CN111322524B - Safety detection method, device and detection equipment for drilling platform - Google Patents

Safety detection method, device and detection equipment for drilling platform Download PDF

Info

Publication number
CN111322524B
CN111322524B CN202010133511.6A CN202010133511A CN111322524B CN 111322524 B CN111322524 B CN 111322524B CN 202010133511 A CN202010133511 A CN 202010133511A CN 111322524 B CN111322524 B CN 111322524B
Authority
CN
China
Prior art keywords
amplitude
ultrasonic
vector
curve
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010133511.6A
Other languages
Chinese (zh)
Other versions
CN111322524A (en
Inventor
周红
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SICHUAN SALT GEOLOGY DRILLING TEAM
Original Assignee
Sichuan Salt Geology Drilling Team
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sichuan Salt Geology Drilling Team filed Critical Sichuan Salt Geology Drilling Team
Priority to CN202010133511.6A priority Critical patent/CN111322524B/en
Priority to CN202011183474.6A priority patent/CN112377822A/en
Priority to CN202011188119.8A priority patent/CN112326791A/en
Publication of CN111322524A publication Critical patent/CN111322524A/en
Application granted granted Critical
Publication of CN111322524B publication Critical patent/CN111322524B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
    • F17D—PIPE-LINE SYSTEMS; PIPE-LINES
    • F17D5/00—Protection or supervision of installations
    • F17D5/02—Preventing, monitoring, or locating loss
    • F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/04—Analysing solids
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/4481—Neural networks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/46—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by spectral analysis, e.g. Fourier analysis or wavelet analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
    • G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
    • G01N29/48—Processing the detected response signal, e.g. electronic circuits specially adapted therefor by amplitude comparison
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

The invention provides a safety detection method, a safety detection device and a safety detection device for a drilling platform, which can analyze a radio-frequency signal sent by an ultrasonic transceiver to obtain an ultrasonic spectrogram, further fit an amplitude curve and determine multiple groups of curve characteristics of the amplitude curve, and then perform characteristic identification by combining operation characteristics corresponding to an operation data list of an extraction device communicated with an oil-gas pipeline, so as to generate a flaw detection result of the oil-gas pipeline. So, can realize detecting a flaw to the oil gas pipeline at the ultrasonic wave aspect, and then discern the slight damage in the oil gas pipeline, so, even if oil gas pipeline does not appear oil gas and reveals, still can accurately detect a flaw to the oil gas pipeline through above-mentioned scheme.

