at the beginning and the end of the sensing optical cable. The two fiber cores at the head end are respectively fused to a 1km standard single-mode optical fiber, and the two fiber cores at the tail end are fused to the two ends of a 2m single-mode optical fiber. The two standard single-mode optical fiber fusion adapters at the head end are connected to the distributed strain sensor host to be tested. Start the distributed strain sensor host to be tested, and set it according to the standard test parameters (loop level 5km, monitoring distance 2.1km, sweep frequency range 10~13GHz, sweep step 5MHz, detection interval 5min) and spatial resolution. After the parameter setting is completed, start the test software and carry out simulation tests under weather conditions that have a significant impact on temperature and humidity, such as no rain, snow, fog, strong wind, and sandstorms. The simulated settlement operation is as follows: after the parameter setting is completed, start the test software for 30 minutes of strain monitoring. During the test, ensure that no personnel or vehicles pass over the soil pool, and then close the test software to stop monitoring. User A records the start and stop time of the test software; during the test, use the soil temperature sensor to test and record the soil temperature in the soil pool once; save the 5 sets of raw data obtained, and use these data as reference data. Repeat this step 4 times to simulate the settlement of 1cm, 2cm, 3cm, and 4cm pipes: open the outlet of the water bag in the settlement test pool, so that the water in the water bag flows out naturally under the gravity of the soil above, use the flow meter to record the water flow, and close the outlet valve when the cumulative water output is 20L per time. After closing the outlet valve, keep silent for 5 minutes, then start the test software for 30 minutes of strain monitoring. During the test, ensure that no personnel or vehicles pass over the settlement test pool, and then close the test software to stop monitoring. The user records the start and stop time of the test software; during the test, use the soil temperature sensor to test and record the soil temperature in the soil pool once; save the 5 sets of raw data obtained. The raw data generated during the test are sorted, named, and backed up. The standard standby distributed strain sensor host was turned off. The staff used shovels and other tools to clean the soil in the sedimentation test pool, removed the optical cable to be tested fixed in the fixture, drained the water in the water bag, and backfilled the fan-shaped slopes on both sides of the sedimentation test pool. After the cleaning was completed, guardrails and warning signs were placed around the sedimentation test pool.
[0041] In some embodiments, the processor 120 is used to: process the time series data of the target parameters corresponding to each abnormal event to obtain a training sample set, the training sample set includes multiple training samples; train the neural network model through the training sample set to obtain a trained risk perception model, the risk perception model is used to output the risk perception result corresponding to the target oil and gas pipeline based on the input time series data of the target parameters of the target oil and gas pipeline.
[0042] In a possible implementation, when the processor 120 is used to process the time series data of the target parameter corresponding to each abnormal event to obtain a training sample set, the processor 120 is specifically used to: determine the abnormal event identifier corresponding to the time series data of the target parameter corresponding to each abnormal event; delete the abnormal values in the time series data of the target parameter corresponding to each abnormal event based on the Gaussian distribution 3σ law; perform noise filtering on the time series data of the target parameter corresponding to each abnormal event; perform zero-mean normalization on the time series data of the target parameter corresponding to each abnormal event to obtain preprocessed data; determine the frequency domain data of the target parameter corresponding to each abnormal event based on the preprocessed data; determine the waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event; obtain multiple training samples based on the waterfall chart of the target parameter corresponding to each abnormal event and the abnormal event identifier; and obtain a training sample set based on the multiple training samples.
[0043] Furthermore, in a case where the processor is used to determine a waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event, the processor is specifically used to: stack the frequency domain data of the target parameter corresponding to each abnormal event to obtain a two-dimensional matrix for displaying time progression; map the two-dimensional matrix to a preset range through a maximum-minimum normalization method to obtain a waterfall chart of the target parameter corresponding to each abnormal event.
