A pipeline safety early warning method and system based on stress detection

Abstract

The present invention relates to the technical field of stress detection, and particularly relates to a pipeline safety early warning method and system based on stress detection. The method includes: obtaining the intensity distribution sequence of the pipeline in the current sampling time period, determining the intensity correlation coefficient of the pipeline based on the intensity values of M intensity sequences, and if it is determined that the intensity correlation coefficient exceeds the preset intensity correlation threshold, then performing pipeline safety early warning; otherwise, determining the amplitude fluctuation value of the detection point based on N intensity values in the intensity sequence of the detection point, and determining the intensity balance degree of the pipeline based on the amplitude fluctuation values of M detection points; determining the damage index of the pipeline based on the intensity distribution sequence, and obtaining the corrected damage prediction value based on the damage index and the intensity balance degree; obtaining the predicted damage threshold interval, and if it is determined that the corrected damage prediction value exceeds the maximum value of the damage threshold interval, then performing pipeline safety early warning; the present invention can realize pipeline safety early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of stress detection, and particularly to a pipeline safety early warning method and system based on stress detection. Background Art

[0002] At present, the common technical means used by chemical enterprises for detecting medium pipeline leakage include smearing soapy water, installing fixed gas detectors, and handheld ultrasonic leak detectors. Due to the concealment of pipeline leakage, the current detection means may have lasted for some time when leakage is discovered. This situation will have an adverse impact on economic costs, personnel safety, environmental protection, etc. These methods have low work efficiency, high operation difficulty, and the implementation difficulty of leakage detection is even higher at night or in an environment with poor visibility.

[0003] During the operation of large units, the support structure and inlet and outlet pipeline systems of the units are always under stress, especially in the case of reciprocating compressors. If the thread fasteners at these parts become loose and are not dealt with in time, or the displacement of the support structure is not detected in time, serious problems such as tripping may occur. Therefore, it is necessary to monitor the excessive deformation state of the thread fastener state to achieve pipeline safety early warning and improve the predictive ability of the safe operation of the unit. Summary of the Invention

[0004] The purpose of the present invention is to provide a pipeline safety early warning method and system based on stress detection, which analyzes the stress detected by stress sensors to achieve pipeline safety early warning and improve the predictive ability of safety early warning.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] In the first aspect, an embodiment of the present invention provides a pipeline safety early warning method based on stress detection, and the method includes the following steps:

[0007] S100, obtaining the intensity distribution sequence of the pipeline in the current sampling time period, where the intensity distribution sequence includes the intensity sequences of M detection points; wherein, the intensity sequence includes N intensity values, and N is the total number of sampling time points in the sampling time period; the M detection points are co-circular and evenly arranged on the flange of the pipeline end face; the intensity distribution sequence is obtained by sampling after photoelectric conversion of the detected optical signal, and the detected optical signal is obtained by stress detection of the M detection points using a stress sensor;

[0008] S200, determining the intensity correlation coefficient of the pipeline based on the intensity values of the M intensity sequences, and if it is determined that the intensity correlation coefficient exceeds the preset intensity correlation threshold, pipeline safety early warning is performed;

[0009] S300. If it is determined that the intensity correlation coefficient does not exceed the preset intensity correlation threshold, then determine the amplitude fluctuation value of the detection point based on N intensity values in the intensity sequence of the detection point, and determine the intensity balance degree of the pipeline based on the amplitude fluctuation values of M such detection points;

[0010] S400. Determine the damage index of the pipeline based on the intensity distribution sequence, and obtain the corrected damage prediction value based on the damage index and the intensity balance degree;

[0011] S500. Obtain the expected damage threshold interval to be constructed. If it is determined that the corrected damage prediction value exceeds the maximum value of the damage threshold interval, then conduct pipeline safety warning.

[0012] Optionally, in S200, the determining the intensity correlation coefficient of the pipeline based on the intensity values of M such intensity sequences includes:

[0013] S210. Group the M intensity sequences in pairs, calculate the Hausdorff distance between the two intensity sequences in each group, and obtain multiple intensity differences;

[0014] S220. After the N intensity values of the two intensity sequences in each group are corresponding one by one according to the sampling time points, calculate the cross-correlation coefficient of the two intensity sequences;

[0015] S230. Calculate multiple correlation coefficients from the intensity differences and cross-correlation coefficients of the two intensity sequences in each group, and use the correlation coefficient with the largest value as the intensity correlation coefficient of the pipeline.

