Pipeline displacement dynamic monitoring and early warning system based on cloud platform

Abstract

The invention discloses a pipeline displacement dynamic monitoring and early warning system based on a cloud platform, and relates to the field of displacement monitoring and early warning, and the system carries out the monitoring and early warning of the displacement of a to-be-monitored pipeline through the displacement data of each displacement detection point on the current to-be-monitored pipeline and the data of a plurality of displacement influence factors. Wherein the center data of each category in the existing measurement point displacement data matrix is calculated, so that a classification basis is provided for subsequently classifying the displacement data of a plurality of displacement measurement points on the to-be-monitored pipeline; by constructing a final displacement deviation level mapping equation, a mapping tool is provided for subsequent mapping of displacement influence factor data of a to-be-monitored pipeline at a future moment; firstly, whether a first alarm is given or not is judged according to displacement data of each measurement point on a to-be-monitored pipeline; and when the first alarm does not need to be performed, whether the second alarm is performed or not is judged from the angle of the displacement influence factor.

Description

Technical Field

[0001] The present invention belongs to the field of displacement monitoring and early warning, and in particular, relates to a pipeline displacement dynamic monitoring and early warning system based on a cloud platform. Background Art

[0002] Oil and gas pipelines are usually buried underground. Over time, these oil and gas pipelines may be displaced due to various influencing factors, such as soil density, humidity, hardness, and changes in external loads such as buildings, roads, bridges above or around the pipelines. If the displacement of the oil and gas pipelines cannot be monitored in time and measures are not taken for early warning and prevention, the pipelines may be deformed, twisted or ruptured, which may lead to oil and gas leakage, and then cause serious accidents such as fire and explosion, which will pose a serious threat to people's lives and safety and may cause casualties. Summary of the invention

[0003] In view of the problems in the related technology, the present invention proposes a pipeline displacement dynamic monitoring and early warning system based on a cloud platform to overcome the above-mentioned technical problems existing in the existing related technology.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0005] The present invention is a pipeline displacement dynamic monitoring and early warning method based on a cloud platform, comprising the following steps:

[0006] S1. Collect the absolute values ​​of the differences between the initial position data and the current position data of multiple displacement measurement points on multiple existing pipelines and the corresponding overall displacement deviation level data to obtain the existing measurement point displacement data matrix and the existing overall displacement deviation level data set; collect the displacement influencing factor data of multiple historical time points corresponding to multiple existing pipelines to obtain the historical displacement influencing factor data matrix set;

[0007] S2. Classify the existing measurement point displacement data matrix according to the existing overall displacement deviation grade data set and calculate the central data of each classification to obtain the existing measurement point displacement classification central data matrix; use the historical displacement influencing factor data matrix set and the existing overall displacement deviation grade data set to construct the final displacement deviation grade mapping equation;

[0008] S3, collecting displacement data of multiple displacement measurement points on the pipeline to be monitored to obtain a displacement data set to be monitored; classifying the displacement data set to be monitored according to the existing measurement point displacement classification center data matrix, obtaining first displacement deviation level data to be monitored and issuing a first alarm;

[0009] S4, predicting the displacement influencing factor data of the pipeline to be monitored at multiple moments in the future according to whether the first alarm is issued, and obtaining a data matrix of the displacement influencing factor to be monitored in the future; using the final displacement deviation level mapping equation to map the data matrix of the displacement influencing factor to be monitored in the future, and obtaining the second displacement deviation level data to be monitored;

[0010] S5, issuing a second alarm according to the second displacement deviation level data to be monitored;

[0011] By collecting the absolute value of the difference between the initial position data and the current position data of multiple displacement measurement points on multiple existing pipelines and the corresponding overall displacement deviation level data, data support is provided for the subsequent construction of the existing measurement point displacement classification center data matrix for classifying the displacement data of multiple displacement measurement points on the monitored pipeline; by collecting the displacement influencing factor data of multiple historical time points corresponding to multiple existing pipelines, data support is provided for the subsequent construction of the final displacement deviation level mapping equation; by calculating the central data of each classification in the existing measurement point displacement data matrix, a classification basis is provided for the subsequent classification of the displacement data of multiple displacement measurement points on the monitored pipeline; by constructing the final displacement deviation level mapping equation, a mapping tool is provided for the subsequent mapping of the displacement influencing factor data of the monitored pipeline at a future moment; first, it is determined whether to issue a first alarm based on the displacement data of each measurement point on the monitored pipeline; when the first alarm is not required, it is determined whether to issue a second alarm from the perspective of the displacement influencing factor.

[0012] Preferably, the S1 comprises the following steps:

[0013] S11, setting a plurality of existing pipelines to obtain an existing pipeline set; evenly setting the same number of displacement measurement points on each pipeline in the existing pipeline set to obtain an existing displacement measurement point matrix a;

[0014]

[0015] Among them, a ij represents the jth displacement measurement point set on the i-th pipeline in the existing pipeline set, a1′ represents the total number of displacement measurement points set on each pipeline in the existing pipeline set, and a′2 represents the total number of existing pipelines;

[0016] A position sensor is set at each displacement measurement point in the existing displacement measurement point matrix to measure the initial position data, current position data and corresponding overall displacement deviation level data of each displacement measurement point on each pipeline in the existing pipeline set and transmit them to the cloud platform for analysis to obtain the initial existing measurement point position data matrix Current existing measurement point location data matrix and the existing overall displacement deviation level dataset represents the overall displacement deviation level data of the i-th pipeline in the existing pipeline set; They are as follows:

[0017]

[0018] in, respectively represent the initial position data and the current position data of the displacement measurement point measured by the position sensor at the j-th displacement measurement point on the i-th pipeline in the existing pipeline set;