[0044] As can be seen from the above, the embodiment of the present invention uses distributed optical fiber sensors set in the target area. Since the geomorphic features of the target area are the same as the geomorphic features of the area where the oil and gas pipeline is set in operation, the abnormal events in the target area are obtained through the distributed optical fiber sensors, and the sample data corresponding to the different abnormal events of the oil and gas pipeline in operation can be accurately and quickly obtained. The risk perception model is trained through the sample data, thereby improving the accuracy of the risk perception model, meeting the risk perception requirements of the oil and gas pipeline, and realizing the safe operation of the oil and gas pipeline. And the process of obtaining sample data will not affect the normal operation of the oil and gas pipeline. That is to say, the system provided by the present invention can test the performance indicators of the abnormal event perception system of the oil and gas pipeline, and can also simulate abnormal events such as artificial excavation, mechanical damage, geological disasters, etc., develop a risk perception model for the oil and gas pipeline, and guide the identification and control of abnormal events in the oil and gas pipeline.
[0045] In one possible implementation, the target area also includes multiple ball drop test areas, each of which is at a different distance from the distributed optical fiber sensor; the distributed optical fiber sensor is also used to: respond to the ball drop operation performed by the user in each ball drop test area, obtain vibration data corresponding to each ball drop operation, the vibration data including time series data of vibration intensity; send the vibration data corresponding to each ball drop operation to the processor; the processor is also used to determine the vibration sensitivity of the distributed optical fiber sensor based on the vibration data corresponding to each ball drop operation.
[0046] For example, see Figure 3 The target area includes multiple ball drop test areas, namely, ball drop test area 250, ball drop test area 260 and ball drop test area 270. The distance between every two adjacent ball drop test areas is 10m.
[0047] Specifically, the above-mentioned ball dropping operation includes: user A performs the ball dropping action in the ball dropping test area 250, the ball dropping test area 260 and the ball dropping test area 270 in turn according to the ball dropping operation process. Each ball dropping test area performs 20 ball dropping actions in total, and the interval between two adjacent ball dropping actions should be 20 seconds. When changing the ball dropping test area, user A must first remain silent for 30 seconds after arriving at the designated position, and then restart the ball dropping action. User B records the time of each ball dropping by user A. After user A completes a total of 60 ball dropping actions in 3 areas, the test ends and leaves the test site. Among them, the ball dropping operation process is: a standard training shot put (7.26kg, hand-held diameter 13cm) is used as the test ball. User A first places the vertical ruler correctly on the soil surface of the test area so that the ruler scale bar is vertical. User A holds the shot put with both hands and holds it horizontally in front of his chest, keeping its height at 1.5m (the center of the ball is aligned with the 1.5m scale). User A quickly releases his hands to allow the shot put to fall naturally and hit the soil surface. User B records the moments before and after the shot put hits the ground.
[0048] In some embodiments, the target area also includes a temperature test area, the temperature test area is provided with a heating device and a plurality of soil temperature sensors, and the plurality of soil temperature sensors are connected to the processor; the distributed optical fiber sensor is also used to: when the heating device is started, obtain first temperature data corresponding to the temperature test area, the first temperature data including time series data of the temperature; send the first temperature data to the processor; the processor is also used to: obtain second temperature data, the second temperature data being time series data of the temperature corresponding to the temperature test area obtained by each of the plurality of soil temperature sensors; determine the temperature sensitivity, structural temperature conduction distance, maximum monitoring distance and positioning accuracy of the distributed optical fiber sensor according to the first temperature data and the second temperature data.