[0016] Optionally, in S300, the determining the amplitude fluctuation value of the detection point based on N intensity values in the intensity sequence of the detection point, and determining the intensity balance degree of the pipeline based on the amplitude fluctuation values of M such detection points includes:

[0017] S310. Obtain N intensity values in the intensity sequences of M detection points;

[0018] S320. For each detection point, calculate the amplitude fluctuation value of the detection point through the following formula:

[0019]

[0020] where Af j is the amplitude fluctuation value of the j-th detection point, Ap j is the intensity value at the peak of the intensity sequence of the j-th detection point, At j is the intensity value at the trough of the intensity sequence of the j-th detection point, A ij is the intensity value of the j-th detection point at the i-th sampling time point, Aavg jis the mean intensity of the j-th detection point, normal represents linear normalization processing, the value range of the amplitude fluctuation value is [0, 1], i = 1, 2,..., N, j = 1, 2,..., M;

[0021] S330, the strength balance degree of the pipeline is calculated through the following formula:

[0022] Bd = max(Af j ) / min(Af j )

[0023] where, Bd is the strength balance degree of the pipeline, max(Af j ) is the maximum value among the amplitude fluctuation values of M detection points, min(Af j ) is the minimum value among the amplitude fluctuation values of M detection points.

[0024] Optionally, in S400, based on the strength distribution sequence, the damage index of the pipeline is determined, and the corrected damage prediction value is obtained based on the damage index and the strength balance degree, including:

[0025] S410, obtain the strength distribution sequence of the current sampling time period, normalize the amplitudes of each sampling time point in the strength distribution sequence to obtain the normalized amplitude of each sampling time point;

[0026] S420, obtain the total number of wave peaks in the strength sequence of each detection point and the reference amplitude of the pipeline, and determine the damage index of the pipeline based on the normalized amplitude of each sampling time point, the total number of wave peaks in the strength sequence of each detection point, and the reference amplitude of the pipeline; where, the reference amplitude of the pipeline represents the critical amplitude when the pipeline is damaged;

[0027] S430, multiply the damage index of the pipeline by the strength balance degree to obtain the corrected damage prediction value.

[0028] Optionally, the damage index of the pipeline is calculated through the following formula:

[0029]

[0030] where, Da is the damage index of the pipeline, Af ij is the normalized amplitude of the j-th detection point at the i-th sampling time point, Afavg is the reference amplitude of the pipeline, max(n j ) is the maximum value among the total number of wave peaks of M detection points, min(n j ) is the minimum value among the total number of wave peaks of M detection points, avg(n j) is the average value among the total number of wave peaks at M detection points, and λ1 and λ2 are weighting coefficients: 0 < λ1 < 1, 0 < λ2 < 1, and λ1 + λ2 = 1.

[0031] Optionally, the damage threshold interval is pre-determined in the following manner:

[0032] S101, apply forces with multiple different test amplitudes to the pipeline, and test the corresponding number of test vibrations when the pipeline changes from being locked to loose;

[0033] S102, construct amplitude combinations based on the test amplitudes and the corresponding number of test vibrations, and determine the test damage index of the pipeline based on multiple said amplitude combinations;

[0034] S103, determine the damage threshold interval based on multiple test damage indices.

[0035] Optionally, the determining the damage threshold interval based on multiple test damage indices includes:

[0036] Determine the mean value and deviation value of the damage index based on multiple test damage indices;

[0037] Determine the damage threshold interval based on the mean value and deviation value of the damage index.

[0038] In a second aspect, an embodiment of the present invention provides a pipeline safety early warning system based on stress detection, and the system includes:

[0039] At least one processor;

[0040] At least one memory for storing at least one program;

[0041] When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in any one of the above.