[0019] S12, performing a difference operation between the initial position data in the initial existing measurement point position data matrix and the corresponding current position data in the current existing measurement point position data matrix and taking an absolute value operation to obtain an existing measurement point displacement data matrix as follows,

[0020]

[0021] in, represents the displacement data of the jth displacement measurement point on the i-th pipeline in the existing pipeline set; the calculation formula is as follows:

[0022]

[0023] S13, according to the initial existing measurement point position data matrix and the current existing measurement point position data matrix, a number of historical measurement time points are set during the period when each pipeline in the existing pipeline set is displaced, to obtain a historical time point set; a plurality of factor types that have an impact on pipeline displacement are set, to obtain a displacement impact factor type set; according to the displacement impact factor type set, displacement impact factor data corresponding to each pipeline in the existing pipeline set is collected at each time point in the historical time point set, to obtain a historical displacement impact factor data matrix set represents the data matrix of historical displacement influencing factors of the i-th pipeline in the existing pipeline set; as follows,

[0024]

[0025] in, express The kth type of displacement influencing factor data corresponding to the jth historical time point in the pipeline, b1 represents the total number of factor types that have an impact on pipeline displacement, and b2 represents the total number of historical measurement time points set during the displacement of each pipeline in the existing pipeline set;

[0026] When installing the position sensor, install the position sensor at the designated location according to the monitoring requirements; ensure that the position sensor is firmly fixed to avoid vibration and impact; install the data collector close to the sensor to collect and transmit monitoring data in real time; connect the corresponding communication line according to the communication method of the system. Ensure that the line connection is correct and stable, and perform necessary insulation treatment; provide a stable power supply for the monitoring equipment. Install the corresponding power socket or power line according to the equipment requirements; the types of displacement influencing factors include geological factors, such as crustal movement, earthquakes, landslides, mudslides, etc.; soil properties, such as soil density, humidity, hardness, etc.; aging, corrosion, damage, etc. of pipelines; changes in external loads such as buildings, roads, bridges, etc. above or around the pipeline; human activities, such as excavation, blasting, construction, etc.; environmental factors, such as temperature, humidity, wind, etc.

[0027] Preferably, S2 comprises the following steps:

[0028] S21, classifying the existing measurement point displacement data matrix according to the existing overall displacement deviation level data set, to obtain the existing measurement point displacement data classification matrix set b i ′ represents the i-th existing measurement point displacement data classification matrix obtained by classifying the existing measurement point displacement data matrix, represents the total number of existing measurement point displacement data classification matrices obtained by classifying the existing measurement point displacement data matrices;

[0029] Calculate the classification center data of each existing measurement point displacement data classification matrix in the existing measurement point displacement data classification matrix set to obtain the existing measurement point displacement classification center data matrix as follows,

[0030]

[0031] in, Represents the displacement data of the j-th displacement measurement point in the classification center data set of the i-th existing measurement point displacement data classification matrix in the existing measurement point displacement data classification matrix set;

[0032] S22, constructing a final displacement deviation level mapping equation using the historical displacement influencing factor data matrix set and the existing overall displacement deviation level data set;

[0033] The final displacement deviation grade mapping equation is constructed by adopting the historical displacement influencing factor data matrix set and the existing overall displacement deviation grade data set. The final displacement deviation grade mapping equation has a good mapping ability from the displacement influencing factor data to the overall displacement deviation grade data, thereby ensuring the accuracy of the subsequent mapping of the displacement influencing factor data of the monitored pipeline.

[0034] Preferably, the S22 comprises the following steps:

[0035] S221, constructing an initial displacement deviation level mapping equation according to the historical displacement influencing factor data matrix set; as follows,

[0036]

[0037] Wherein, c is the dependent variable of the initial displacement deviation level mapping equation, which represents the displacement deviation level data; ceil represents the rounding function; c′ 2ij is the i·jth independent variable of the initial displacement deviation level mapping equation, representing the jth type of displacement influencing factor data corresponding to the i-th historical time point, c1′ ij c′ 2ij The independent variable coefficient; c3′ represents the offset of the initial displacement from the level mapping equation;

[0038] S222, each historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set is substituted into the initial displacement deviation level mapping equation for mapping, to obtain an initial displacement deviation level mapping data set. represents displacement deviation grade mapping data obtained by substituting the i-th historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set into the initial displacement deviation grade mapping equation for mapping;

[0039] S223, setting a deviation number ratio threshold; when the ratio of the number of displacement deviation level mapping data that exist in the initial displacement deviation level mapping data set and are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set to the total number is greater than or equal to the deviation number ratio threshold, optimizing the initial displacement deviation level mapping equation until the ratio of the number of displacement deviation level mapping data that exist in the initial displacement deviation level mapping data set and are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set to the total number is less than the deviation number ratio threshold, and obtaining the final displacement deviation level mapping equation; otherwise, there is no need to optimize the initial displacement deviation level mapping equation, and the initial displacement deviation level mapping equation is used as the final displacement deviation level mapping equation;

[0040] Since the displacement deviation level is of integer type, the result obtained after the input data is operated through the rounding function is mapped to an integer, so that the mapping data of the initial displacement deviation level mapping equation can better correspond to the displacement deviation level; by substituting the historical displacement influencing factor data matrix into the mapping equation in advance for mapping, and then comparing the mapping result with the actual result, when the accuracy does not meet the requirements, it is necessary to optimize the initial displacement deviation level mapping equation to ensure its mapping accuracy, thereby ensuring the accuracy of the subsequent mapping of the displacement influencing factor data of the monitored pipeline.