Description

Safety detection method, device and detection equipment for drilling platform
Technical Field
The invention relates to the technical field of oil and gas exploration, in particular to a safety detection method, a safety detection device and safety detection equipment for a drilling platform.
Background
Drilling platforms are indispensable structures for oil and gas exploration and development. Oil and gas exploration and development environments are mostly severe, and damage to a drilling platform is easily caused, so that safety accidents are caused. For example, if a damaged oil and gas transmission pipeline in a drilling platform causes oil and gas leakage, explosion is easy to occur when exposed to open fire or weak current. Therefore, how to perform timely and effective safety detection on the drilling platform is the key to ensure the safety and orderly performance of oil and gas exploration and development.
Disclosure of Invention
In order to solve the problems, the invention provides a drilling platform safety detection method, a drilling platform safety detection device and a drilling platform safety detection device.
In a first aspect of an embodiment of the present invention, a drilling platform safety detection method is provided, which is applied to a detection device, where the detection device is in communication with an ultrasonic transceiver and an extraction device, and the extraction device is communicated with an oil and gas pipeline, where the method at least includes:
receiving a radio frequency signal sent by ultrasonic transceiver equipment, wherein the radio frequency signal is obtained by the ultrasonic transceiver equipment through conversion according to received second ultrasonic waves, and the second ultrasonic waves are reflected echoes formed at an oil-gas pipeline by first ultrasonic waves transmitted to the oil-gas pipeline by the ultrasonic transceiver equipment;
analyzing the radio frequency signal according to a signal conversion protocol negotiated with the ultrasonic transceiver in advance to obtain an ultrasonic spectrogram corresponding to the second ultrasonic wave;
fitting an amplitude curve according to the ultrasonic spectrogram, and determining multiple groups of curve characteristics corresponding to the amplitude curve based on the iterative relationship between each curve node and the adjacent curve nodes in the amplitude curve;
acquiring an operation data list of an extraction device corresponding to a set time period from an operation data storage device of the extraction device communicated with the oil-gas pipeline, wherein the set time period is a time period from a first time to a second time, the first time is a time when the ultrasonic transceiver transmits the first ultrasonic wave to the oil-gas pipeline, and the second time is a time when the ultrasonic transceiver receives the second ultrasonic wave reflected by the first ultrasonic wave at the oil-gas pipeline;
and determining the operating characteristics of the extraction equipment from the operating data list, and performing characteristic identification on the operating characteristics and the multiple groups of curve characteristics to generate a flaw detection result of the oil and gas pipeline.
Optionally, the analyzing the radio frequency signal according to a signal conversion protocol pre-negotiated with the ultrasonic transceiver to obtain an ultrasonic spectrogram corresponding to the second ultrasonic wave includes:
acquiring a signal coding library according to path information of the signal coding library included in the signal conversion protocol, and coding the radio-frequency signal according to the signal coding library to obtain a distribution map of amplitude-frequency information in the radio-frequency signal; identifying and obtaining the characteristic vectors of amplitude-frequency information in the radio frequency signal by using a preset amplitude-frequency characteristic identification model, and obtaining the vector weight of each characteristic vector; wherein the vector weight comprises a stability coefficient for characterizing the distortion rate of each feature vector and an association coefficient for characterizing the association of each feature vector with other vectors in the magnitude-frequency information;
according to the vector weight of each eigenvector, the vector weight of each eigenvector is coded by using the signal coding library, and a conversion factor of a spectrum vector corresponding to each eigenvector is obtained, wherein the conversion factor is used for representing a weighting coefficient when each eigenvector is converted into a frequency vector;
respectively judging whether the first matching degree of each feature vector and the distribution diagram is greater than the second matching degree of each corresponding spectrum vector to the distribution diagram or not according to the conversion factor of each spectrum vector and the feature vector corresponding to each spectrum vector;
if so, acquiring a conversion factor of the frequency spectrum vector corresponding to the feature vector as a frequency map conversion base number of the feature vector; if not, keeping the vector weight of the feature vector unchanged; judging whether the size of the overall stability change of all the characteristic vectors of the amplitude-frequency information in the radio frequency signal before and after the judgment is smaller than a preset reference value or not; if the amplitude information is smaller than the reference stability coefficient, determining the stability coefficients of all the characteristic vectors of the amplitude information in the radio frequency signal as the reference stability coefficients meeting the requirements; determining the conversion base number of the frequency map of each feature vector according to the reference stability coefficient; if not, returning to the step of encoding the vector weight of each eigenvector by using the signal encoding library and obtaining the conversion factor of the frequency spectrum vector corresponding to each eigenvector;
and determining frequency coding information corresponding to each feature vector from the signal coding library according to the frequency map conversion base number of each feature vector, and generating an ultrasonic frequency spectrogram based on the frequency coding information.
Optionally, the fitting a magnitude curve according to the ultrasonic spectrogram includes:
acquiring amplitude information of the ultrasonic spectrogram, wherein the amplitude information comprises a plurality of ultrasonic amplitudes and time information corresponding to each ultrasonic amplitude;
acquiring a fitting weight corresponding to the amplitude information; wherein, the obtaining of the fitting weight corresponding to the amplitude information specifically includes: acquiring time-frequency correlation coefficients of all ultrasonic amplitudes in the amplitude information, and performing statistics; taking the time-frequency correlation coefficient with the maximum specific gravity as the fitting weight; the time-frequency correlation coefficient is used for describing the amplitude variation trend of each ultrasonic amplitude in the time dimension;
splitting the amplitude information according to the fitting weight to obtain an amplitude unit of the amplitude information; the amplitude unit splitting the amplitude information according to the fitting weight to obtain the amplitude information specifically includes: splitting the amplitude information according to the fitting weight through a first preset splitting rule or a second preset splitting rule to obtain an amplitude unit of the amplitude information; wherein, the first preset splitting rule specifically comprises: obtaining an amplitude cluster in which a plurality of ultrasonic amplitudes continuously increasing or continuously decreasing exist in the amplitude information, and sequentially splitting the ultrasonic amplitudes according to a continuously increasing or continuously decreasing gradient and a continuously increasing or continuously decreasing accumulated value until fluctuation weights corresponding to the upper limit values of the amplitudes of the plurality of continuously increasing or continuously decreasing ultrasonic amplitudes in the amplitude information are the fitting weights; wherein the second preset splitting rule specifically includes: determining three weights of amplitude weight, moment weight and amplitude moment weight of each ultrasonic amplitude in the amplitude information, traversing all ultrasonic amplitudes through a preset iteration traversal rule to find a target amplitude weight corresponding to a median of the ultrasonic amplitudes, a target moment weight and a target ultrasonic amplitude corresponding to the target amplitude moment weight, and splitting the amplitude information by taking the target ultrasonic amplitude as a splitting midpoint;
dividing the ultrasonic spectrogram according to the amplitude unit of the amplitude information; and generating a distribution track expressing the size and the sequence of each amplitude unit in the ultrasonic spectrogram according to the divided ultrasonic spectrogram, and fitting and generating the amplitude curve according to the distribution track.
Optionally, the determining, based on an iterative relationship between each curve node in the amplitude curve and its adjacent curve nodes, a plurality of sets of curve features corresponding to the amplitude curve includes:
determining a two-dimensional coordinate value of each curve node in the amplitude curve;
determining a first distance between each curve node and a first curve node adjacent to the curve node in a coordinate system corresponding to the amplitude curve and a second distance between each curve node adjacent to the curve node and the amplitude curve according to each two-dimensional coordinate value;
judging whether the difference value between the first distance and the second distance corresponding to each curve node is smaller than a set value or not aiming at each curve node, and determining the curve node as an iterable node when the difference value between the first distance and the second distance corresponding to the node is smaller than the set value;
and extracting the curve characteristics corresponding to each curve segment according to the relative position of the iterable nodes in the curve segment.
Optionally, the obtaining an operation data list of an extraction device corresponding to a set time period from an operation data storage device of the extraction device communicated with the oil and gas pipeline includes:
acquiring a working signal trigger condition and each running data packet of the running data storage equipment;
under the condition that the operating data storage device is determined to contain the working state form according to the working signal triggering condition, determining consistency comparison results between each operating data packet of the operating data storage device under the non-working state form and each operating data packet of the operating data storage device under the working state form according to the operating data packet of the operating data storage device under the working state form and the state parameters of the operating data packet;
transferring the running data packets of the running data storage device in the non-working state form, which are consistent with the running data packets in the working state form, to the working state form;
under the condition that the operating data storage device contains a plurality of operating data packets in the non-operating state form, determining consistency comparison results of the operating data storage device among the operating data packets in the non-operating state form according to the operating data packets and state parameters of the operating data storage device in the operating state form;
filtering each operation data packet in the non-working state form according to the consistency comparison result between each operation data packet;
setting transfer information for each running data packet reserved after filtering according to the running data packet of the running data storage device in the working state form and the state parameters of the running data packet, and transferring each running data packet reserved after filtering to the working state form based on the transfer information;
and generating the operating data list according to all the operating data packets in the working state form.
Optionally, the determining the operation characteristics of the extraction device from the operation data list includes:
caching the running data list into a preset caching interval and copying the running data list into a preset dynamic storage space, wherein the running data list in the caching interval cannot be updated, and the running data list in the dynamic storage space can be updated;
receiving target data updated by the running data storage equipment at regular time, and updating a running data list in the dynamic storage space based on the target data to obtain a target data list;