[0042] The beneficial effects of the present invention are as follows: The present invention discloses a pipeline safety early warning method and system based on stress detection. By obtaining the intensity distribution sequence of the pipeline in the current sampling time period, the intensity correlation coefficient of the pipeline is determined based on the intensity values of M intensity sequences. If it is determined that the intensity correlation coefficient exceeds the preset intensity correlation threshold, pipeline safety early warning is carried out; thus, real-time early warning is performed when the pipeline already has damage. The amplitude fluctuation value of the detection point is determined based on N intensity values in the intensity sequence of the detection point, and the intensity balance degree of the pipeline is determined based on the amplitude fluctuation values of M detection points. The damage index of the pipeline is determined based on the intensity distribution sequence, and the corrected damage prediction value is obtained based on the damage index and the intensity balance degree. Combining the current and previous loss degrees of the pipeline, the final damage index of the pipeline is comprehensively reflected. By obtaining the expected damage threshold interval, if it is determined that the corrected damage prediction value exceeds the maximum value of the damage threshold interval, pipeline safety early warning is carried out. The present invention analyzes the data of the stress detected by the stress sensor, realizes pipeline safety early warning, and improves the prediction ability of safety early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a schematic flow chart of a pipeline safety early warning method based on stress detection in an embodiment of the present invention;

[0045] Figure 2 It is a schematic diagram of the influence of vibration amplitude on pre-tightening force in an embodiment of the present invention;

[0046] Figure 3 It is a structural block diagram of a pipeline safety early warning system based on stress detection in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following will clearly and completely describe the concept, specific structure and technical effects generated by the present invention in combination with the embodiments and the drawings, so as to fully understand the purpose, solution and effects of the present invention. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0048] Elastic stress-luminescent materials refer to materials that exhibit stress-luminescence during elastic deformation, and the stress-luminescence intensity is linearly related to the applied stress. It belongs to non-destructive stress-luminescence, and the stress on an object can be deduced based on the stress-luminescence intensity. After being excited by an external light source, the luminescence intensity of the elastic stress-luminescent material can be completely restored. Due to the characteristics of non-destructive luminescence, repeatability, and force-light conversion sensing of elastic stress-luminescent materials.

[0049] Due to the light-responsive characteristics of elastic stress-luminescent materials, stress sensors made of them can be used for wireless sensing or remote stress distribution observation, and for measuring the stress distribution of irregular or moving objects. Therefore, elastic stress-luminescent materials have potential application value in measuring the stress distribution of mechanical components.

[0050] Based on this, the present invention provides a pipeline safety early warning method and system based on stress detection. By analyzing the stress detected by a stress sensor, pipeline safety early warning is realized, and the predictive ability of safety early warning is improved.

[0051] Refer to Figure 1 and Figure 2 A pipeline safety early warning method based on stress detection provided by the present invention includes the following steps:

[0052] S100, obtaining an intensity distribution sequence of the pipeline in the current sampling time period, where the intensity distribution sequence includes intensity sequences of M detection points; wherein, each intensity sequence includes N intensity values, and N is the total number of sampling time points in the sampling time period; the M detection points are co-circular and evenly arranged on the flange of the pipeline end face; the intensity distribution sequence is obtained by sampling after photoelectric conversion of the detected optical signal, and the detected optical signal is obtained by a stress sensor detecting the stress of the M detection points;

[0053] It should be noted that under normal working conditions of the unit, the connecting end face of the pipeline is uniformly stressed, and the stress of each detection point is generally the same, fluctuating within the stress range; when the threaded fastener becomes loose, the pipeline will shake, and the stress on each detection point is different, resulting in a significant increase or decrease in the stress-luminescence intensity of some detection points; based on this phenomenon, in the embodiments provided by the present invention, pipeline safety early warning is carried out by analyzing and processing the light intensity of each detection point through data processing.

[0054] Specifically, a flange is provided on the connecting end face of the pipeline. The flange is provided with a plurality of circular screw holes, and the centers of the plurality of screw holes are concentric and evenly arranged; a plurality of screw holes are evenly arranged at the connection of the pipeline, and each screw hole is correspondingly provided with an elastic stress luminescent material as a detection point; the light intensity of each detection point is detected by the elastic stress luminescent material provided in each screw hole. A stress sensor based on the elastic stress luminescent material is used to convert the stress magnitude received at the detection point into a detection optical signal of the corresponding light intensity and send it to a processing device (such as a server) in the background; after the processing device converts the detection optical signal into a corresponding analog electrical signal through a photoelectric sensor, the analog electrical signal is amplified in gain, subjected to analog-to-digital conversion and digital sampling to obtain a serialized digital signal, forming an intensity distribution sequence. The intensity distribution sequence includes the intensity sequences of M detection points. By analyzing and processing the intensity values of the digital signals, pipeline safety early warning is realized. In some embodiments, both M and N are positive integers, and M≥3, N≥30.