[0041] Preferably, optimizing the initial displacement deviation level mapping equation in S223 includes the following steps:

[0042] S2231, Constructing deviation level mapping equation to optimize sparrow population represents the i-th sparrow in the sparrow population optimized by the deviation level mapping equation, d represents the size of the sparrow population optimized by the deviation level mapping equation; the maximum number of iterations of the sparrow population optimized by the deviation level mapping equation is set to d1′ and the current number of iterations is set to d2′; the search space dimension of the sparrow population optimized by the deviation level mapping equation is b1′·b2′+1;

[0043] S2232, setting the value interval of each independent variable coefficient and the offset in the initial displacement deviation level mapping equation to obtain the independent variable value interval matrix And the bias value range respectively represent the lower limit and the upper limit of the offset in the initial displacement deviation level mapping equation; as follows,

[0044]

[0045] in, They respectively represent the lower limit and upper limit of the independent variable coefficient corresponding to the i×jth independent variable of the initial displacement deviation grade mapping equation;

[0046] According to the independent variable value interval matrix and the bias value interval, the deviation level mapping equation is set to optimize the initial position of each sparrow in the sparrow population, and the first initial position matrix set is obtained. The deviation from the rank mapping equation optimizes the initial position matrix of the kth sparrow in the sparrow population;

[0047]

[0048] in, It represents the position component of the initial position of the k-th sparrow in the sparrow population optimized by the deviation grade mapping equation on the independent variable coefficient dimension corresponding to the i×j-th independent variable of the initial displacement deviation grade mapping equation; represents the position component of the initial position of the kth sparrow in the sparrow population optimized by the deviation grade mapping equation in the offset dimension in the initial displacement deviation grade mapping equation; The calculation formulas are as follows:

[0049]

[0050] In the formula, Respectively for as well as Generate a random number between 0 and 1;

[0051] S2233, mapping the data set according to the initial displacement deviation level and the existing overall displacement deviation level dataset Construct the deviation level mapping equation to optimize the fitness function e1 of the sparrow population; as follows,

[0052]

[0053] Among them, β is a positive number, indicating the correction parameter;

[0054] S2234, start iteration, and set the current iteration number d2′ to 1 before iteration; in the first round of iteration, use the deviation level mapping equation to optimize the fitness function e1 of the sparrow population to calculate the fitness value of the initial position matrix of each sparrow in the first initial position matrix set to obtain a first fitness value set; use the maximum fitness in the first fitness value set and the corresponding initial position matrix of the sparrow as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each sparrow in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number d2′ and enter the next round of iteration;

[0055] In each other round of iteration, the fitness function e1 of the sparrow population optimized by the deviation level mapping equation is used to calculate the fitness value of the position matrix of each sparrow in the sparrow population optimized by the deviation level mapping equation obtained in the previous round of iteration, and a second fitness value set is obtained; the maximum fitness in the second fitness value set and the corresponding initial position matrix of the sparrow are respectively used as the second global optimal fitness and the second global optimal position; the position matrix of each sparrow in the sparrow population optimized by the deviation level mapping equation obtained in the previous round of iteration is updated again according to the second global optimal fitness and the second global optimal position; after the update is completed, the current number of iterations d2′ is increased by 1 and the next round of iteration is entered;

[0056] S2235. When d2′≥d1′, stop the iteration, and substitute each position component in the position matrix of the sparrow with the largest fitness value in the sparrow population optimized by the deviation grade mapping equation obtained in the last round of iteration into the initial displacement deviation grade mapping equation to obtain the optimized displacement deviation grade mapping equation; substitute each historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set into the optimized displacement deviation grade mapping equation for mapping to obtain the optimized displacement deviation grade mapping data set;

[0057] When the proportion of the number of displacement deviation level mapping data that are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set in the optimized displacement deviation level mapping data set to the total number is less than the deviation number ratio threshold, the optimized displacement deviation level mapping equation is used as the final displacement deviation level mapping equation; otherwise, return to S2234 to continue iterating until the proportion of the number of displacement deviation level mapping data that are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set in the optimized displacement deviation level mapping data set to the total number is less than the deviation number ratio threshold;

[0058] The sparrow optimization algorithm is inspired by the foraging and anti-predator behaviors of sparrows in nature and has high natural adaptability. It adopts the method of swarm intelligence to solve the optimization problem through mutual cooperation and competition among individuals. It has a fast convergence speed and high solution quality. It can effectively explore the solution space and find high-quality solutions. Based on the above advantages, the sparrow optimization algorithm is used in this scheme to perform multiple iterative optimizations on each independent variable coefficient and offset of the initial displacement deviation rank mapping equation, and the error between the mapped data and the actual data is used as the fitness function. Therefore, as the iteration proceeds, the independent variable coefficients and offsets obtained by the iteration replace the original independent variable coefficients and offsets, so that the mapping accuracy of the initial displacement deviation rank mapping equation becomes higher and higher, and finally meets the requirements.

[0059] Preferably, S3 comprises the following steps:

[0060] S31, set a pipeline to be monitored; set a number of displacement measurement points on the pipeline to be monitored and install position sensors at the displacement measurement points; first measure the initial position and current position of each displacement measurement point on the pipeline to be monitored by the position sensor, and obtain the initial position data set to be monitored And the current location data set to be monitored e1′ i , e′ 2i represent the initial position data and current position data of the i-th displacement measurement point on the pipeline to be monitored respectively; the displacement data set to be monitored is obtained by subtracting the initial position data set to be monitored from the current position data set to be monitored and removing the absolute value.

[0061] e3′ i Indicates the current displacement data of the pipeline to be monitored;

[0062] S32, calculating the Euclidean distance between the displacement data set to be monitored and each row of data in the existing measurement point displacement classification center data matrix to obtain a Euclidean distance set; taking the overall displacement deviation level data of the row of data in the existing measurement point displacement classification center data matrix corresponding to the smallest Euclidean distance in the Euclidean distance set as the overall displacement deviation level data of the pipeline to be monitored, and recording it as the first displacement deviation level data to be monitored;

[0063] S33, determining whether it is necessary to issue a first alarm according to the first displacement deviation level data to be monitored;

[0064] By using a position sensor to measure the initial position and current position of each displacement measurement point on the pipeline to be monitored, a data basis is provided for the subsequent acquisition of the corresponding displacement deviation level data; by calculating the Euclidean distance between the displacement data set to be monitored and each row of data in the existing measurement point displacement classification center data matrix, the one with the smallest Euclidean distance indicates that the two rows of data are the most similar, so that the two can be classified as the same.