performing data extraction on the target data list according to a preset extraction rule to obtain working condition parameters which are included in the target data list and used for representing the operation state change of the extraction equipment, wherein the working condition parameters comprise a gas pressure value and an operation current value of the extraction equipment; the extraction rule is obtained by performing list structure analysis on the running data list in the cache interval;
determining the variation trend of the working condition parameters in an operation data list located in the dynamic storage space, mapping the variation trend to a list structure distribution diagram corresponding to the operation parameter list located in the cache interval to obtain a target vector corresponding to the variation trend, and obtaining the operation characteristics of the extraction equipment based on the target vector.
Optionally, the performing feature recognition on the operation features and the plurality of sets of curve features to generate flaw detection results of the oil and gas pipeline includes:
respectively fusing the first vectors corresponding to the operating features with the second vectors corresponding to each group of curve features to obtain third vectors, wherein the vector dimensions of the first vectors are the same as those of the second vectors, and when the first vectors and each second vector are fused, the vector values of the first vectors and each second vector at the same vector dimension position are weighted difference or weighted sum;
inputting each third vector into a pre-built convolutional neural network, and acquiring a flaw detection result output by the convolutional neural network, wherein the flaw detection result comprises the damage position and the damage degree of the oil and gas pipeline, the damage position and the damage degree are stored in the detection equipment in a numerical value pair mode, the convolutional neural network is obtained through training of a training set, the training set comprises different damage positions and different damage degrees corresponding to different sizes of reference oil and gas pipelines, the training set is packaged in a reference vector mode, the vector dimension of the reference vector is the same as that of the third vector, and the convolutional neural network calculates the cosine distance between each third vector and each reference vector in the training set to determine the flaw detection result.
In a second aspect of the embodiments of the present invention, there is provided a drilling platform safety detection apparatus, including:
the receiving module is used for receiving a radio frequency signal sent by ultrasonic transceiver equipment, wherein the radio frequency signal is obtained by the ultrasonic transceiver equipment through conversion according to received second ultrasonic waves, and the second ultrasonic waves are reflected echoes formed at an oil-gas pipeline by first ultrasonic waves emitted to the oil-gas pipeline by the ultrasonic transceiver equipment;
the analysis module is used for analyzing the radio-frequency signal according to a signal conversion protocol negotiated with the ultrasonic transceiver in advance to obtain an ultrasonic spectrogram corresponding to the second ultrasonic wave;
the fitting module is used for fitting an amplitude curve according to the ultrasonic spectrogram and determining a plurality of groups of curve characteristics corresponding to the amplitude curve based on the iterative relationship between each curve node in the amplitude curve and the adjacent curve nodes;
an obtaining module, configured to obtain an operation data list of an extraction device corresponding to a set time period from an operation data storage device of the extraction device communicated with the oil and gas pipeline, where the set time period is a time period from a first time to a second time, the first time is a time when the ultrasonic transceiver transmits the first ultrasonic wave to the oil and gas pipeline, and the second time is a time when the ultrasonic transceiver receives the second ultrasonic wave reflected by the first ultrasonic wave at the oil and gas pipeline;
and the identification module is used for determining the operation characteristics of the extraction equipment from the operation data list and carrying out characteristic identification on the operation characteristics and the multiple groups of curve characteristics to generate the flaw detection result of the oil and gas pipeline.
In a third aspect of the embodiments of the present invention, there is provided a detection apparatus, including: a processor and a memory and bus connected to the processor; the processor and the memory are communicated with each other through the bus; the processor is used for calling the computer program in the memory so as to execute the drilling platform safety detection method.
In a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, on which a program is stored, the program, when being executed by a processor, implementing the above-mentioned drilling platform safety detection method.
According to the drilling platform safety detection method, device and detection equipment provided by the embodiment of the invention, the radio-frequency signal sent by the ultrasonic transceiver can be analyzed to obtain the ultrasonic spectrogram, so that the amplitude curve is fitted, multiple groups of curve characteristics of the amplitude curve are determined, and then the characteristic identification is carried out by combining the operation characteristics corresponding to the operation data list of the extraction equipment communicated with the oil-gas pipeline, so that the flaw detection result of the oil-gas pipeline is generated. So, can realize detecting a flaw to the oil gas pipeline at the ultrasonic wave aspect, and then discern the slight damage in the oil gas pipeline, so, even if oil gas pipeline does not appear oil gas and reveals, still can accurately detect a flaw to the oil gas pipeline through above-mentioned scheme.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart of a drilling platform safety detection method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a communication connection of a detection device according to an embodiment of the present invention.
Fig. 3 is a functional block diagram of a drilling platform safety detection device according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of a product module of a detection apparatus according to an embodiment of the present invention.
Icon:
10-a detection device; 101-a drilling platform safety detection device; 1011-a receiving module; 1012-a resolution module; 1013-a fitting module; 1014-an acquisition module; 1015-an identification module; 121-a processor; 122-a memory; 123-bus;
20-an ultrasonic transceiver device;
30-an oil and gas pipeline;
40-an extraction device; 41-operating the data storage device.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In order to better understand the technical solutions of the present invention, the following detailed descriptions of the technical solutions of the present invention are provided with the accompanying drawings and the specific embodiments, and it should be understood that the specific features in the embodiments and the examples of the present invention are the detailed descriptions of the technical solutions of the present invention, and are not limitations of the technical solutions of the present invention, and the technical features in the embodiments and the examples of the present invention may be combined with each other without conflict.
The inventor finds that the existing flaw detection method for the oil and gas transmission pipeline in the drilling platform mostly carries out indirect flaw detection by arranging a gas sensor, and if the gas sensor detects gas leakage, the damage of the oil and gas transmission pipeline is indicated. However, this method can only detect when the oil and gas transmission pipeline is damaged to the extent of oil and gas leakage, and if the oil and gas transmission pipeline is slightly damaged but oil and gas leakage does not occur, the accuracy of the method is greatly reduced.
In order to solve the above problems, embodiments of the present invention provide a method, an apparatus, and a device for testing safety of a drilling platform, which can perform ultrasonic flaw detection on an oil-gas transmission pipeline and accurately perform flaw detection on the oil-gas transmission pipeline in combination with a working state of a device connected to the oil-gas transmission pipeline.
On the basis of the above, fig. 1 shows a flowchart of a drilling platform safety detection method provided by an embodiment of the present invention, the method is applied to the detection device 10 in fig. 2, the detection device 10 is in communication with an ultrasonic transceiver 20, and the ultrasonic transceiver 20 is configured to transmit ultrasonic waves to the oil and gas pipeline 30 and receive echoes reflected by the oil and gas pipeline 30.
Further, when the ultrasonic transceiver 20 receives the echo, the echo is converted into a radio frequency signal and is sent to the detection device 10, and the detection device 10 analyzes the radio frequency signal and realizes accurate flaw detection of the oil and gas pipeline 30 by combining the working state of the extraction device 40 connected with the oil and gas pipeline 30.
In this embodiment, the method for detecting the safety of the drilling platform shown in fig. 1 may specifically include the following steps.
Step S21, receiving a radio frequency signal sent by an ultrasonic transceiver, wherein the radio frequency signal is obtained by the ultrasonic transceiver through conversion according to a received second ultrasonic wave, and the second ultrasonic wave is a reflected echo formed at an oil-gas pipeline by a first ultrasonic wave transmitted to the oil-gas pipeline by the ultrasonic transceiver.
In this embodiment, the ultrasound transceiver device 20 periodically transmits a first ultrasound wave to the hydrocarbon pipeline 30, which forms a reflected echo at the hydrocarbon pipeline 30, which may be a second ultrasound wave. Further, the ultrasonic transceiver 20 may convert the second ultrasonic wave into a radio frequency signal to be transmitted to the detecting device 10.
Step S22, analyzing the radio frequency signal according to a signal conversion protocol negotiated with the ultrasonic transceiver in advance, to obtain an ultrasonic spectrogram corresponding to the second ultrasonic wave.
In this embodiment, the ultrasonic spectrogram includes ultrasonic amplitudes at different times in a continuous time window, and the plurality of continuous ultrasonic amplitudes may also form an amplitude curve in the continuous time window, where the amplitude curve may be used for analysis and identification by the detection apparatus 10.
And step S23, fitting an amplitude curve according to the ultrasonic spectrogram, and determining multiple groups of curve characteristics corresponding to the amplitude curve based on the iterative relationship between each curve node and the adjacent curve nodes in the amplitude curve.
Step S24, obtaining an operation data list of an extraction device corresponding to a set time period from an operation data storage device of the extraction device communicated with the oil-gas pipeline, wherein the set time period is a time period from a first time to a second time, the first time is a time when the ultrasonic transceiver transmits the first ultrasonic wave to the oil-gas pipeline, and the second time is a time when the ultrasonic transceiver receives the second ultrasonic wave reflected by the first ultrasonic wave at the oil-gas pipeline.
In the present embodiment, the extraction device 40 is in communication with an oil and gas pipeline and is configured to extract oil and gas in the exploration area, and the operation data storage device 41 of the extraction device 40 is configured to record operation data of the extraction device 40 and form an operation data list according to the operation data.
Step S25, determining the operation characteristics of the extraction equipment from the operation data list, and performing characteristic identification on the operation characteristics and the multiple groups of curve characteristics to generate the flaw detection result of the oil and gas pipeline.
In this embodiment, the flaw detection result may include a damage level and a damage location of the oil and gas pipeline 30, and an oil and gas leakage probability determined based on the damage level and the damage location. It can be understood that by the above flaw detection method, flaw detection of the oil and gas pipeline 30 can be realized at the ultrasonic level, and further, a slight damage in the oil and gas pipeline 30 can be identified, so that even if oil and gas leakage does not occur in the oil and gas pipeline 30, accurate flaw detection of the oil and gas pipeline 30 can still be performed by the above scheme.