[0055] S200. Determine the strength correlation coefficient of the pipeline based on the intensity values of the M intensity sequences. If it is determined that the strength correlation coefficient exceeds a preset strength correlation threshold, pipeline safety early warning is performed.

[0056] It should be noted that when some bolts are severely loosened or even fall off, the acting forces on each detection point are significantly different. For example, when a certain bolt is loosened, the stress magnitude at the corresponding position on the flange surface decreases as the pre-tightening force of the corresponding loosened bolt decreases. With different pre-tightening forces applied, the stress change range at the corresponding position of the flange is also different. In this step, by determining the strength correlation coefficient of the M detection points, it is possible to first determine whether there is serious damage to the pipeline and perform pipeline safety early warning when the pipeline has already been damaged. The strength correlation threshold can be preset according to the results calculated in the actual scenario. When ensuring pipeline safety, the strength correlation coefficient does not exceed the preset strength correlation threshold.

[0057] S300. If it is determined that the strength correlation coefficient does not exceed the preset strength correlation threshold, determine the amplitude fluctuation value of the detection point based on the N intensity values in the intensity sequence of the detection point, and determine the strength balance degree of the pipeline based on the amplitude fluctuation values of the M detection points.

[0058] It should be noted that when a certain bolt is loosened, the pipeline will become unbalanced, and the strength balance degree can reflect the early damage of the pipeline.

[0059] S400. Determine the damage index of the pipeline based on the intensity distribution sequence, and obtain a corrected damage prediction value based on the damage index and the strength balance degree.

[0060] It should be noted that the amplitude and frequency reflect the current damage suffered by the pipeline. Combining the current and previous damage degrees of the pipeline, the final damage index of the pipeline is comprehensively reflected.

[0061] S500, obtain the predicted damage threshold interval. If it is determined that the corrected damage prediction value exceeds the maximum value of the damage threshold interval, pipeline safety early warning is carried out.

[0062] It should be noted that the pre-tightening force will rapidly decay with the increase of the vibration amplitude. In the initial stage of bolt loosening, the pre-tightening force drops rapidly, and then shows a regular periodic decay. Therefore, it is necessary to consider the magnitude of the strength correlation coefficient and also the change of the amplitude fluctuation value to identify different stages of bolt loosening and the change of the pre-tightening force between pipelines, so as to obtain an accurate safety early warning.

[0063] In some embodiments, in S200, determining the strength correlation coefficient of the pipeline based on the strength values of the M strength sequences includes:

[0064] S210, group the M strength sequences in pairs of two, calculate the Hausdorff distance between the two strength sequences in each group, and obtain a plurality of strength differences;

[0065] S220, after corresponding the N strength values of the two strength sequences in each group one by one according to the sampling time points, calculate the cross-correlation coefficient of the two strength sequences;

[0066] S230, calculate a plurality of correlation coefficients from the strength differences and cross-correlation coefficients of the two strength sequences in each group, and take the correlation coefficient with the largest value as the strength correlation coefficient of the pipeline.

[0067] In this embodiment, through the strength difference, the consistency of the M detection points can be initially judged, and the situation of too large strength difference can be highlighted. If the strength difference is small, it indicates strong consistency or dislocation, resulting in the false appearance of a small Hausdorff distance. To exclude this possibility, combined with the cross-correlation coefficient, the overall strength distribution situation is obtained, so as to accurately judge the consistency of the M detection points;

[0068] In some embodiments, for two strength sequences X = {x i} and Y = {y i}, x i represents the strength value at the i-th time sampling point in the strength sequence X, and y i represents the strength value at the i-th time sampling point in the strength sequence Y. The correlation coefficient ρxy of the corresponding two detection points is calculated by the following formula:

[0069]

[0070] The correlation coefficient between two detection points is calculated using the formula exp(max(dxy)) + exp(max(ρxy)), where dxy represents the intensity difference between two intensity sequences X = {x i} and Y = {y i}, max(dxy) represents the maximum value among all intensity differences, and max(ρxy) represents the maximum value among all correlation coefficients.