[0065] Preferably, the S33 comprises the following steps:

[0066] S331, setting a displacement deviation level threshold; when the first displacement deviation level data to be monitored is greater than or equal to the displacement deviation level threshold, issuing a first alarm; otherwise, no first alarm is required;

[0067] By setting the displacement deviation level threshold, a quantitative basis is provided for determining whether the first displacement deviation level data to be monitored meets the requirements; through the first alarm, an alarm is issued for the first time to determine whether there is displacement abnormality in the monitored pipeline, so that relevant staff can be notified in time to carry out maintenance and adjustments.

[0068] Preferably, S4 comprises the following steps:

[0069] S41, when the first alarm is not issued, the displacement influencing factor data corresponding to the pipeline to be monitored at several historical time points are collected according to the displacement influencing factor type set to obtain a historical displacement influencing factor data matrix to be monitored; the displacement influencing factor data at several future time points are predicted according to the historical displacement influencing factor data matrix to be monitored to obtain a future displacement influencing factor data matrix to be monitored

[0070]

[0071] in, represents the j-th type of displacement influencing factor data predicted at the i-th future time point;

[0072] S42, inputting the future displacement influencing factor data matrix to be monitored into the final displacement deviation level mapping equation for mapping, to obtain second displacement deviation level data to be monitored;

[0073] By predicting the displacement influencing factor data at several time points in the future, data support is provided for the subsequent mapping of the displacement deviation level data of the pipeline to be monitored at future moments.

[0074] Preferably, the S5 comprises the following steps:

[0075] S51, when the second displacement deviation level data to be monitored is greater than or equal to the displacement deviation level threshold, issuing a second alarm; otherwise, no second alarm is required;

[0076] By issuing a second alarm, an early warning is issued for possible abnormal displacement of the monitored pipeline in the future, so that relevant staff can be notified in time to take corresponding preventive measures, further ensuring the normal operation of the pipeline.

[0077] Preferably, the pipeline comprises an oil and gas pipeline.

[0078] The cloud platform-based pipeline displacement dynamic monitoring and early warning system includes an existing displacement data acquisition module, an existing historical displacement influencing factor data acquisition module, a classification center calculation acquisition module, a displacement deviation level mapping equation construction module, a pipeline displacement data acquisition module to be monitored, a classification module, a first alarm module, a prediction module, a mapping module, and a second alarm module.

[0079] The present invention has the following beneficial effects:

[0080] 1. The present invention monitors and warns the displacement of the pipeline to be monitored by using the displacement data of each displacement detection point on the pipeline to be monitored and multiple displacement influencing factor data; wherein, by calculating the central data of each classification in the existing measurement point displacement data matrix, a classification basis is provided for subsequent classification of the displacement data of multiple displacement measurement points on the pipeline to be monitored; by constructing a final displacement deviation level mapping equation, a mapping tool is provided for subsequent mapping of the displacement influencing factor data of the pipeline to be monitored at a future moment; first, it is determined whether to issue a first alarm based on the displacement data of each measurement point on the pipeline to be monitored; when the first alarm is not needed, it is determined whether to issue a second alarm from the perspective of the displacement influencing factor.

[0081] 2. In the present invention, the sparrow optimization algorithm is used to perform multiple iterative optimizations on each independent variable coefficient and bias of the initial displacement deviation level mapping equation, and the error between the mapped data and the actual data is used as the fitness function; therefore, as the iteration proceeds, the mapping accuracy of the initial displacement deviation level mapping equation becomes higher and higher, and finally meets the requirements.

[0082] 3. In the present invention, the first alarm is used to initially warn whether there is abnormal displacement in the monitored pipeline, so that relevant staff can be notified in time to carry out maintenance and adjustment; the second alarm is used to warn of abnormal displacement that may occur in the monitored pipeline at a future time, so that relevant staff can be notified in time to take corresponding preventive measures, further ensuring the normal operation of the pipeline.

[0083] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0085] Figure 1It is a flow chart of the pipeline displacement dynamic monitoring and early warning method based on the cloud platform of the present invention. DETAILED DESCRIPTION

[0086] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0087] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0088] Embodiment 1

[0089] See also Figure 1 , this embodiment is a pipeline displacement dynamic monitoring and early warning method based on a cloud platform, comprising the following steps:

[0090] S1. Collect the absolute values ​​of the differences between the initial position data and the current position data of multiple displacement measurement points on multiple existing pipelines and the corresponding overall displacement deviation level data to obtain the existing measurement point displacement data matrix and the existing overall displacement deviation level data set; collect the displacement influencing factor data of multiple historical time points corresponding to multiple existing pipelines to obtain the historical displacement influencing factor data matrix set;

[0091] The S1 comprises the following steps:

[0092] S11, setting a plurality of existing pipelines to obtain an existing pipeline set; evenly setting the same number of displacement measurement points on each pipeline in the existing pipeline set to obtain an existing displacement measurement point matrix a;

[0093]

[0094] Among them, a ij represents the jth displacement measurement point set on the i-th pipeline in the existing pipeline set, a1′ represents the total number of displacement measurement points set on each pipeline in the existing pipeline set, and a′2 represents the total number of existing pipelines;