It can be understood that based on the above steps S21-S25, the radio frequency signal sent by the ultrasonic transceiver device can be analyzed to obtain an ultrasonic spectrogram, and then an amplitude curve is fitted and multiple groups of curve features of the amplitude curve are determined, and then feature recognition is performed by combining the operation features corresponding to the operation data list of the extraction device communicated with the oil and gas pipeline, so as to generate the flaw detection result of the oil and gas pipeline. So, can realize detecting a flaw to the oil gas pipeline at the ultrasonic wave aspect, and then discern the slight damage in the oil gas pipeline, so, even if oil gas pipeline does not appear oil gas and reveals, still can accurately detect a flaw to the oil gas pipeline through above-mentioned scheme.
In an alternative embodiment, the signal conversion protocol between the detection device 10 and the ultrasound transceiver device 20 may be implemented in particular by the detection device 10 in the following manner.
Step S31 is to obtain a first signal processing log generated by processing an ultrasonic signal in the ultrasonic transceiver and determine first signal processing logic information corresponding to the first signal processing log, where the first signal processing log is stored in a database of the ultrasonic transceiver and the first signal processing log is updated in real time.
Step S32, obtaining a second signal processing log of the detection device, and calculating a similarity between the first signal processing log and the second signal processing log according to the first signal processing logic information.
Step S33, if the similarity between the first signal processing log and the second signal processing log is smaller than a preset similarity threshold, matching second signal processing logic information corresponding to the second signal processing log of the detection device with the first signal processing logic information to obtain target logic information, where the target logic information is used to indicate a compatibility adjustment policy between the detection device and the ultrasonic transceiver device, and the compatibility adjustment policy is used to indicate the detection device and the ultrasonic transceiver device to perform parameter adjustment.
In step S33, after the parameter adjustment is performed by the detection device 10 and the ultrasonic wave transmission/reception device 20, compatibility between them can be achieved, and signal transmission failure can be avoided.
Step S34, splitting the target logic information into information sets, and building a signal conversion protocol with the information sets as a protocol framework and the signal processing thread information of the first signal processing log in the ultrasonic transceiver device as protocol content to obtain a first protocol.
Step S35, adjusting the first protocol according to the second signal processing log to obtain a second protocol, that is, adding the consideration of the first signal processing log, and adjusting the first protocol, so as to obtain an adjustment result with high compatibility, that is, the second protocol.
Step S36, determining a first error rate of the second protocol relative to the information set, and matching the logic thread in the second protocol corresponding to the first error rate with the target logic information to obtain a matching result.
Step S37, if the similarity between the first signal processing log and the second signal processing log is greater than or equal to the similarity threshold, determining a second error rate of the first protocol relative to the information set, and matching a logical thread in the first protocol corresponding to the second error rate with the target logical information to obtain a matching result.
Step S38, adding the first address of the detection device and the second address of the ultrasonic transceiver device to the protocol address corresponding to the second protocol according to the matching result to obtain the signal conversion protocol.
It can be understood that, through the above, the signal conversion protocol can be accurately determined, and thus the compatibility between the detection device 10 and the ultrasonic transceiver 20 is improved, so as to ensure the accuracy of the radio frequency signal analysis by the detection device 10.
In order to ensure that the detection device 10 can analyze the second ultrasonic wave comprehensively, it is necessary to analyze the ultrasonic spectrogram of the second ultrasonic wave according to the radio frequency signal. Therefore, in order to ensure the accuracy of analyzing the radio frequency signal so as to avoid distortion of the ultrasonic spectrogram, in step S22, the analyzing the radio frequency signal according to the signal conversion protocol pre-negotiated with the ultrasonic transceiver to obtain the ultrasonic spectrogram corresponding to the second ultrasonic wave may specifically include the following.
Step S221, acquiring the signal coding library according to path information of the signal coding library included in the signal conversion protocol, and coding the radio frequency signal according to the signal coding library to obtain a distribution map of amplitude-frequency information in the radio frequency signal; identifying and obtaining the characteristic vectors of amplitude-frequency information in the radio frequency signal by using a preset amplitude-frequency characteristic identification model, and obtaining the vector weight of each characteristic vector; wherein the vector weights comprise a stabilization coefficient for characterizing a distortion rate of each feature vector and an association coefficient for characterizing an association of each feature vector with other vectors in the magnitude-frequency information.
Step S222, according to the vector weight of each feature vector, encoding the vector weight of each feature vector by using the signal encoding library and obtaining a conversion factor of the spectrum vector corresponding to each feature vector, where the conversion factor is used to represent a weighting coefficient when each feature vector is converted into a frequency vector.
Step S223, respectively judging whether the first matching degree of each feature vector and the distribution diagram is greater than the second matching degree from the corresponding spectrum vector to the distribution diagram according to the conversion factor of each spectrum vector and the feature vector corresponding to each spectrum vector;
step S224, if yes, obtaining a conversion factor of the feature vector corresponding to the frequency spectrum vector as a frequency map conversion base number of the feature vector; if not, keeping the vector weight of the feature vector unchanged; judging whether the size of the overall stability change of all the characteristic vectors of the amplitude-frequency information in the radio frequency signal before and after the judgment is smaller than a preset reference value or not; if the amplitude information is smaller than the reference stability coefficient, determining the stability coefficients of all the characteristic vectors of the amplitude information in the radio frequency signal as the reference stability coefficients meeting the requirements; determining the conversion base number of the frequency map of each feature vector according to the reference stability coefficient; and if not, returning to the step of encoding the vector weight of each eigenvector by using the signal encoding library and obtaining the conversion factor of the spectrum vector corresponding to each eigenvector.
Step S225, determining frequency coding information corresponding to each feature vector from the signal coding library according to the frequency map conversion base number of each feature vector, and generating an ultrasonic spectrogram based on the frequency coding information.
In this embodiment, based on the above steps, frequency coding information corresponding to each eigenvector can be determined based on the obtained signal coding library and the result of performing feature analysis on the radio frequency signal, and then the ultrasonic spectrogram is generated based on the frequency coding information, so that accuracy of analyzing the radio frequency signal can be ensured to avoid distortion of the ultrasonic spectrogram.
On the basis of the above, in order to accurately fit the amplitude curve according to the ultrasonic spectrogram, in step S23, the fitting of the amplitude curve according to the ultrasonic spectrogram specifically includes the following steps.
Step S2311, obtaining amplitude information of the ultrasonic spectrogram, wherein the amplitude information includes a plurality of ultrasonic amplitudes and time information corresponding to each ultrasonic amplitude.
Step S2312, obtaining a fitting weight corresponding to the amplitude information; wherein, the obtaining of the fitting weight corresponding to the amplitude information specifically includes: acquiring time-frequency correlation coefficients of all ultrasonic amplitudes in the amplitude information, and performing statistics; taking the time-frequency correlation coefficient with the maximum specific gravity as the fitting weight; the time-frequency correlation coefficient is used for describing the amplitude variation trend of each ultrasonic amplitude in the time dimension.
Step S2313, splitting the amplitude information according to the fitting weight to obtain an amplitude unit of the amplitude information; the amplitude unit splitting the amplitude information according to the fitting weight to obtain the amplitude information specifically includes: splitting the amplitude information according to the fitting weight through a first preset splitting rule or a second preset splitting rule to obtain an amplitude unit of the amplitude information; wherein, the first preset splitting rule specifically comprises: obtaining an amplitude cluster in which a plurality of ultrasonic amplitudes continuously increasing or continuously decreasing exist in the amplitude information, and sequentially splitting the ultrasonic amplitudes according to a continuously increasing or continuously decreasing gradient and a continuously increasing or continuously decreasing accumulated value until fluctuation weights corresponding to the upper limit values of the amplitudes of the plurality of continuously increasing or continuously decreasing ultrasonic amplitudes in the amplitude information are the fitting weights; wherein the second preset splitting rule specifically includes: determining three weights of the amplitude weight, the moment weight and the amplitude moment weight of each ultrasonic amplitude in the amplitude information, traversing all the ultrasonic amplitudes through a preset iteration traversal rule to find a target amplitude weight corresponding to the median of the ultrasonic amplitudes, a target moment weight and a target ultrasonic amplitude corresponding to the target amplitude moment weight, and splitting the amplitude information by taking the target ultrasonic amplitude as a splitting midpoint.
Step S2314, segmenting the ultrasonic spectrogram according to the amplitude unit of the amplitude information; and generating a distribution track expressing the size and the sequence of each amplitude unit in the ultrasonic spectrogram according to the divided ultrasonic spectrogram, and fitting and generating the amplitude curve according to the distribution track.
Based on the above, the fitting weight corresponding to the amplitude information of the ultrasonic spectrogram can be analyzed, so that the amplitude unit of the amplitude information is determined, the ultrasonic spectrogram is divided based on the amplitude unit, then the distribution track expressing the size and the sequence of each amplitude unit in the ultrasonic spectrogram is generated, and finally, the amplitude curve is generated by fitting according to the distribution track, so that the amplitude curve can be accurately fitted according to the ultrasonic spectrogram.
In practical applications, in step S23, the determining, based on the iterative relationship between each curve node in the amplitude curve and its adjacent curve nodes, multiple sets of curve features corresponding to the amplitude curve may specifically include the following.
Step S2321, determining a two-dimensional coordinate value of each curve node in the amplitude curve.
Step S2322, according to each two-dimensional coordinate value, a first distance of each curve node in the coordinate system corresponding to the amplitude curve from a first curve node adjacent to the curve node and a second distance of a second curve node adjacent to the curve node in the coordinate system corresponding to the amplitude curve are determined.
Step S2323, for each curve node, determining whether a difference between the first distance and the second distance corresponding to the curve node is smaller than a set value, and when the difference between the first distance and the second distance corresponding to the node is smaller than the set value, determining that the curve node is an iterable node.