[0049] For details, see Figure 4The temperature test area includes a 20m×1m×1m optical cable trench, and multiple soil temperature sensors are arranged at intervals, namely soil temperature sensor 1, soil temperature sensor 2, soil temperature sensor 3, soil temperature sensor 4, soil temperature sensor 5 and soil temperature sensor 6. The heating device includes a high-precision temperature controller and multiple heating coils, namely heating coil 1, heating coil 2 and heating coil 3. The distance between soil temperature sensor 4, soil temperature sensor 5 and soil temperature sensor 6 is 0.5m, and the distance between heating coil 1, heating coil 2 and heating coil 3 is 0.5m. The high-precision temperature controller is used to heat the heating coil to adjust the temperature of the temperature test area. The soil temperature sensor is used to monitor real-time temperature changes. The distributed optical fiber sensor can be buried in the temperature test area. When the soil temperature changes, the monitoring data of the distributed optical fiber sensor is obtained according to the following process.
[0050] Optionally, the temperature sensitivity of the distributed optical fiber sensor is determined in the following manner: user A operates according to the standard operating procedure 1 of the temperature sensitivity test, and performs soil heating operation in the temperature test area. User B operates according to the standard operating procedure 2 of the temperature sensitivity test. After completing one test process, when the temperatures of soil temperature sensor 1, soil temperature sensor 2 and soil temperature sensor 3 are equal to the temperatures measured before the first test, user A operates again according to the standard operating procedure 1 of the temperature sensitivity test. User B operates again according to the standard operating procedure 2 of the temperature sensitivity test. User B records the original data of the corresponding time of the two temperature changes. Among them, the standard operating procedure 1 of the temperature sensitivity test is: user A confirms that the soil temperature sensors 1, soil temperature sensor 2, soil temperature sensor 3 and soil temperature sensor 4 inserted into the soil in the temperature test area are turned on and can read normally. Control the soil heating coil 1 to start heating the soil, observe the soil temperature sensor 4 to determine whether the soil heating coil is working, and keep it relatively still after confirming that it is correct, and keep the soil heating coil 1 working for 20 minutes before turning it off. Among them, the standard operation process 2 of the temperature sensitivity test is: User B records the temperature readings of soil temperature sensor 1, soil temperature sensor 2, soil temperature sensor 3 and soil temperature sensor 4 before the soil heating coil 1 is turned on. When user A operates the soil heating coil 1 to heat up, user B records the start time and the closing time of the heating coil 1, and records the readings of soil temperature sensor 1, soil temperature sensor 2, soil temperature sensor 3 and soil temperature sensor 4 every 5 minutes within 20 minutes. A total of 4 records are required, and during this period, the personnel and the environment must remain relatively still.
[0051] Optionally, the temperature conduction distance of the distributed optical fiber sensor is determined in the following manner: user A operates according to the standard operating procedure 1 of the temperature conduction distance test, and performs soil heating operation in the temperature test area. User B operates according to the standard operating procedure 2 of the temperature conduction distance test. After completing a test process, when the temperature of soil temperature sensor 1, soil temperature sensor 2 and soil temperature sensor 3 is equal to the temperature measured before the first test, user A operates again according to the standard operating procedure 1 of the temperature conduction distance test. User B operates again according to the standard operating procedure 2 of the temperature conduction distance test. User B records the original data of the corresponding time of two temperature changes. Among them, the standard operating procedure 1 of the temperature conduction distance test is: user A confirms that the soil temperature sensors 1, soil temperature sensor 2, soil temperature sensor 3, soil temperature sensor 4, soil temperature sensor 5 and soil temperature sensor 6 inserted into the soil in the soil temperature test area are turned on and can read normally. Control the soil heating coil 1 to start heating to heat the soil, observe the soil temperature sensor 4 to determine whether the soil heating coil is working, and keep it relatively still after confirming that it is correct, and keep the soil heating coil 1 working for 20 minutes before turning it off. When the readings of soil temperature sensors 1, 2, and 3 are the same as the readings of the thermometer before heating, user A controls soil heating coil 2 to start heating the soil, observes soil temperature sensor 5 to determine whether the heating coil is working, and keeps relatively still after confirming that it is correct. After keeping soil heating coil 2 working for 20 minutes, it will be turned off. When