[0095] A position sensor is set at each displacement measurement point in the existing displacement measurement point matrix to measure the initial position data, current position data and corresponding overall displacement deviation level data of each displacement measurement point on each pipeline in the existing pipeline set and transmit them to the cloud platform for analysis to obtain the initial existing measurement point position data matrix Current existing measurement point location data matrix and the existing overall displacement deviation level dataset represents the overall displacement deviation level data of the i-th pipeline in the existing pipeline set; They are as follows:

[0096]

[0097] in, respectively represent the initial position data and the current position data of the displacement measurement point measured by the position sensor at the j-th displacement measurement point on the i-th pipeline in the existing pipeline set;

[0098] S12, performing a difference operation between the initial position data in the initial existing measurement point position data matrix and the corresponding current position data in the current existing measurement point position data matrix and taking an absolute value operation to obtain an existing measurement point displacement data matrix as follows,

[0099]

[0100] in, represents the displacement data of the jth displacement measurement point on the i-th pipeline in the existing pipeline set; the calculation formula is as follows:

[0101]

[0102] S13, according to the initial existing measurement point position data matrix and the current existing measurement point position data matrix, a number of historical measurement time points are set during the period when each pipeline in the existing pipeline set is displaced, to obtain a historical time point set; a plurality of factor types that have an impact on pipeline displacement are set, to obtain a displacement impact factor type set; according to the displacement impact factor type set, displacement impact factor data corresponding to each pipeline in the existing pipeline set is collected at each time point in the historical time point set, to obtain a historical displacement impact factor data matrix set represents the data matrix of historical displacement influencing factors of the i-th pipeline in the existing pipeline set; as follows,

[0103]

[0104] in, express The kth type of displacement influencing factor data corresponding to the jth historical time point in the pipeline, b1 represents the total number of factor types that have an impact on pipeline displacement, and b2 represents the total number of historical measurement time points set during the displacement of each pipeline in the existing pipeline set;

[0105] S2. Classify the existing measurement point displacement data matrix according to the existing overall displacement deviation grade data set and calculate the central data of each classification to obtain the existing measurement point displacement classification central data matrix; use the historical displacement influencing factor data matrix set and the existing overall displacement deviation grade data set to construct the final displacement deviation grade mapping equation;

[0106] The S2 comprises the following steps:

[0107] S21, classifying the existing measurement point displacement data matrix according to the existing overall displacement deviation level data set, to obtain the existing measurement point displacement data classification matrix set b i ′ represents the i-th existing measurement point displacement data classification matrix obtained by classifying the existing measurement point displacement data matrix, represents the total number of existing measurement point displacement data classification matrices obtained by classifying the existing measurement point displacement data matrices;

[0108] Calculate the classification center data of each existing measurement point displacement data classification matrix in the existing measurement point displacement data classification matrix set to obtain the existing measurement point displacement classification center data matrix as follows,

[0109]

[0110] in, Represents the displacement data of the j-th displacement measurement point in the classification center data set of the i-th existing measurement point displacement data classification matrix in the existing measurement point displacement data classification matrix set;

[0111] The classification center data refers to a set of data corresponding to each row of data in the existing measurement point displacement data classification matrix, the sum of the Euclidean distances between the data is the smallest;

[0112] S22, constructing a final displacement deviation level mapping equation using the historical displacement influencing factor data matrix set and the existing overall displacement deviation level data set;

[0113] The S22 comprises the following steps:

[0114] S221, constructing an initial displacement deviation level mapping equation according to the historical displacement influencing factor data matrix set; as follows,

[0115]

[0116] Wherein, c is the dependent variable of the initial displacement deviation level mapping equation, which represents the displacement deviation level data; ceil represents the rounding function; c′ 2ij is the i·jth independent variable of the initial displacement deviation level mapping equation, representing the jth type of displacement influencing factor data corresponding to the i-th historical time point, c1′ ij c′ 2ij The independent variable coefficient; c3′ represents the offset of the initial displacement from the level mapping equation;

[0117] S222, each historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set is substituted into the initial displacement deviation level mapping equation for mapping, to obtain an initial displacement deviation level mapping data set. represents displacement deviation grade mapping data obtained by substituting the i-th historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set into the initial displacement deviation grade mapping equation for mapping;

[0118] S223, setting a deviation number ratio threshold; when the ratio of the number of displacement deviation level mapping data that exists in the initial displacement deviation level mapping data set and is different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set to the total number is greater than or equal to the deviation number ratio threshold, optimizing the initial displacement deviation level mapping equation until the ratio of the number of displacement deviation level mapping data that exists in the initial displacement deviation level mapping data set and is different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set to the total number is less than the deviation number ratio threshold, and obtaining a final displacement deviation level mapping equation; otherwise, there is no need to optimize the initial displacement deviation level mapping equation, and the initial displacement deviation level mapping equation is used as the final displacement deviation level mapping equation;

[0119] The optimization of the initial displacement deviation level mapping equation in S223 includes the following steps:

[0120] S2231, Constructing deviation level mapping equation to optimize sparrow population represents the i-th sparrow in the sparrow population optimized by the deviation level mapping equation, d represents the size of the sparrow population optimized by the deviation level mapping equation; the maximum number of iterations of the sparrow population optimized by the deviation level mapping equation is set to d1′ and the current number of iterations is set to d2′; the search space dimension of the sparrow population optimized by the deviation level mapping equation is b1′·b2′+1;

[0121] S2232, setting the value interval of each independent variable coefficient and the offset in the initial displacement deviation level mapping equation to obtain the independent variable value interval matrix And the bias value range respectively represent the lower limit and the upper limit of the offset in the initial displacement deviation level mapping equation; as follows,

[0122]

[0123] in, They respectively represent the lower limit and upper limit of the independent variable coefficient corresponding to the i×jth independent variable of the initial displacement deviation grade mapping equation;