Step S2324, determining whether a plurality of continuous iterable nodes exist in the amplitude curve, if yes, respectively calculating a third distance between each iterable node in the plurality of iterable nodes and a first curve node in the amplitude curve, and dividing the amplitude curve based on each calculated third distance to obtain a plurality of groups of curve segments, where each group of curve segments includes at least one iterable node.
Step S2325, extracting the curve characteristics corresponding to each curve segment according to the relative position of the iterable nodes in each curve segment in the curve segment.
It can be understood that, based on steps S2321-S2325, the iteration condition of each curve node in the amplitude curve can be analyzed and judged, so that multiple groups of curve features corresponding to the amplitude curve are accurately determined, and a reliable judgment basis is provided for subsequent flaw detection diagnosis.
When the operation data list is obtained, it is necessary to distinguish between an operating state and a non-operating state of the extraction device, so as to ensure that the operation data list corresponds to the extraction device in the operating state, and for this purpose, in step S24, the operation data list of the extraction device corresponding to the set time period is obtained from the operation data storage device of the extraction device communicated with the oil and gas pipeline, which may specifically include the following contents.
Step S241, obtaining the operating signal trigger condition of the operating data storage device and each operating data packet.
Step S242, determining, according to the operating data packets and the state parameters of the operating data storage device in the operating state form, a consistency comparison result between each operating data packet of the operating data storage device in the non-operating state form and each operating data packet of the operating data storage device in the operating state form under the condition that it is determined that the operating data storage device includes the operating state form according to the operating signal trigger condition.
Step S243, transferring the running data packet of the running data storage device in the non-working state form, which is consistent with the running data packet in the working state form, to the working state form.
Step S244, determining a comparison result of consistency between the operation data packets of the operation data storage device in the non-operating state form according to the operation data packets of the operation data storage device in the operating state form and the state parameters thereof, when the operation data storage device includes a plurality of operation data packets in the non-operating state form.
And step S245, filtering the operation data packets in the non-working state form according to the consistency comparison result between the operation data packets.
Step S246, setting transfer information for each running data packet retained after the filtering according to the running data packet of the running data storage device in the working state form and the state parameter thereof, and transferring each running data packet retained after the filtering to the working state form based on the transfer information.
Step S247, generating the operation data list according to all the operation data packets in the working state form.
In this embodiment, through the above steps, the operation data packets of the extraction device in the working state and the non-working state can be analyzed, so that the operation data packets in the working state form are supplemented and perfected, the accuracy of the operation data packets in the working state form is ensured, and the operation data list is accurately determined.
In step S25, the determining the operation characteristics of the extraction device from the operation data list may specifically include the following.
Step S2511, caching the operation data list into a preset caching interval and copying the operation data list into a preset dynamic storage space, where the operation data list in the caching interval is not updatable and the operation data list in the dynamic storage space is updatable.
Step S2512, receiving target data updated by the operating data storage device at regular time, and updating the operating data list located in the dynamic storage space based on the target data to obtain a target data list.
Step S2513, data extraction is carried out on the target data list according to a preset extraction rule, so as to obtain working condition parameters which are included in the target data list and used for representing the operation state change of the extraction equipment, wherein the working condition parameters comprise a gas pressure value and an operation current value of the extraction equipment; the extraction rule is obtained by performing list structure analysis on the running data list located in the cache interval.
Step S2514, determining a variation trend of the operating condition parameter in the operating data list located in the dynamic storage space, mapping the variation trend to the list structure distribution map corresponding to the operating parameter list located in the cache region, obtaining a target vector corresponding to the variation trend, and obtaining the operating characteristics of the extraction device based on the target vector.
In this embodiment, through step S2511 to step S2514, the update state of the operation data list can be considered, so as to accurately determine the operation characteristics of the extraction device, and provide an accurate and reliable judgment basis for subsequent flaw detection identification.
In particular implementation, in order to ensure accurate flaw detection of the oil and gas pipeline 30, in step S25, the performing feature recognition on the operation features and the multiple sets of curve features to generate a flaw detection result of the oil and gas pipeline may specifically include the following.
Step S2521, respectively fusing the first vectors corresponding to the operating features with the second vectors corresponding to each group of curve features to obtain third vectors, where the vector dimensions of the first vectors are the same as those of the second vectors, and when the first vectors and each second vector are fused, the vector values of the first vectors and each second vector at the same vector dimension position are weighted difference or weighted sum.
Step S2522, inputting each third vector into a pre-constructed convolutional neural network, and obtaining a flaw detection result output by the convolutional neural network, wherein the flaw detection result comprises damage positions and damage degrees of the oil and gas pipelines, the damage positions and the damage degrees are stored in the detection equipment in a numerical value pair mode, the convolutional neural network is obtained through training of a training set, the training set comprises different damage positions and different damage degrees corresponding to different-size reference oil and gas pipelines, the training set is packaged in a reference vector mode, the vector dimension of the reference vector is the same as the vector dimension of the third vector, and the convolutional neural network calculates the cosine distance between each third vector and each reference vector in the training set to determine the flaw detection result.
It can be understood that through above-mentioned step, can carry out feature recognition to the third vector that the second vector that corresponds according to the first vector that the operation characteristic corresponds and every group curve feature fuses based on the convolutional neural network to determine oil gas pipeline 40's the result of detecting a flaw, so, not only can detect a flaw accurately oil gas pipeline 30, can also store the position of detecting a flaw and the damage degree that the result of detecting a flaw corresponds, thereby subsequent fault detection of being convenient for.
On the basis of the above, please refer to fig. 3, which is a block diagram of a safety inspection device 101 for a drilling platform according to an embodiment of the present invention, the safety inspection device 101 for a drilling platform may include the following modules.
The receiving module 1011 is configured to receive a radio frequency signal sent by an ultrasonic transceiver, where the radio frequency signal is obtained by converting a received second ultrasonic wave, and the second ultrasonic wave is an echo formed by a reflected echo at an oil-gas pipeline by a first ultrasonic wave transmitted to the oil-gas pipeline by the ultrasonic transceiver.
An analyzing module 1012, configured to analyze the radio frequency signal according to a signal conversion protocol negotiated with the ultrasonic transceiver in advance, so as to obtain an ultrasonic spectrogram corresponding to the second ultrasonic wave.
And a fitting module 1013 configured to fit an amplitude curve according to the ultrasonic spectrogram, and determine a plurality of sets of curve features corresponding to the amplitude curve based on an iterative relationship between each curve node in the amplitude curve and its adjacent curve nodes.
An obtaining module 1014, configured to obtain, from an operation data storage device of an extraction device communicated with the oil and gas pipeline, an operation data list of the extraction device corresponding to a set time period, where the set time period is a time period from a first time to a second time, the first time is a time when the ultrasonic transceiver transmits the first ultrasonic wave to the oil and gas pipeline, and the second time is a time when the ultrasonic transceiver receives the second ultrasonic wave reflected by the first ultrasonic wave at the oil and gas pipeline.
An identifying module 1015, configured to determine the operation characteristics of the extraction device from the operation data list, and perform characteristic identification on the operation characteristics and the multiple sets of curve characteristics to generate a flaw detection result of the oil and gas pipeline.
Embodiments of the present invention also provide a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the above-mentioned drilling platform safety detection method.
The embodiment of the invention also provides a processor, wherein the processor is used for running the program, and the drilling platform safety detection method is executed when the program runs.
In this embodiment, as shown in fig. 4, the detection device 10 includes at least one processor 121, and a memory 122 and a bus 123 connected to the processor 121. Wherein the processor 121 and the memory 122 communicate with each other via a bus 123. The processor 121 is configured to call program instructions in the memory 122 to perform the above-described rig safety detection method.
To sum up, the drilling platform safety detection method, the drilling platform safety detection device and the drilling platform safety detection equipment provided by the embodiment of the invention can analyze the radio-frequency signals sent by the ultrasonic transceiver to obtain the ultrasonic spectrogram, further fit the amplitude curve and determine multiple groups of curve characteristics of the amplitude curve, and then perform characteristic identification by combining the operation characteristics corresponding to the operation data list of the extraction equipment communicated with the oil-gas pipeline, so as to generate the flaw detection result of the oil-gas pipeline. So, can realize detecting a flaw to the oil gas pipeline at the ultrasonic wave aspect, and then discern the slight damage in the oil gas pipeline, so, even if oil gas pipeline does not appear oil gas and reveals, still can accurately detect a flaw to the oil gas pipeline through above-mentioned scheme.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, cloud detection devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing cloud detection apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing cloud detection apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a cloud detection device includes one or more processors (CPUs), memory, and a bus. The cloud detection device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), random access memory with other feature weights (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic tape cassettes, magnetic tape disk storage or other magnetic storage cloud detection devices, or any other non-transmission medium that can be used to store information that can be matched by a computing cloud detection device. As defined herein, computer readable media does not include transitory computer readable media such as modulated data signals and carrier waves.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or cloud detection apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or cloud detection apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or cloud detection device that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (4)