the readings of soil temperature sensors 1, 2, and 3 are the same as the readings of the thermometer before heating, user A controls soil heating coil 3 to start heating the soil, observes soil temperature sensor 6 to determine whether the heating coil is working, and keeps relatively still after confirming that it is correct. After keeping soil heating coil 3 working for 20 minutes, it will be turned off. The standard operating procedure 2 of the temperature conduction distance test is: User B records the temperature readings of soil temperature sensor 1, soil temperature sensor 2, soil temperature sensor 3, soil temperature sensor 4, soil temperature sensor 5, and soil temperature sensor 6 before the soil heating coil 1 is turned on. When user A operates soil heating coil 1 to heat up, user B records the start time and the shut down time of heating coil 1, and records the readings of soil temperature sensors 1, 2, 3, and 4 every 5 minutes within 20 minutes. A total of 4 records are required, and the personnel and the environment must remain relatively still during this period. When user A operates soil heating coil 2 to heat up, user B records the start time and the shut down time of heating coil 2, and records the readings of soil temperature sensors 1, 2, 3, and 5 every 5 minutes within 20 minutes. A total of 4 records are required, and the personnel and the environment must remain relatively still during this period.When user A operates the soil heating coil 3 to heat up, user B records the start time and the shut down time of the heating coil 3, and records the readings of the soil temperature sensors 1, 2, 3, and 6 every 5 minutes within 20 minutes. A total of 4 records are required. During this period, the personnel and the environment must remain relatively still.
[0052] Optionally, the maximum temperature monitoring distance of the distributed optical fiber sensor is determined in the following manner: User A and User B operate according to the standard operating procedure for the maximum temperature monitoring distance test, and test the maximum monitoring distance in the temperature test area. During the test, the changes in the monitoring software need to be observed at all times. After completing a test, the test scene is restored to the initial state, and the standard operating procedure for the maximum temperature monitoring distance test is repeated again. User B records the original data of the corresponding time of two temperature changes. Among them, the standard operating procedure for the maximum temperature monitoring distance test is: User A confirms that the soil temperature sensors 1, 2, 3, and 4 inserted into the soil in the soil temperature test area are turned on and can read normally. Control the soil heating coil 1 to start heating the soil, and observe the soil temperature sensor 4 to determine whether the soil heating coil is working. When the soil temperature sensor 2 reading remains unchanged, User B records the time and temperature at this time, and observes whether the temperature reading and position on the monitoring software are consistent with the soil temperature sensor 2 reading and the soil heating coil position. After recording, User A adds a 5km optical fiber coil at the head end of the optical cable to achieve the purpose of increasing the detection distance, and User B repeats the above recording and observation process. User A increases the monitoring distance by 5 km each time until User B stops increasing the monitoring distance when he observes that the temperature and position cannot be accurately displayed on the monitoring software. Turn off the soil heating coil and remove the 5 km optical fiber reel to restore it to its original state.
[0053] Optionally, the temperature positioning accuracy of the distributed optical fiber sensor is determined in the following manner: User A and User B operate according to the standard operating procedure for temperature positioning accuracy and test the temperature positioning accuracy in the temperature test area. During the test, changes in the monitoring software need to be observed at all times.
[0054] After completing a test, restore the test scene to its original state and repeat the temperature positioning accuracy standard operation process again. User A records the original data of the corresponding time of two temperature changes. Temperature positioning accuracy standard operation process:
[0055] User A confirms that the soil temperature sensors 1, 2, 3, and 4 inserted into the soil in the soil temperature test area are turned on and can read normally. Control the soil heating coil 1 to start heating the soil, and observe the soil temperature sensor 4 to determine whether the soil heating coil is working. When the soil temperature sensor 2 reading remains unchanged, user B records the time and temperature at this time, and observes whether the temperature reading and position on the monitoring software match the soil temperature sensor 2 reading and the soil heating coil position. After recording, user A adds a 5km fiber optic coil at the head end of the optical cable to change the position of the temperature influence, and user B repeats the above recording and observation process. Turn off the soil heating coil, and remove the 5km fiber optic coil to restore it to the initial state.