[0124] According to the independent variable value interval matrix and the bias value interval, the deviation level mapping equation is set to optimize the initial position of each sparrow in the sparrow population, and the first initial position matrix set is obtained. The deviation from the rank mapping equation optimizes the initial position matrix of the kth sparrow in the sparrow population;

[0125]

[0126] in, It represents the position component of the initial position of the k-th sparrow in the sparrow population optimized by the deviation grade mapping equation on the independent variable coefficient dimension corresponding to the i×j-th independent variable of the initial displacement deviation grade mapping equation; represents the position component of the initial position of the kth sparrow in the sparrow population optimized by the deviation grade mapping equation in the offset dimension in the initial displacement deviation grade mapping equation; The calculation formulas are as follows:

[0127]

[0128] In the formula, Respectively for as well as Generate a random number between 0 and 1;

[0129] S2233, mapping the data set according to the initial displacement deviation level and the existing overall displacement deviation level dataset Construct the deviation level mapping equation to optimize the fitness function e1 of the sparrow population; as follows,

[0130]

[0131] Among them, β is a positive number, indicating the correction parameter;

[0132] S2234, start iteration, and set the current iteration number d2′ to 1 before iteration; in the first round of iteration, use the deviation level mapping equation to optimize the fitness function e1 of the sparrow population to calculate the fitness value of the initial position matrix of each sparrow in the first initial position matrix set to obtain a first fitness value set; use the maximum fitness in the first fitness value set and the corresponding initial position matrix of the sparrow as the first global optimal fitness and the first global optimal position respectively; update the initial position matrix of each sparrow in the first initial position matrix set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number d2′ and enter the next round of iteration;

[0133] In each other round of iteration, the fitness function e1 of the sparrow population optimized by the deviation level mapping equation is used to calculate the fitness value of the position matrix of each sparrow in the sparrow population optimized by the deviation level mapping equation obtained in the previous round of iteration, and a second fitness value set is obtained; the maximum fitness in the second fitness value set and the corresponding initial position matrix of the sparrow are respectively used as the second global optimal fitness and the second global optimal position; the position matrix of each sparrow in the sparrow population optimized by the deviation level mapping equation obtained in the previous round of iteration is updated again according to the second global optimal fitness and the second global optimal position; after the update is completed, the current number of iterations d2′ is increased by 1 and the next round of iteration is entered;

[0134] S2235. When d2′≥d1′, stop the iteration, and substitute each position component in the position matrix of the sparrow with the largest fitness value in the sparrow population optimized by the deviation grade mapping equation obtained in the last round of iteration into the initial displacement deviation grade mapping equation to obtain the optimized displacement deviation grade mapping equation; substitute each historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set into the optimized displacement deviation grade mapping equation for mapping to obtain the optimized displacement deviation grade mapping data set;

[0135] When the proportion of the number of displacement deviation level mapping data that are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set in the optimized displacement deviation level mapping data set to the total number is less than the deviation number ratio threshold, the optimized displacement deviation level mapping equation is used as the final displacement deviation level mapping equation; otherwise, return to S2234 to continue iterating until the proportion of the number of displacement deviation level mapping data that are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set in the optimized displacement deviation level mapping data set to the total number is less than the deviation number ratio threshold;

[0136] S3, collecting displacement data of multiple displacement measurement points on the pipeline to be monitored to obtain a displacement data set to be monitored; classifying the displacement data set to be monitored according to the existing measurement point displacement classification center data matrix, obtaining first displacement deviation level data to be monitored and issuing a first alarm;

[0137] The S3 comprises the following steps:

[0138] S31, set a pipeline to be monitored; set a number of displacement measurement points on the pipeline to be monitored and install position sensors at the displacement measurement points; first measure the initial position and current position of each displacement measurement point on the pipeline to be monitored by the position sensor, and obtain the initial position data set to be monitored And the current location data set to be monitored e1′ i , e′ 2i represent the initial position data and current position data of the i-th displacement measurement point on the pipeline to be monitored respectively; the displacement data set to be monitored is obtained by subtracting the initial position data set to be monitored from the current position data set to be monitored and removing the absolute value. e3′ i Indicates the current displacement data of the pipeline to be monitored;

[0139] S32, calculating the Euclidean distance between the displacement data set to be monitored and each row of data in the existing measurement point displacement classification center data matrix to obtain a Euclidean distance set; taking the overall displacement deviation level data of the row of data in the existing measurement point displacement classification center data matrix corresponding to the smallest Euclidean distance in the Euclidean distance set as the overall displacement deviation level data of the pipeline to be monitored, and recording it as the first displacement deviation level data to be monitored;

[0140] S33, determining whether it is necessary to issue a first alarm according to the first displacement deviation level data to be monitored;

[0141] The S33 comprises the following steps:

[0142] S331, setting a displacement deviation level threshold; when the first displacement deviation level data to be monitored is greater than or equal to the displacement deviation level threshold, issuing a first alarm; otherwise, no first alarm is required;

[0143] S4, predicting the displacement influencing factor data of the pipeline to be monitored at multiple moments in the future according to whether the first alarm is issued, and obtaining a data matrix of the displacement influencing factor to be monitored in the future; using the final displacement deviation level mapping equation to map the data matrix of the displacement influencing factor to be monitored in the future, and obtaining the second displacement deviation level data to be monitored;

[0144] The S4 comprises the following steps:

[0145] S41, when the first alarm is not issued, the displacement influencing factor data corresponding to the pipeline to be monitored at several historical time points are collected according to the displacement influencing factor type set to obtain a historical displacement influencing factor data matrix to be monitored; the displacement influencing factor data at several future time points are predicted according to the historical displacement influencing factor data matrix to be monitored to obtain a future displacement influencing factor data matrix to be monitored

[0146]

[0147] in, represents the j-th type of displacement influencing factor data predicted at the i-th future time point;

[0148] S42, inputting the future displacement influencing factor data matrix to be monitored into the final displacement deviation level mapping equation for mapping, to obtain second displacement deviation level data to be monitored;

[0149] S5, issuing a second alarm according to the second displacement deviation level data to be monitored;

[0150] The S5 comprises the following steps:

[0151] S51. When the second displacement deviation level data to be monitored is greater than or equal to the displacement deviation level threshold, a second alarm is issued; otherwise, there is no need to issue a second alarm.