1. A drilling platform safety detection method is applied to detection equipment, wherein the detection equipment is communicated with ultrasonic receiving and transmitting equipment and extraction equipment, and the extraction equipment is communicated with an oil and gas pipeline, and the method at least comprises the following steps:
receiving a radio frequency signal sent by ultrasonic transceiver equipment, wherein the radio frequency signal is obtained by the ultrasonic transceiver equipment through conversion according to received second ultrasonic waves, and the second ultrasonic waves are reflected echoes formed at an oil-gas pipeline by first ultrasonic waves transmitted to the oil-gas pipeline by the ultrasonic transceiver equipment;
analyzing the radio frequency signal according to a signal conversion protocol negotiated with the ultrasonic transceiver in advance to obtain an ultrasonic spectrogram corresponding to the second ultrasonic wave; the method specifically comprises the following steps: acquiring a signal coding library according to path information of the signal coding library included in the signal conversion protocol, and coding the radio-frequency signal according to the signal coding library to obtain a distribution map of amplitude-frequency information in the radio-frequency signal; identifying and obtaining the characteristic vectors of amplitude-frequency information in the radio frequency signal by using a preset amplitude-frequency characteristic identification model, and obtaining the vector weight of each characteristic vector; wherein the vector weight comprises a stability coefficient for characterizing the distortion rate of each feature vector and an association coefficient for characterizing the association of each feature vector with other vectors in the magnitude-frequency information; according to the vector weight of each eigenvector, the vector weight of each eigenvector is coded by using the signal coding library, and a conversion factor of a spectrum vector corresponding to each eigenvector is obtained, wherein the conversion factor is used for representing a weighting coefficient when each eigenvector is converted into a frequency vector; respectively judging whether the first matching degree of each feature vector and the distribution diagram is greater than the second matching degree of each corresponding spectrum vector to the distribution diagram or not according to the conversion factor of each spectrum vector and the feature vector corresponding to each spectrum vector; if so, acquiring a conversion factor of the frequency spectrum vector corresponding to the feature vector as a frequency map conversion base number of the feature vector; if not, keeping the vector weight of the feature vector unchanged; judging whether the size of the overall stability change of all the characteristic vectors of the amplitude-frequency information in the radio frequency signal before and after the judgment is smaller than a preset reference value or not; if the amplitude information is smaller than the reference stability coefficient, determining the stability coefficients of all the characteristic vectors of the amplitude information in the radio frequency signal as the reference stability coefficients meeting the requirements; determining the conversion base number of the frequency map of each feature vector according to the reference stability coefficient; if not, returning to the step of encoding the vector weight of each eigenvector by using the signal encoding library and obtaining the conversion factor of the frequency spectrum vector corresponding to each eigenvector; determining frequency coding information corresponding to each feature vector from the signal coding library according to the frequency map conversion base number of each feature vector, and generating an ultrasonic frequency spectrogram based on the frequency coding information;
fitting an amplitude curve according to the ultrasonic spectrogram, which specifically comprises: acquiring amplitude information of the ultrasonic spectrogram, wherein the amplitude information comprises a plurality of ultrasonic amplitudes and time information corresponding to each ultrasonic amplitude; acquiring a fitting weight corresponding to the amplitude information; wherein, the obtaining of the fitting weight corresponding to the amplitude information specifically includes: acquiring time-frequency correlation coefficients of all ultrasonic amplitudes in the amplitude information, and performing statistics; taking the time-frequency correlation coefficient with the maximum specific gravity as the fitting weight; the time-frequency correlation coefficient is used for describing the amplitude variation trend of each ultrasonic amplitude in the time dimension; splitting the amplitude information according to the fitting weight to obtain an amplitude unit of the amplitude information; the amplitude unit splitting the amplitude information according to the fitting weight to obtain the amplitude information specifically includes: splitting the amplitude information according to the fitting weight through a first preset splitting rule or a second preset splitting rule to obtain an amplitude unit of the amplitude information; wherein, the first preset splitting rule specifically comprises: obtaining an amplitude cluster in which a plurality of ultrasonic amplitudes continuously increasing or continuously decreasing exist in the amplitude information, and sequentially splitting the ultrasonic amplitudes according to a continuously increasing or continuously decreasing gradient and a continuously increasing or continuously decreasing accumulated value until fluctuation weights corresponding to the upper limit values of the amplitudes of the plurality of continuously increasing or continuously decreasing ultrasonic amplitudes in the amplitude information are the fitting weights; wherein the second preset splitting rule specifically includes: determining three weights of amplitude weight, moment weight and amplitude moment weight of each ultrasonic amplitude in the amplitude information, traversing all ultrasonic amplitudes through a preset iteration traversal rule to find a target amplitude weight corresponding to a median of the ultrasonic amplitudes, a target moment weight and a target ultrasonic amplitude corresponding to the target amplitude moment weight, and splitting the amplitude information by taking the target ultrasonic amplitude as a splitting midpoint; dividing the ultrasonic spectrogram according to the amplitude unit of the amplitude information; generating a distribution track expressing the size and the sequence of each amplitude unit in the ultrasonic spectrogram according to the divided ultrasonic spectrogram, and fitting to generate the amplitude curve according to the distribution track;
and determining a plurality of groups of curve characteristics corresponding to the amplitude curve based on the iterative relationship between each curve node and the adjacent curve nodes in the amplitude curve, which specifically comprises the following steps: determining a two-dimensional coordinate value of each curve node in the amplitude curve; determining a first distance between each curve node and a first curve node adjacent to the curve node in a coordinate system corresponding to the amplitude curve and a second distance between each curve node adjacent to the curve node and the amplitude curve according to each two-dimensional coordinate value; judging whether the difference value between the first distance and the second distance corresponding to each curve node is smaller than a set value or not aiming at each curve node, and determining the curve node as an iterable node when the difference value between the first distance and the second distance corresponding to the node is smaller than the set value; extracting curve characteristics corresponding to each curve segment according to the relative position of the iterable nodes in each curve segment in the curve segment;
the method comprises the following steps of obtaining an operation data list of the extraction equipment corresponding to a set time period from operation data storage equipment of the extraction equipment communicated with the oil-gas pipeline, and specifically comprises the following steps: acquiring a working signal trigger condition and each running data packet of the running data storage equipment; under the condition that the operating data storage device is determined to contain the working state form according to the working signal triggering condition, determining consistency comparison results between each operating data packet of the operating data storage device under the non-working state form and each operating data packet of the operating data storage device under the working state form according to the operating data packet of the operating data storage device under the working state form and the state parameters of the operating data packet; transferring the running data packets of the running data storage device in the non-working state form, which are consistent with the running data packets in the working state form, to the working state form; under the condition that the operating data storage device contains a plurality of operating data packets in the non-operating state form, determining consistency comparison results of the operating data storage device among the operating data packets in the non-operating state form according to the operating data packets and state parameters of the operating data storage device in the operating state form; filtering each operation data packet in the non-working state form according to the consistency comparison result between each operation data packet; setting transfer information for each running data packet reserved after filtering according to the running data packet of the running data storage device in the working state form and the state parameters of the running data packet, and transferring each running data packet reserved after filtering to the working state form based on the transfer information; generating the operating data list according to all operating data packets in the working state form; the set time interval is a time interval between a first time and a second time, the first time is a time when the ultrasonic transceiver transmits the first ultrasonic wave to the oil and gas pipeline, and the second time is a time when the ultrasonic transceiver receives the second ultrasonic wave reflected by the first ultrasonic wave at the oil and gas pipeline;
determining the operation characteristics of the extraction device from the operation data list, which specifically includes: caching the running data list into a preset caching interval and copying the running data list into a preset dynamic storage space, wherein the running data list in the caching interval cannot be updated, and the running data list in the dynamic storage space can be updated; receiving target data updated by the running data storage equipment at regular time, and updating a running data list in the dynamic storage space based on the target data to obtain a target data list; performing data extraction on the target data list according to a preset extraction rule to obtain working condition parameters which are included in the target data list and used for representing the operation state change of the extraction equipment, wherein the working condition parameters comprise a gas pressure value and an operation current value of the extraction equipment; the extraction rule is obtained by performing list structure analysis on the running data list in the cache interval; determining the variation trend of the working condition parameters in an operation data list in the dynamic storage space, mapping the variation trend to a list structure distribution diagram corresponding to an operation parameter list in the cache interval to obtain a target vector corresponding to the variation trend, and obtaining the operation characteristics of the extraction equipment based on the target vector;
and carrying out characteristic identification on the operation characteristics and the multiple groups of curve characteristics to generate a flaw detection result of the oil and gas pipeline, and specifically comprising the following steps: respectively fusing the first vectors corresponding to the operating features with the second vectors corresponding to each group of curve features to obtain third vectors, wherein the vector dimensions of the first vectors are the same as those of the second vectors, and when the first vectors and each second vector are fused, the vector values of the first vectors and each second vector at the same vector dimension position are weighted difference or weighted sum; inputting each third vector into a pre-built convolutional neural network, and acquiring a flaw detection result output by the convolutional neural network, wherein the flaw detection result comprises the damage position and the damage degree of the oil and gas pipeline, the damage position and the damage degree are stored in the detection equipment in a numerical value pair mode, the convolutional neural network is obtained through training of a training set, the training set comprises different damage positions and different damage degrees corresponding to different sizes of reference oil and gas pipelines, the training set is packaged in a reference vector mode, the vector dimension of the reference vector is the same as that of the third vector, and the convolutional neural network calculates the cosine distance between each third vector and each reference vector in the training set to determine the flaw detection result.
2. A drilling platform safety inspection device, comprising:
the receiving module is used for receiving a radio frequency signal sent by ultrasonic transceiver equipment, wherein the radio frequency signal is obtained by the ultrasonic transceiver equipment through conversion according to received second ultrasonic waves, and the second ultrasonic waves are reflected echoes formed at an oil-gas pipeline by first ultrasonic waves emitted to the oil-gas pipeline by the ultrasonic transceiver equipment;