[0071] In some embodiments, in S300, determining the amplitude fluctuation value of the detection point based on N intensity values in the intensity sequence of the detection point, and determining the strength balance degree of the pipeline based on the amplitude fluctuation values of M detection points includes:

[0072] S310, obtaining N intensity values in the intensity sequences of M detection points;

[0073] S320, for each detection point, calculating the amplitude fluctuation value of the detection point through the following formula:

[0074]

[0075] where Af j is the amplitude fluctuation value of the j-th detection point, Ap j is the intensity value at the peak of the intensity sequence of the j-th detection point, At j is the intensity value at the trough of the intensity sequence of the j-th detection point, A ij is the intensity value of the j-th detection point at the i-th sampling time point, Aavg j is the intensity mean of the j-th detection point, normal represents linear normalization processing, and the value range of the amplitude fluctuation value is [0, 1], i = 1, 2,..., N, j = 1, 2,..., M;

[0076] S330, calculating the strength balance degree of the pipeline through the following formula:

[0077] Bd = max(Af j ) / min(Af j )

[0078] where Bd is the strength balance degree of the pipeline, max(Af j ) is the maximum value among the amplitude fluctuation values of M detection points, and min(Af j ) is the minimum value among the amplitude fluctuation values of M detection points.

[0079] In some embodiments, in S400, determining the damage index of the pipeline based on the intensity distribution sequence, and obtaining the corrected damage prediction value based on the damage index and the strength balance degree includes:

[0080] S410. Obtain the intensity distribution sequence of the current sampling time period, normalize the amplitudes of each sampling time point in the intensity distribution sequence to obtain the normalized amplitude of each sampling time point.

[0081] S420. Obtain the total number of wave peaks in the intensity sequence of each detection point and the reference amplitude of the pipeline. Determine the damage index of the pipeline based on the normalized amplitude of each sampling time point, the total number of wave peaks in the intensity sequence of each detection point, and the reference amplitude of the pipeline. Wherein, the reference amplitude of the pipeline represents the critical amplitude when the pipeline is damaged.

[0082] The damage index of the pipeline is calculated by the following formula:

[0083]

[0084] Where Af ij is the normalized amplitude of the j-th detection point at the i-th sampling time point, Afavg is the reference amplitude of the pipeline, max(n j ) is the maximum value among the total number of wave peaks of M detection points, min(n j ) is the minimum value among the total number of wave peaks of M detection points, avg(n j ) is the average value among the total number of wave peaks of M detection points, and λ1, λ2 are weight coefficients: 0 < λ1 < 1, 0 < λ2 < 1, and λ1 + λ2 = 1.

[0085] It should be noted that the greater the amplitude, the stronger the destructive force on the pipeline, and the greater the damage prediction value is reflected. By linearly normalizing the amplitude of each sampling time point, it is mapped to the interval [0, 1]. The reference amplitude that the pipeline can withstand without being damaged is obtained through pre-testing as the reference amplitude of the pipeline. Based on the difference between the amplitude and the reference amplitude of the pipeline, a model of the pipeline loss caused by the amplitude is constructed. The total number of wave peaks is approximated to the number of vibrations. Thus, the damage index of the pipeline is calculated by combining the amplitude and the number of vibrations, which can reflect the cumulative damage of the pipeline caused by the acting forces of different amplitudes.

[0086] S430. Multiply the damage index of the pipeline by the intensity balance degree to obtain the corrected damage prediction value.

[0087] In some embodiments, the damage threshold interval is determined in advance by the following method:

[0088] S101. Apply forces with multiple different test amplitudes to the pipeline and test the corresponding test vibration times when the pipeline changes from being locked to being loose.

[0089] S102. Construct amplitude combinations based on the test amplitudes and the corresponding test vibration times, and determine the test damage index of the pipeline based on multiple said amplitude combinations.