[0152] Embodiment 2

[0153] This embodiment discloses a pipeline displacement dynamic monitoring and early warning system based on a cloud platform, and the system can implement the method of the above embodiment, including an existing displacement data acquisition module, an existing historical displacement influencing factor data acquisition module, a classification center calculation acquisition module, a displacement deviation level mapping equation construction module, a pipeline displacement data acquisition module to be monitored, a classification module, a first alarm module, a prediction module, a mapping module, and a second alarm module;

[0154] The existing displacement data acquisition module is used to collect the absolute value of the difference between the initial position data and the current position data of multiple displacement measurement points on multiple existing pipelines and the corresponding overall displacement deviation level data to obtain the existing measurement point displacement data matrix and the existing overall displacement deviation level data set;

[0155] The existing historical displacement influencing factor data acquisition module is used to collect displacement influencing factor data at multiple historical time points corresponding to multiple existing pipelines to obtain a historical displacement influencing factor data matrix set;

[0156] The classification center calculation acquisition module is used to classify the existing measurement point displacement data matrix according to the existing overall displacement deviation level data set and calculate the center data of each classification to obtain the existing measurement point displacement classification center data matrix;

[0157] The displacement deviation grade mapping equation construction module is used to construct a final displacement deviation grade mapping equation using the historical displacement influencing factor data matrix set and the existing overall displacement deviation grade data set;

[0158] The displacement data acquisition module of the pipeline to be monitored is used to collect displacement data of multiple displacement measurement points on the pipeline to be monitored to obtain a displacement data set to be monitored;

[0159] The classification module is used to classify the displacement data set to be monitored according to the existing measurement point displacement classification center data matrix to obtain the first displacement deviation level data to be monitored;

[0160] The first alarm module is used to issue a first alarm according to the first displacement deviation level data to be monitored;

[0161] The prediction module is used to predict the displacement influencing factor data of the pipeline to be monitored at multiple moments in the future according to whether the first alarm is issued, and obtain a data matrix of the displacement influencing factor to be monitored in the future;

[0162] The mapping module is used to map the future displacement influencing factor data matrix to be monitored using the final displacement deviation level mapping equation to obtain second displacement deviation level data to be monitored;

[0163] The second alarm module is used to issue a second alarm according to the second displacement deviation level data to be monitored.

[0164] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0165] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A cloud platform-based pipeline displacement dynamic monitoring and early warning method, characterized in that: The following steps are involved: S1. Collect the absolute values ​​of the differences between the initial position data and the current position data of multiple displacement measurement points on multiple existing pipelines and the corresponding overall displacement deviation level data to obtain the existing measurement point displacement data matrix and the existing overall displacement deviation level data set; collect the displacement influencing factor data of multiple historical time points corresponding to multiple existing pipelines to obtain the historical displacement influencing factor data matrix set; S2. Classify the existing measurement point displacement data matrix according to the existing overall displacement deviation grade data set and calculate the central data of each classification to obtain the existing measurement point displacement classification central data matrix; use the historical displacement influencing factor data matrix set and the existing overall displacement deviation grade data set to construct the final displacement deviation grade mapping equation; S3, collecting displacement data of multiple displacement measurement points on the pipeline to be monitored to obtain a displacement data set to be monitored; classifying the displacement data set to be monitored according to the existing measurement point displacement classification center data matrix, obtaining first displacement deviation level data to be monitored and issuing a first alarm; S4, predicting the displacement influencing factor data of the pipeline to be monitored at multiple moments in the future according to whether the first alarm is issued, and obtaining a data matrix of the displacement influencing factor to be monitored in the future; using the final displacement deviation level mapping equation to map the data matrix of the displacement influencing factor to be monitored in the future, and obtaining the second displacement deviation level data to be monitored; S5. Issue a second alarm according to the second displacement deviation level data to be monitored.

2. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 1 is characterized in that: The S1 comprises the following steps: S11, setting a plurality of existing pipelines to obtain an existing pipeline set; evenly setting the same number of displacement measurement points on each pipeline in the existing pipeline set to obtain an existing displacement measurement point matrix; setting a position sensor at each displacement measurement point in the existing displacement measurement point matrix, measuring the initial position data, current position data and corresponding overall displacement deviation level data of each displacement measurement point on each pipeline in the existing pipeline set, and transmitting the data to the cloud platform for analysis, to obtain an initial existing measurement point position data matrix, a current existing measurement point position data matrix and an existing overall displacement deviation level data set; S12, performing a difference operation between the initial position data in the initial existing measurement point position data matrix and the corresponding current position data in the current existing measurement point position data matrix and taking an absolute value operation to obtain an existing measurement point displacement data matrix; S13, according to the initial existing measurement point position data matrix and the current existing measurement point position data matrix, a number of historical measurement time points are set during the period when each pipeline in the existing pipeline set is displaced, to obtain a historical time point set; a plurality of factor types that have an impact on pipeline displacement are set, to obtain a displacement impact factor type set; according to the displacement impact factor type set, displacement impact factor data corresponding to each pipeline in the existing pipeline set are collected at each time point in the historical time point set, to obtain a historical displacement impact factor data matrix set.

3. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 2 is characterized in that: The S2 comprises the following steps: S21, classifying the existing measurement point displacement data matrix according to the existing overall displacement deviation level data set to obtain an existing measurement point displacement data classification matrix set; calculating the classification center data of each existing measurement point displacement data classification matrix in the existing measurement point displacement data classification matrix set to obtain an existing measurement point displacement classification center data matrix; S22. Constructing a final displacement deviation grade mapping equation using the historical displacement influencing factor data matrix set and the existing overall displacement deviation grade data set.

4. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 3 is characterized in that: The S22 comprises the following steps: S221, constructing an initial displacement deviation level mapping equation according to the historical displacement influencing factor data matrix set; S222, substituting each historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set into the initial displacement deviation level mapping equation for mapping, to obtain an initial displacement deviation level mapping data set; S223, setting a deviation number ratio threshold; when the ratio of the number of displacement deviation level mapping data that exist in the initial displacement deviation level mapping data set and are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set to the total number is greater than or equal to the deviation number ratio threshold, the initial displacement deviation level mapping equation is optimized until the ratio of the number of displacement deviation level mapping data that exist in the initial displacement deviation level mapping data set and are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set to the total number is less than the deviation number ratio threshold, and the final displacement deviation level mapping equation is obtained; otherwise, there is no need to optimize the initial displacement deviation level mapping equation, and the initial displacement deviation level mapping equation is used as the final displacement deviation level mapping equation.

5. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 4 is characterized in that: The optimization of the initial displacement deviation level mapping equation in S223 includes the following steps: S2231, constructing a deviation level mapping equation to optimize the sparrow population; setting the maximum number of iterations of the deviation level mapping equation to optimize the sparrow population to d′1 and the current number of iterations to d′2; S2232, setting the value interval of each independent variable coefficient and the offset in the initial displacement deviation grade mapping equation to obtain the independent variable value interval matrix and the offset value interval; setting the deviation grade mapping equation according to the independent variable value interval matrix and the offset value interval to optimize the initial position of each sparrow in the sparrow population, and obtaining a first initial position matrix set; S2233, constructing a deviation level mapping equation to optimize the fitness function of the sparrow population according to the initial displacement deviation level mapping data set and the existing overall displacement deviation level data set; S2234, start iteration; in each round of iteration, use the deviation level mapping equation to optimize the fitness function of the sparrow population to calculate the fitness value of the position matrix of each sparrow in the sparrow population optimized by the deviation level mapping equation obtained in the previous round of iteration, and update the position matrix of each sparrow in the sparrow population optimized by the deviation level mapping equation obtained in the previous round of iteration; S2235. When d′2≥d′1, stop the iteration, substitute each position component in the position matrix of the sparrow with the largest fitness value in the sparrow population optimized by the deviation grade mapping equation obtained in the last round of iteration into the initial displacement deviation grade mapping equation, and obtain the optimized displacement deviation grade mapping equation; substitute each historical displacement influencing factor data matrix in the historical displacement influencing factor data matrix set into the optimized displacement deviation grade mapping equation for mapping, and obtain the optimized displacement deviation grade mapping data set; When the proportion of the number of displacement deviation level mapping data in the optimized displacement deviation level mapping data set that are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set to the total number is less than the deviation number ratio threshold, the optimized displacement deviation level mapping equation is used as the final displacement deviation level mapping equation; otherwise, return to S2234 and continue to iterate until the proportion of the number of displacement deviation level mapping data in the optimized displacement deviation level mapping data set that are different from the corresponding overall displacement deviation level data in the existing overall displacement deviation level data set is less than the deviation number ratio threshold.

6. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 5 is characterized in that: The S3 comprises the following steps: S31, setting a pipeline to be monitored; setting a number of displacement measurement points on the pipeline to be monitored and installing position sensors at the displacement measurement points; firstly measuring the initial position and current position of each displacement measurement point on the pipeline to be monitored by the position sensor to obtain an initial position data set to be monitored; subtracting the initial position data set to be monitored from the current position data set to be monitored and removing the absolute value to obtain a displacement data set to be monitored; S32, calculating the Euclidean distance between the displacement data set to be monitored and each row of data in the existing measurement point displacement classification center data matrix to obtain a Euclidean distance set; taking the overall displacement deviation level data of the row of data in the existing measurement point displacement classification center data matrix corresponding to the smallest Euclidean distance in the Euclidean distance set as the overall displacement deviation level data of the pipeline to be monitored, and recording it as the first displacement deviation level data to be monitored; S33: Determine whether it is necessary to issue a first alarm based on the first displacement deviation level data to be monitored.

7. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 6 is characterized in that: The S33 comprises the following steps: S331, setting a displacement deviation level threshold; when the first displacement deviation level data to be monitored is greater than or equal to the displacement deviation level threshold, issuing a first alarm; otherwise, there is no need to issue a first alarm.

8. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 7 is characterized in that: The S4 comprises the following steps: S41, when the first alarm is not issued, collecting displacement influencing factor data corresponding to the pipeline to be monitored at several historical time points according to the displacement influencing factor type set, and obtaining a historical displacement influencing factor data matrix to be monitored; predicting the displacement influencing factor data at several time points in the future according to the historical displacement influencing factor data matrix to be monitored, and obtaining a future displacement influencing factor data matrix to be monitored; S42, inputting the future displacement influencing factor data matrix to be monitored into the final displacement deviation level mapping equation for mapping, and obtaining second displacement deviation level data to be monitored.

9. The cloud platform-based pipeline displacement dynamic monitoring and early warning method according to claim 8 is characterized in that: The S5 comprises the following steps: S51. When the second displacement deviation level data to be monitored is greater than or equal to the displacement deviation level threshold, a second alarm is issued; otherwise, a second alarm does not need to be issued.

10. A system for implementing the cloud platform-based pipeline displacement dynamic monitoring and early warning method as described in any one of claims 1 to 9.

Images