an analysis module, configured to analyze the radio frequency signal according to a signal conversion protocol pre-negotiated with the ultrasonic transceiver to obtain an ultrasonic spectrogram corresponding to the second ultrasonic wave, and specifically configured to: acquiring a signal coding library according to path information of the signal coding library included in the signal conversion protocol, and coding the radio-frequency signal according to the signal coding library to obtain a distribution map of amplitude-frequency information in the radio-frequency signal; identifying and obtaining the characteristic vectors of amplitude-frequency information in the radio frequency signal by using a preset amplitude-frequency characteristic identification model, and obtaining the vector weight of each characteristic vector; wherein the vector weight comprises a stability coefficient for characterizing the distortion rate of each feature vector and an association coefficient for characterizing the association of each feature vector with other vectors in the magnitude-frequency information; according to the vector weight of each eigenvector, the vector weight of each eigenvector is coded by using the signal coding library, and a conversion factor of a spectrum vector corresponding to each eigenvector is obtained, wherein the conversion factor is used for representing a weighting coefficient when each eigenvector is converted into a frequency vector; respectively judging whether the first matching degree of each feature vector and the distribution diagram is greater than the second matching degree of each corresponding spectrum vector to the distribution diagram or not according to the conversion factor of each spectrum vector and the feature vector corresponding to each spectrum vector; if so, acquiring a conversion factor of the frequency spectrum vector corresponding to the feature vector as a frequency map conversion base number of the feature vector; if not, keeping the vector weight of the feature vector unchanged; judging whether the size of the overall stability change of all the characteristic vectors of the amplitude-frequency information in the radio frequency signal before and after the judgment is smaller than a preset reference value or not; if the amplitude information is smaller than the reference stability coefficient, determining the stability coefficients of all the characteristic vectors of the amplitude information in the radio frequency signal as the reference stability coefficients meeting the requirements; determining the conversion base number of the frequency map of each feature vector according to the reference stability coefficient; if not, returning to the step of encoding the vector weight of each eigenvector by using the signal encoding library and obtaining the conversion factor of the frequency spectrum vector corresponding to each eigenvector; determining frequency coding information corresponding to each feature vector from the signal coding library according to the frequency map conversion base number of each feature vector, and generating an ultrasonic frequency spectrogram based on the frequency coding information;
a fitting module, configured to fit an amplitude curve according to the ultrasonic spectrogram, and determine, based on an iterative relationship between each curve node in the amplitude curve and an adjacent curve node thereof, a plurality of sets of curve features corresponding to the amplitude curve, and specifically configured to:
acquiring amplitude information of the ultrasonic spectrogram, wherein the amplitude information comprises a plurality of ultrasonic amplitudes and time information corresponding to each ultrasonic amplitude; acquiring a fitting weight corresponding to the amplitude information; wherein, the obtaining of the fitting weight corresponding to the amplitude information specifically includes: acquiring time-frequency correlation coefficients of all ultrasonic amplitudes in the amplitude information, and performing statistics; taking the time-frequency correlation coefficient with the maximum specific gravity as the fitting weight; the time-frequency correlation coefficient is used for describing the amplitude variation trend of each ultrasonic amplitude in the time dimension; splitting the amplitude information according to the fitting weight to obtain an amplitude unit of the amplitude information; the amplitude unit splitting the amplitude information according to the fitting weight to obtain the amplitude information specifically includes: splitting the amplitude information according to the fitting weight through a first preset splitting rule or a second preset splitting rule to obtain an amplitude unit of the amplitude information; wherein, the first preset splitting rule specifically comprises: obtaining an amplitude cluster in which a plurality of ultrasonic amplitudes continuously increasing or continuously decreasing exist in the amplitude information, and sequentially splitting the ultrasonic amplitudes according to a continuously increasing or continuously decreasing gradient and a continuously increasing or continuously decreasing accumulated value until fluctuation weights corresponding to the upper limit values of the amplitudes of the plurality of continuously increasing or continuously decreasing ultrasonic amplitudes in the amplitude information are the fitting weights; wherein the second preset splitting rule specifically includes: determining three weights of amplitude weight, moment weight and amplitude moment weight of each ultrasonic amplitude in the amplitude information, traversing all ultrasonic amplitudes through a preset iteration traversal rule to find a target amplitude weight corresponding to a median of the ultrasonic amplitudes, a target moment weight and a target ultrasonic amplitude corresponding to the target amplitude moment weight, and splitting the amplitude information by taking the target ultrasonic amplitude as a splitting midpoint; dividing the ultrasonic spectrogram according to the amplitude unit of the amplitude information; generating a distribution track expressing the size and the sequence of each amplitude unit in the ultrasonic spectrogram according to the divided ultrasonic spectrogram, and fitting to generate the amplitude curve according to the distribution track;
determining a two-dimensional coordinate value of each curve node in the amplitude curve; determining a first distance between each curve node and a first curve node adjacent to the curve node in a coordinate system corresponding to the amplitude curve and a second distance between each curve node adjacent to the curve node and the amplitude curve according to each two-dimensional coordinate value; judging whether the difference value between the first distance and the second distance corresponding to each curve node is smaller than a set value or not aiming at each curve node, and determining the curve node as an iterable node when the difference value between the first distance and the second distance corresponding to the node is smaller than the set value; extracting curve characteristics corresponding to each curve segment according to the relative position of the iterable nodes in each curve segment in the curve segment;
an obtaining module, configured to obtain an operation data list of an extraction device corresponding to a set time period from an operation data storage device of the extraction device communicated with the oil and gas pipeline, where the set time period is a time period from a first time to a second time, the first time is a time when the ultrasonic transceiver transmits the first ultrasonic wave to the oil and gas pipeline, and the second time is a time when the ultrasonic transceiver receives the second ultrasonic wave reflected by the first ultrasonic wave at the oil and gas pipeline, and specifically configured to: acquiring a working signal trigger condition and each running data packet of the running data storage equipment; under the condition that the operating data storage device is determined to contain the working state form according to the working signal triggering condition, determining consistency comparison results between each operating data packet of the operating data storage device under the non-working state form and each operating data packet of the operating data storage device under the working state form according to the operating data packet of the operating data storage device under the working state form and the state parameters of the operating data packet; transferring the running data packets of the running data storage device in the non-working state form, which are consistent with the running data packets in the working state form, to the working state form; under the condition that the operating data storage device contains a plurality of operating data packets in the non-operating state form, determining consistency comparison results of the operating data storage device among the operating data packets in the non-operating state form according to the operating data packets and state parameters of the operating data storage device in the operating state form; filtering each operation data packet in the non-working state form according to the consistency comparison result between each operation data packet; setting transfer information for each running data packet reserved after filtering according to the running data packet of the running data storage device in the working state form and the state parameters of the running data packet, and transferring each running data packet reserved after filtering to the working state form based on the transfer information; generating the operating data list according to all operating data packets in the working state form;
the identification module is used for determining the operation characteristics of the extraction equipment from the operation data list and carrying out characteristic identification on the operation characteristics and the multiple groups of curve characteristics to generate a flaw detection result of the oil and gas pipeline; the method is specifically used for:
caching the running data list into a preset caching interval and copying the running data list into a preset dynamic storage space, wherein the running data list in the caching interval cannot be updated, and the running data list in the dynamic storage space can be updated; receiving target data updated by the running data storage equipment at regular time, and updating a running data list in the dynamic storage space based on the target data to obtain a target data list; performing data extraction on the target data list according to a preset extraction rule to obtain working condition parameters which are included in the target data list and used for representing the operation state change of the extraction equipment, wherein the working condition parameters comprise a gas pressure value and an operation current value of the extraction equipment; the extraction rule is obtained by performing list structure analysis on the running data list in the cache interval; determining the variation trend of the working condition parameters in an operation data list in the dynamic storage space, mapping the variation trend to a list structure distribution diagram corresponding to an operation parameter list in the cache interval to obtain a target vector corresponding to the variation trend, and obtaining the operation characteristics of the extraction equipment based on the target vector;
respectively fusing the first vectors corresponding to the operating features with the second vectors corresponding to each group of curve features to obtain third vectors, wherein the vector dimensions of the first vectors are the same as those of the second vectors, and when the first vectors and each second vector are fused, the vector values of the first vectors and each second vector at the same vector dimension position are weighted difference or weighted sum; inputting each third vector into a pre-built convolutional neural network, and acquiring a flaw detection result output by the convolutional neural network, wherein the flaw detection result comprises the damage position and the damage degree of the oil and gas pipeline, the damage position and the damage degree are stored in the detection equipment in a numerical value pair mode, the convolutional neural network is obtained through training of a training set, the training set comprises different damage positions and different damage degrees corresponding to different sizes of reference oil and gas pipelines, the training set is packaged in a reference vector mode, the vector dimension of the reference vector is the same as that of the third vector, and the convolutional neural network calculates the cosine distance between each third vector and each reference vector in the training set to determine the flaw detection result.
3. A detection apparatus, comprising: a processor and a memory and bus connected to the processor; the processor and the memory are communicated with each other through the bus; the processor is configured to invoke a computer program in the memory to perform the rig safety inspection method of claim 1.
4. A computer-readable storage medium, characterized in that it has a program stored thereon, which when executed by a processor, implements the rig safety inspection method of claim 1.
CN202010133511.6A 2020-03-02 2020-03-02 Safety detection method, device and detection equipment for drilling platform Active CN111322524B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202010133511.6A CN111322524B (en) 2020-03-02 2020-03-02 Safety detection method, device and detection equipment for drilling platform
CN202011183474.6A CN112377822A (en) 2020-03-02 2020-03-02 Drilling platform safety detection method and detection equipment based on ultrasonic waves
CN202011188119.8A CN112326791A (en) 2020-03-02 2020-03-02 Safety detection method and detection equipment for drilling platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010133511.6A CN111322524B (en) 2020-03-02 2020-03-02 Safety detection method, device and detection equipment for drilling platform