[0090] Specifically, multiple combinations of test amplitudes and corresponding test vibration times are obtained through multiple test trials. For different test trials, forces with different test amplitudes are applied. During the same test, forces with the same test amplitude are applied to M detection points in the pipeline. The test amplitude and the corresponding test vibration times are used as amplitude combinations, and several groups of amplitude combinations are summarized to construct an amplitude set. The test amplitude is linearly normalized and mapped to the interval [0, 1], and then the test damage index of the pipeline is calculated:

[0091] The test damage index is calculated by the following formula:

[0092]

[0093] where Ta avg is the mean value of the test amplitude, and Tf avg is the mean value of the test vibration times; λ3 and λ4 are weight coefficients: 0 < λ3 < 1, 0 < λ4 < 1, and λ3 + λ4 = 1. Ta ij is the test amplitude of the j-th detection point at the i-th sampling time point, Tf j is the test vibration times of the j-th detection point, and T is the total number of amplitude combinations;

[0094] S103. Determine the damage threshold interval based on multiple test damage indices.

[0095] The damage threshold interval is calculated by the following formula:

[0096]

[0097] where k = 1, 2,..., K, K is the total number of test damage indices, and TDa avg is the mean value of the damage index; TDa i is the i-th damage index.

[0098] It should be noted that the damage index reflects the damage degree caused by continuously applying a force with the same amplitude to the pipeline. Since the external force suffered by the pipeline may not be balanced and is usually the superposition of forces with multiple different amplitudes, it is necessary to comprehensively consider this imbalance in the damage to the pipeline. By updating the damage index, the damage degree of the pipeline can be more comprehensively and accurately reflected.

[0099] Corresponding to Figure 1 's method, referring to Figure 3 , an embodiment of the present invention provides a pipeline safety warning system based on stress detection, including:

[0100] At least one processor;

[0101] At least one memory for storing at least one program;

[0102] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method.

[0103] It can be seen that the content in the above method embodiments is applicable to the system embodiments of the present invention. The functions specifically implemented by the system embodiments of the present invention are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0104] In addition, the embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program is stored in a computer-readable storage medium. The processor of the computer device can read the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the above-mentioned method. Similarly, the content in the above method embodiments is applicable to the storage medium embodiments of the present invention. The functions specifically implemented by the storage medium embodiments of the present invention are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0105] Those of ordinary skill in the art can understand that all or some of the methods and systems disclosed above can be implemented as software, firmware, hardware, and their appropriate combinations. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or can be implemented as hardware, or can be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or a non-transitory medium) and a communication medium (or a transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory, or other memory technologies, CD-ROM, digital versatile disc (DVD), or other optical disc storage, magnetic cassette, tape, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium generally includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0106] The above is a specific description of the preferred embodiments of the present disclosure. However, the present disclosure is not limited to the above embodiments. Those skilled in the art can make various equivalent deformations or substitutions without departing from the spirit of the present disclosure, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present disclosure.

Claims

1. A pipeline safety early warning method based on stress detection, characterized in that, The method includes the following steps: S100. Obtain the intensity distribution sequence of the pipeline in the current sampling time period. The intensity distribution sequence includes the intensity sequences of M detection points. Among them, the intensity sequence includes N intensity values, and N is the total number of sampling time points in the sampling time period. The M detection points are co-circular and evenly arranged on the flange of the pipeline end face. The intensity distribution sequence is obtained by sampling after photoelectric conversion of the detection optical signal, and the detection optical signal is obtained by stress detection of the M detection points using a stress sensor. S200. Determine the intensity correlation coefficient of the pipeline based on the intensity values of the M intensity sequences. If it is determined that the intensity correlation coefficient exceeds the preset intensity correlation threshold, pipeline safety warning is performed. S300. If it is determined that the intensity correlation coefficient does not exceed the preset intensity correlation threshold, determine the amplitude fluctuation value of the detection point based on the N intensity values in the intensity sequence of the detection point, and determine the intensity balance degree of the pipeline based on the amplitude fluctuation values of the M detection points. S400. Determine the damage index of the pipeline based on the intensity distribution sequence, and obtain the corrected damage prediction value based on the damage index and the intensity balance degree. S500. Obtain the predicted damage threshold interval. If it is determined that the corrected damage prediction value exceeds the maximum value of the damage threshold interval, pipeline safety warning is performed. The determining the intensity correlation coefficient of the pipeline based on the intensity values of the M intensity sequences includes: S210. Group the M intensity sequences in pairs of two, calculate the Hausdorff distance between the two intensity sequences in each group to obtain a plurality of intensity differences. S220. After the N intensity values of the two intensity sequences in each group are corresponding one by one according to the sampling time points, calculate the cross-correlation coefficient of the two intensity sequences. S230. Calculate a plurality of correlation coefficients from the intensity differences and the cross-correlation coefficients of the two intensity sequences in each group, and use the correlation coefficient with the largest value as the intensity correlation coefficient of the pipeline.

2. The method according to claim 1, wherein In S300, the determining the amplitude fluctuation value of the detection point based on the N intensity values in the intensity sequence of the detection point and determining the intensity balance degree of the pipeline based on the amplitude fluctuation values of the M detection points includes: S310. Obtain the N intensity values in the intensity sequences of the M detection points. S320. For each detection point, calculate the amplitude fluctuation value of the detection point through the following formula: where, Af j is the amplitude fluctuation value of the j-th detection point, Ap j is the intensity value at the peak of the intensity sequence of the j-th detection point, At j is the intensity value at the trough of the intensity sequence of the j-th detection point, A ij is the intensity value of the j-th detection point at the i-th sampling time point, Aavg j is the average intensity of the j-th detection point, normal represents linear normalization processing, the value range of the amplitude fluctuation value is [0, 1], i = 1, 2, …, N, j = 1, 2, …, M; S330. Calculate the intensity balance degree of the pipeline through the following formula: Bd = max(Af j ) / min(Af j ) Among them, Bd is the strength balance degree of the pipeline, and max(Af j ) is the maximum value among the amplitude fluctuation values of M detection points, and min(Af j ) is the minimum value among the amplitude fluctuation values of M detection points.

3. The method according to claim 2, wherein In S400, the determining the damage index of the pipeline based on the intensity distribution sequence and obtaining the corrected damage prediction value based on the damage index and the intensity balance degree includes: S410. Obtain the intensity distribution sequence of the current sampling time period, normalize the amplitudes of each sampling time point in the intensity distribution sequence to obtain the normalized amplitude of each sampling time point. S420. Obtain the total number of wave peaks in the intensity sequence of each detection point and the reference amplitude of the pipeline, and determine the damage index of the pipeline based on the normalized amplitude at each sampling time point, the total number of wave peaks in the intensity sequence of each detection point, and the reference amplitude of the pipeline; wherein, the reference amplitude of the pipeline characterizes the critical amplitude when the pipeline is damaged. S430. Multiply the damage index of the pipeline by the intensity balance degree to obtain a corrected damage prediction value.

4. The method according to claim 3, characterized in that, The damage index of the pipeline is calculated by the following formula: where, Da is the damage index of the pipeline, Af ij is the normalized amplitude of the j-th detection point at the i-th sampling time point, Afavg is the reference amplitude of the pipeline, max(n j ) is the maximum value among the total number of wave peaks of M detection points, min(n j ) is the minimum value among the total number of wave peaks of M detection points, avg(n j ) is the average value among the total number of wave peaks of M detection points, and λ1, λ2 are weighting coefficients: 0 < λ1 < 1, 0 < λ2 < 1, and λ1 + λ2 = 1.

5. The method according to claim 1, wherein The damage threshold interval is determined in advance by the following method: S101. Apply forces with multiple different test amplitudes to the pipeline, and test the corresponding test vibration times when the pipeline changes from being locked to loose. S102. Construct amplitude combinations based on the test amplitudes and the corresponding test vibration times, and determine the test damage index of the pipeline based on multiple said amplitude combinations. S103. Determine the damage threshold interval based on multiple test damage indexes.

6. The method according to claim 5, characterized in that The determining the damage threshold interval based on multiple test damage indexes includes: Determine the mean value and deviation value of the damage index based on multiple test damage indexes. Determine the damage threshold interval based on the mean value and deviation value of the damage index.

7. A pipeline safety early warning system based on stress detection, characterized in that The system includes: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 6.

Images