[0056] After the above tests are completed, the raw data generated during the test will be sorted, named and backed up. The monitoring host will be turned off, and the staff will confirm that all soil heating coils and soil temperature sensors are turned off, and use tools such as shovels to re-level the ground to restore it to its initial state before the test as much as possible.
[0057] It is to be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the risk perception test system 100. In other embodiments of the present invention, the risk perception test system 100 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.
[0058] The following describes a risk perception testing method for an oil and gas pipeline provided by an embodiment of the present invention in conjunction with the accompanying drawings.
[0059] Figure 5 A flow chart of a risk perception test method for oil and gas pipelines provided in an embodiment of the present invention. Optionally, the method may be performed by Figure 1 The risk perception test system 100 is shown to perform. The method may include the following steps:
[0060] S1, the distributed optical fiber sensor responds to different types of abnormal events performed by the user in the target area and obtains the time series data of the target parameters corresponding to each abnormal event;
[0061] In one possible implementation, the types of abnormal events include manual excavation operations, mechanical excavation operations, and geological settlement operations, and the target area also includes a vibration test area and a stress test area. The above S1 specifically includes: the distributed optical fiber sensor responds to the manual excavation operation or mechanical excavation operation performed by the user in the vibration test area, and obtains the time series data of the target parameters corresponding to the manual excavation operation or the mechanical excavation operation; the distributed optical fiber sensor responds to the simulated settlement operation performed by the user in the stress test area, and obtains the time series data of the target parameters corresponding to the simulated settlement operation.
[0062] S2, the distributed optical fiber sensor sends the time series data of the target parameter corresponding to each abnormal event to the processor, the target parameter including vibration intensity, temperature or stress;
[0063] S3. The processor processes the time series data of the target parameter corresponding to each abnormal event to obtain a training sample set, where the training sample set includes multiple training samples;
[0064] In a possible implementation, the above S3 specifically includes: the processor determines the abnormal event identifier corresponding to the time series data of the target parameter corresponding to each abnormal event; the processor deletes the abnormal values in the time series data of the target parameter corresponding to each abnormal event based on the Gaussian distribution 3σ law; the processor performs noise filtering on the time series data of the target parameter corresponding to each abnormal event; the processor performs zero-mean normalization processing on the time series data of the target parameter corresponding to each abnormal event to obtain preprocessed data; the processor determines the frequency domain data of the target parameter corresponding to each abnormal event based on the preprocessed data; the processor determines the waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event; the processor obtains multiple training samples based on the waterfall chart of the target parameter corresponding to each abnormal event and the abnormal event identifier; the processor obtains a training sample set based on the multiple training samples.
[0065] Optionally, the processor determines a waterfall chart of the target parameter corresponding to each abnormal event based on the frequency domain data of the target parameter corresponding to each abnormal event, including: the processor stacks the frequency domain data of the target parameter corresponding to each abnormal event to obtain a two-dimensional matrix for displaying time progression; the processor maps the two-dimensional matrix to a preset range through a maximum-minimum normalization method to obtain a waterfall chart of the target parameter corresponding to each abnormal event.
[0066] S4. The processor trains the neural network model through the training sample set to obtain a trained risk perception model. The risk perception model is used to output the risk perception result corresponding to the target oil and gas pipeline according to the input time series data of the target parameters of the target oil and gas pipeline.
[0067] It should be understood that the specific implementation method of the method provided in the embodiment of the present invention is the same as the specific implementation method of the above-mentioned risk perception testing system 100, and the beneficial effects produced thereby are also the same. Please refer to the description of the above-mentioned embodiment for details, and no further details will be given here.
[0068] The above mainly introduces the scheme of the embodiment of the present invention from the perspective of the method. It can be understood that in order to realize the above functions, the risk perception test system 100 includes at least one of the hardware structure and software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment disclosed in this article, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiment of the present invention.
[0069] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A risk perception test system for oil and gas pipelines, characterized in that: The system comprises a distributed optical fiber sensor and a processor, wherein the distributed optical fiber sensor is connected to the processor, and the distributed optical fiber sensor is arranged in a target area, and the target area has the same geomorphic features as the area where the target oil and gas pipeline is arranged; The distributed optical fiber sensor is used for: In response to different types of abnormal events performed by a user in the target area, acquiring time series data of a target parameter corresponding to each abnormal event, and sending the time series data of the target parameter corresponding to each abnormal event to the processor, wherein the target parameter includes vibration intensity, temperature or stress; The processor is used to: Processing the time series data of the target parameter corresponding to each of the abnormal events to obtain a training sample set, wherein the training sample set includes a plurality of training samples; The neural network model is trained by the training sample set to obtain a trained risk perception model, and the risk perception model is used to output the risk perception result corresponding to the target oil and gas pipeline according to the input time series data of the target parameters of the target oil and gas pipeline.
2. The system according to claim 1, characterized in that The types of abnormal events include manual excavation operations, mechanical excavation operations and geological settlement operations, and the target area also includes a vibration test area and a stress test area; The distributed optical fiber sensor is specifically used for: In response to a manual excavation operation or a mechanical excavation operation performed by a user in the vibration test area, acquiring time series data of a target parameter corresponding to the manual excavation operation or the mechanical excavation operation; In response to a simulated settlement operation performed by a user in the stress test area, time series data of a target parameter corresponding to the simulated settlement operation is acquired.
3. The system according to claim 2, characterized in that In the case where the processor is used to process the time series data of the target parameter corresponding to each of the abnormal events to obtain a training sample set, the processor is specifically used to: Determine an abnormal event identifier corresponding to the time series data of the target parameter corresponding to each of the abnormal events; Deleting outliers in the time series data of the target parameter corresponding to each of the abnormal events based on the Gaussian distribution 3σ rule; Performing noise filtering on the time series data of the target parameter corresponding to each of the abnormal events; Performing zero-mean normalization processing on the time series data of the target parameter corresponding to each of the abnormal events to obtain preprocessed data; Determine frequency domain data of target parameters corresponding to each abnormal event according to the preprocessed data; Determine a waterfall diagram of the target parameter corresponding to each of the abnormal events according to the frequency domain data of the target parameter corresponding to each of the abnormal events; Obtain multiple training samples according to the waterfall chart of the target parameter corresponding to each abnormal event and the abnormal event identifier; A training sample set is obtained according to multiple training samples.
4. The system according to claim 3, characterized in that In a case where the processor is used to determine a waterfall diagram of the target parameter corresponding to each abnormal event according to the frequency domain data of the target parameter corresponding to each abnormal event, the processor is specifically used to: Stacking the frequency domain data of the target parameter corresponding to each abnormal event to obtain a two-dimensional matrix for displaying time progression; The two-dimensional matrix is mapped to a preset range through a maximum-minimum value normalization method to obtain a waterfall chart of the target parameter corresponding to each abnormal event.
5. The system according to claim 4, characterized in that The target area further includes a plurality of ball drop test areas, each of which is at a different distance from the distributed optical fiber sensor; The distributed optical fiber sensor is also used for: In response to a ball dropping operation performed by a user in each ball dropping test area, obtaining vibration data corresponding to each ball dropping operation, wherein the vibration data includes time series data of vibration intensity; sending vibration data corresponding to each ball drop operation to the processor; The processor is further configured to determine the vibration sensitivity of the distributed optical fiber sensor according to the vibration data corresponding to each ball dropping operation.
6. The system according to claim 5, characterized in that The target area also includes a temperature test area, the temperature test area is provided with a heating device and a plurality of soil temperature sensors, and the plurality of soil temperature sensors are connected to the processor; The distributed optical fiber sensor is also used for: When the heating device is started, obtaining first temperature data corresponding to the temperature test area, wherein the first temperature data includes time series data of temperature; sending the first temperature data to the processor; The processor is further configured to: Acquire second temperature data, where the second temperature data is time series data of the temperature corresponding to the temperature test area acquired by each of the plurality of soil temperature sensors; The temperature sensitivity, structural temperature conduction distance, maximum monitoring distance and positioning accuracy of the distributed optical fiber sensor are determined according to the first temperature data and the second temperature data.
7. A risk perception testing method for oil and gas pipelines, characterized in that: Applied to a risk perception test system, the system comprises a distributed optical fiber sensor and a processor, the distributed optical fiber sensor is connected to the processor, the distributed optical fiber sensor is arranged in a target area, and the target area has the same geomorphic features as the area where the target oil and gas pipeline is arranged; The method comprises: The distributed optical fiber sensor responds to different types of abnormal events performed by the user in the target area, and obtains time series data of target parameters corresponding to each abnormal event; The distributed optical fiber sensor sends time series data of a target parameter corresponding to each of the abnormal events to the processor, wherein the target parameter includes vibration intensity, temperature or stress; The processor processes the time series data of the target parameter corresponding to each of the abnormal events to obtain a training sample set, wherein the training sample set includes a plurality of training samples; The processor trains the neural network model through the training sample set to obtain a trained risk perception model, and the risk perception model is used to output the risk perception result corresponding to the target oil and gas pipeline based on the input time series data of the target parameters of the target oil and gas pipeline.
8. The method according to claim 7, characterized in that The types of abnormal events include manual excavation operations, mechanical excavation operations and geological settlement operations, and the target area also includes a vibration test area and a stress test area; The distributed optical fiber sensor responds to different types of abnormal events performed by the user in the target area, and obtains time series data of target parameters corresponding to each abnormal event, including: The distributed optical fiber sensor responds to a manual excavation operation or a mechanical excavation operation performed by a user in the vibration test area to obtain time series data of a target parameter corresponding to the manual excavation operation or the mechanical excavation operation; The distributed optical fiber sensor responds to a simulated settlement operation performed by a user in the stress test area to obtain time series data of a target parameter corresponding to the simulated settlement operation.
9. The method according to claim 8, characterized in that The processor processes the time series data of the target parameter corresponding to each of the abnormal events to obtain a training sample set, including: The processor determines an abnormal event identifier corresponding to the time series data of the target parameter corresponding to each of the abnormal events; The processor deletes the abnormal value in the time series data of the target parameter corresponding to each abnormal event based on the Gaussian distribution 3σ law; The processor performs noise filtering on the time series data of the target parameter corresponding to each of the abnormal events; The processor performs zero-mean normalization processing on the time series data of the target parameter corresponding to each of the abnormal events to obtain preprocessed data; The processor determines the frequency domain data of the target parameter corresponding to each of the abnormal events according to the preprocessed data; The processor determines a waterfall diagram of the target parameter corresponding to each of the abnormal events according to the frequency domain data of the target parameter corresponding to each of the abnormal events; The processor obtains a plurality of training samples according to the waterfall diagram of the target parameter corresponding to each of the abnormal events and the abnormal event identifier; The processor obtains a training sample set according to a plurality of training samples.
10. The method according to claim 9, characterized in that The processor determines a waterfall diagram of the target parameter corresponding to each abnormal event according to the frequency domain data of the target parameter corresponding to each abnormal event, including: The processor stacks the frequency domain data of the target parameter corresponding to each abnormal event to obtain a two-dimensional matrix for displaying time progress; The processor maps the two-dimensional matrix to a preset range through a maximum-minimum value normalization method to obtain a waterfall chart of the target parameter corresponding to each abnormal event.