Related Child Applications (2)

Application Number Title Priority Date Filing Date
CN202011183474.6A Division CN112377822A (en) 2020-03-02 2020-03-02 Drilling platform safety detection method and detection equipment based on ultrasonic waves
CN202011188119.8A Division CN112326791A (en) 2020-03-02 2020-03-02 Safety detection method and detection equipment for drilling platform

Publications (2)

Publication Number Publication Date
CN111322524A CN111322524A (en) 2020-06-23
CN111322524B true CN111322524B (en) 2021-07-09

Family

ID=71168207

Family Applications (3)

Application Number Title Priority Date Filing Date
CN202011183474.6A Withdrawn CN112377822A (en) 2020-03-02 2020-03-02 Drilling platform safety detection method and detection equipment based on ultrasonic waves
CN202011188119.8A Withdrawn CN112326791A (en) 2020-03-02 2020-03-02 Safety detection method and detection equipment for drilling platform
CN202010133511.6A Active CN111322524B (en) 2020-03-02 2020-03-02 Safety detection method, device and detection equipment for drilling platform

Family Applications Before (2)

Application Number Title Priority Date Filing Date
CN202011183474.6A Withdrawn CN112377822A (en) 2020-03-02 2020-03-02 Drilling platform safety detection method and detection equipment based on ultrasonic waves
CN202011188119.8A Withdrawn CN112326791A (en) 2020-03-02 2020-03-02 Safety detection method and detection equipment for drilling platform

Country Status (1)

Country Link
CN (3) CN112377822A (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112507151B (en) * 2020-11-23 2023-02-03 首钢京唐钢铁联合有限责任公司 Pressure data processing method, device, equipment and medium
CN112859725B (en) * 2021-01-04 2022-06-24 中国核电工程有限公司 Monitoring system for status characteristic signals of plant equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102494247A (en) * 2011-10-28 2012-06-13 北京嘉华思创科技有限公司 Gas leakage detection method based on voice frequency characteristic recognition and failure remote detector
CN104792865A (en) * 2015-03-30 2015-07-22 暨南大学 Recognizing and positioning method of small defects of pipelines through ultrasonic guided waves based on fractal dimensions
CN106960126A (en) * 2017-03-28 2017-07-18 联想(北京)有限公司 Data early warning method and equipment

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4704536B2 (en) * 2000-01-20 2011-06-15 株式会社テイエルブイ Liquid level measuring device in pipe and liquid level measuring method
CN101199427A (en) * 2006-12-11 2008-06-18 乐金电子(中国)研究开发中心有限公司 IMCT and supersonic detecting based on it
JP4910769B2 (en) * 2007-02-28 2012-04-04 Ｊｆｅスチール株式会社 Pipe quality control method and manufacturing method
CN102537669B (en) * 2010-12-23 2013-12-04 中国石油天然气股份有限公司 Method and system for detecting pipeline defect based on ultrasonic guided wave focusing
CN103292160B (en) * 2013-06-27 2015-11-18 陕西师范大学 The ultrasonic detection device of pipe leakage and method
CN103836347B (en) * 2014-03-07 2015-07-22 中国石油大学(华东) Leakage monitoring device and method for crude oil gathering pipelines
CN107327713A (en) * 2017-07-10 2017-11-07 天津大学 The ultrasound damage device and method of a kind of water supply line
CN108181059B (en) * 2017-12-27 2019-12-10 钦州学院 Multi-phase flow pipeline leakage sound wave signal identification method based on wavelet signals
CN109977920B (en) * 2019-04-11 2022-06-07 福州大学 Water turbine set fault diagnosis method based on time-frequency spectrogram and convolutional neural network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102494247A (en) * 2011-10-28 2012-06-13 北京嘉华思创科技有限公司 Gas leakage detection method based on voice frequency characteristic recognition and failure remote detector
CN104792865A (en) * 2015-03-30 2015-07-22 暨南大学 Recognizing and positioning method of small defects of pipelines through ultrasonic guided waves based on fractal dimensions
CN106960126A (en) * 2017-03-28 2017-07-18 联想(北京)有限公司 Data early warning method and equipment

Also Published As

Publication number Publication date
CN112377822A (en) 2021-02-19
CN112326791A (en) 2021-02-05
CN111322524A (en) 2020-06-23

Similar Documents

Publication Publication Date Title
CN111322524B (en) Safety detection method, device and detection equipment for drilling platform
US20230167739A1 (en) Method and system for real-time prediction of jamming in tbm tunneling
CN110888126A (en) Unmanned ship information perception system data comprehensive processing method based on multi-source sensor
CN111767957A (en) Method and device for detecting log abnormity, storage medium and electronic equipment
CN110443275A (en) Remove method, equipment and the storage medium of noise
CN111194001A (en) LTE fingerprint positioning correction method, device and system
RU2576341C2 (en) Phase-based tracking
CN117751301A (en) Method, device, equipment and storage medium for processing laser radar point cloud
CN116778329A (en) Urban road underground shallow disease detection method, device, equipment and medium
CN116452574A (en) Gap detection method, system and storage medium based on improved YOLOv7
CN103532931A (en) Method and system for testing transmission performance of data stream, and server
CN103475527B (en) Network management fault reliability analyzing system and method
CN111277953B (en) Communication network stability processing method and system and electronic equipment
CN112612663B (en) Method for reversely solving 1553B bus ICD
CN112561171B (en) Landslide prediction method, device, equipment and storage medium
US20210241074A1 (en) System for generating synthetic digital data for data multiplication
CN103733033A (en) Linear relationship between tracks
CN109061652B (en) Detection efficiency evaluation method of underwater acoustic networking detection system
CN111368905B (en) Signal recovery method and device applied to oil and gas exploration and signal recovery equipment
Pöpperli et al. Realistic ultrasonic environment simulation using conditional generative adversarial networks
CN111007464A (en) Road underground cavity identification method, device and system based on optimal weighting
Moschos et al. Real-Time Validation of Operational Ocean Models Via Eddy-Decting Deep Neural Networks
CN116594018B (en) Helicopter flight obstacle alarm system and method
Concas et al. Proactive Congestion Management
CN117033983B (en) Unmanned ship self-noise detection and identification method and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: No.80 chunman Avenue, Kunming Economic and Technological Development Zone, Yunnan Province, 650011

Applicant after: Zhou Hong

Address before: 266580 China University of Petroleum (Qingdao), No. 66 Changjiang West Road, Huangdao District, Shandong, China

Applicant before: Zhou Hong

CB02 Change of applicant information
TA01 Transfer of patent application right

Effective date of registration: 20210623

Address after: No.8-11, Yandu Avenue, Da'an District, Zigong City, Sichuan Province

Applicant after: SICHUAN SALT GEOLOGY DRILLING TEAM

Address before: No.80 chunman Avenue, Kunming Economic and Technological Development Zone, Yunnan 650011

Applicant before: Zhou Hong

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant