A method and system for intelligent optimization processing of pipeline measurement data

Abstract

The present invention provides an intelligent optimization processing method and system for pipeline measurement data, which relates to the field of data processing technology. The method includes: for each section of pipeline, randomly selecting two symbolic points as reference points; calculating the qualified rate of each section of pipeline according to the position information and attribute information of the reference points, combined with the preset quality standard; analyzing the similarity of the reference points between multiple sections of pipelines, by comparing the position and attribute information of the reference points of different sections of pipelines, and combining the qualified rate of each section of pipeline, comprehensively evaluating the quality of the entire pipeline to obtain an evaluation result; based on the evaluation result, identifying abnormal points of pipeline sections. The present invention improves data processing efficiency, accurately divides pipeline sections, comprehensively evaluates pipeline quality, and accurately identifies abnormal points.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent optimization processing method and system for pipeline measurement data. Background Art

[0002] In recent years, intelligent processing technologies for pipeline measurement data have received extensive attention and research. These technologies aim to improve the processing efficiency and accuracy of pipeline measurement data through automated and intelligent methods, thereby better monitoring and managing the status and quality of pipeline systems.

[0003] However, the existing intelligent processing technology still has some shortcomings.

[0004] For example, when evaluating pipeline quality, some existing methods only consider a single indicator, such as the location accuracy of pipeline points or the integrity of attribute information, but ignore the comprehensive evaluation among multiple indicators. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide an intelligent optimization processing method and system for pipeline measurement data, which improves data processing efficiency, accurately divides pipeline segments, comprehensively evaluates pipeline quality, and accurately identifies abnormal points.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0007] In a first aspect, a method for intelligent optimization processing of pipeline measurement data is provided, the method comprising:

[0008] Receiving pipeline measurement data, wherein the pipeline measurement data includes location information and attribute information of a plurality of pipeline points;

[0009] Preprocessing the pipeline measurement data to obtain preprocessed measurement data;

[0010] The pre-processed measurement data is segmented, and the pipeline is divided into multiple segments according to the direction and curvature of the pipeline, and each segment contains several continuous pipeline points;

[0011] For each section of pipeline, two symbolic points are randomly selected as reference points; based on the location information and attribute information of the reference points and the preset quality standards, the qualified rate of each section of pipeline is calculated;

[0012] Analyze the similarity of the benchmarks between multiple pipeline sections, compare the location and attribute information of the benchmarks of different pipeline sections, and combine the qualified rate of each pipeline section to comprehensively evaluate the quality of the entire pipeline to obtain the evaluation results;

[0013] Based on the evaluation results, abnormal points in the pipeline segment are identified.

[0014] Furthermore, for each pipeline section, two symbolic points are randomly selected as reference points, including:

[0015] Determine all the symbolic points in each pipeline segment, randomly select two symbolic points from the candidate point set as a particle, and repeat to initialize multiple particles;

[0016] Determine the fitness function used to evaluate the quality of the two selected symbol points, and calculate the fitness value of each initialized particle;

[0017] For each particle, calculate the gravitational force between it and all the remaining particles;

[0018] According to Newton's second law, the calculated gravity is used to update the speed and position of each particle. The position update means selecting a new symbol point and making sure that the updated particle is within the candidate point set. If it is beyond the boundary, it is adjusted. After each position update, the fitness value of the particle is recalculated.

[0019] If the preset number of iterations is reached, the iteration is stopped and the corresponding particle is selected as the final result. The final result is that two symbolic points in the particle are selected as reference points.

[0020] Furthermore, the calculation formula of the fitness function is:

[0021] ;

[0022] in, Represents particles The total fitness value of and represents the weight coefficient; Indicates the total number of symbol points; Symbol point and The distance between Represents the maximum value of the distance between all pairs of symbolic points; Indicates the amount of attribute information; Symbol point No. attribute value; Indicates Reference value of each attribute value; and Respectively represent The maximum and minimum values ​​of the attribute values; , and Indicates the index value.

[0023] Furthermore, for each particle, the gravitational force between it and all the remaining particles is calculated, including:

[0024] For each particle, Calculate the gravitational force between it and all remaining particles;

[0025] in, Represents particles The magnitude of the combined gravitational force of all other particles; is a summation symbol, indicating that except for the particle All particles except Perform summation; is the total number of particles; is the gravitational constant; It is a particle Quality, It is a particle quality; Represents particles and particles The distance between Represents the particle Pointing to particles The unit vector of .

[0026] Furthermore, according to Newton's second law, the calculated gravity is used to update the velocity and position of each particle. The velocity update formula is:

[0027] ;

[0028] in, It is a particle Speed ​​at the next moment; It is a particle Speed ​​at the current moment It is a particle quality; is the time step, representing the time interval between two updates;

[0029] The update formula of position is:

[0030] ;

[0031] in, It is a particle The position at the next moment; It is a particle The location at the current moment.

[0032] Furthermore, the qualified rate of each pipeline section The calculation formula is:

[0033] ;

[0034] in, Indicates the total number of pipeline sections; Indicates Importance coefficient of pipeline segment; Indicates The number of reference points in the segment pipeline; Indicates The weight coefficient of each benchmark point; and Respectively represent Section 1 The weight of the location information and attribute information of each benchmark point; and Respectively represent Section 1 The number of benchmarks with qualified locations and qualified attributes; Indicates Section 1 The total number of benchmarks.

[0035] Furthermore, the similarity of the benchmarks between multiple pipeline sections is analyzed. By comparing the location and attribute information of the benchmarks of different pipeline sections and combining the qualified rate of each pipeline section, the quality of the entire pipeline is comprehensively evaluated to obtain the evaluation results, including:

[0036] For each pipeline section, determine the number and location of its reference points;

[0037] For two reference points A and B, their position coordinates are ( x 1 , y 1 , z 1 )and( x 2 , y 2 , z 2 ), calculate the Euclidean distance d1 between the two reference points A and B; take the reciprocal of the Euclidean distance d1 as the position similarity score S1; convert the attributes of the reference points into numerical vectors, and for the attribute vectors of the two reference points and , calculate the Euclidean distance d2, and take the reciprocal of the Euclidean distance d2 as the attribute similarity score S2;

[0038] The location similarity score S1 and the attribute similarity score S2 are weighted and summed to obtain a comprehensive similarity score;

[0039] Calculate the weighted sum of the comprehensive similarity scores and use it as the corresponding aggregate score for each pipeline segment;

[0040] The aggregate scores of all pipeline segments are compared, and the quality of the entire pipeline is evaluated based on the aggregate scores to obtain an evaluation result.

[0041] Furthermore, based on the evaluation results, abnormal points in the pipeline segment are identified, including:

[0042] The aggregated scores of all pipeline segments are obtained. For each pipeline segment, if its aggregated score is lower than the set abnormal threshold, it is marked as an abnormal point.

[0043] In a second aspect, an intelligent optimization processing system for pipeline measurement data includes:

[0044] An acquisition module, configured to receive pipeline measurement data, wherein the pipeline measurement data includes location information and attribute information of a plurality of pipeline points;

[0045] A preprocessing module, used for preprocessing the pipeline measurement data to obtain preprocessed measurement data;

[0046] The segmentation module is used to segment the pre-processed measurement data and divide the pipeline into multiple segments according to the direction and curvature of the pipeline. Each segment contains several continuous pipeline points.

[0047] The calculation module is used to randomly select two symbolic points as reference points for each section of pipeline; calculate the qualified rate of each section of pipeline according to the position information and attribute information of the reference points and the preset quality standards;

[0048] The analysis module is used to analyze the similarity of the reference points between multiple pipeline sections. By comparing the location and attribute information of the reference points of different pipeline sections and combining the qualified rate of each pipeline section, the quality of the entire pipeline is comprehensively evaluated to obtain the evaluation results;

[0049] The identification module is used to identify abnormal points of the pipeline segment based on the evaluation results.

[0050] According to a third aspect, a computing device includes:

[0051] one or more processors;

[0052] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0053] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0054] The above scheme of the present invention includes at least the following beneficial effects.

[0055] By automatically receiving and preprocessing pipeline measurement data, the present invention can quickly clean and organize a large amount of data, remove noise and outliers, and thus significantly improve the efficiency of data processing. The present invention intelligently divides the pipeline into multiple sections according to the actual direction and curvature of the pipeline. This division method is more in line with the actual physical characteristics of the pipeline and helps to more accurately analyze and evaluate the quality of the pipeline.

[0056] By randomly selecting the symbolic point of each pipeline section as the reference point, the present invention can more comprehensively reflect the characteristics of each pipeline section. At the same time, combined with the location information and attribute information of the reference point, the qualified rate of each pipeline section can be more accurately evaluated. The present invention not only considers the qualified rate of each pipeline section, but also comprehensively evaluates the quality of the entire pipeline by analyzing the similarity of the reference points between multiple pipeline sections. This evaluation method can more comprehensively reflect the overall condition of the pipeline. Based on the comprehensive evaluation results, the present invention can accurately identify abnormal points in the pipeline segment. This helps to promptly discover and deal with problems in the pipeline and ensure the safe and stable operation of the pipeline. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flow chart of an intelligent optimization processing method for pipeline measurement data provided by an embodiment of the present invention.

[0058] Figure 2 It is a schematic diagram of an intelligent optimization processing system for pipeline measurement data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0060] like Figure 1 As shown, an embodiment of the present invention provides an intelligent optimization processing method for pipeline measurement data, the method comprising the following steps:

[0061] Step 11, receiving pipeline measurement data, wherein the pipeline measurement data includes location information and attribute information of multiple pipeline points;

[0062] Step 12, preprocessing the pipeline measurement data to obtain preprocessed measurement data;

[0063] Step 13, segmenting the preprocessed measurement data, and dividing the pipeline into multiple pipeline segments according to the direction and curvature of the pipeline, each pipeline segment contains a number of continuous pipeline points;

[0064] Step 14, for each section of pipeline, two symbolic points are randomly selected as reference points; based on the position information and attribute information of the reference points and in combination with the preset quality standards, the qualified rate of each section of pipeline is calculated;

[0065] Step 15, analyzing the similarity of the reference points between the multiple pipeline sections, by comparing the positions and attribute information of the reference points of different pipeline sections and combining the qualified rate of each pipeline section, comprehensively evaluating the quality of the entire pipeline to obtain an evaluation result;

[0066] Step 16: Based on the evaluation results, identify abnormal points in the pipeline segment.

[0067] In an embodiment of the present invention, by automatically receiving and preprocessing pipeline measurement data, the present invention can quickly clean and organize a large amount of data, remove noise and outliers, and thus significantly improve the efficiency of data processing. The present invention intelligently divides the pipeline into multiple sections according to the actual direction and curvature of the pipeline. This division method is more in line with the actual physical characteristics of the pipeline and helps to more accurately analyze and evaluate the quality of the pipeline. By randomly selecting the symbolic point of each section of the pipeline as a reference point, the present invention can more comprehensively reflect the characteristics of each section of the pipeline. At the same time, combined with the location information and attribute information of the reference point, the qualified rate of each section of the pipeline can be more accurately evaluated. The present invention not only considers the qualified rate of each section of the pipeline, but also comprehensively evaluates the quality of the entire pipeline by analyzing the similarity of the reference points between multiple sections of the pipeline; based on the comprehensive evaluation results, the present invention can accurately identify abnormal points in the pipeline segment, which helps to timely discover and deal with problems in the pipeline and ensure the safe and stable operation of the pipeline.

[0068] The above step 11 specifically includes:

[0069] Determine the format of data reception, such as CSV, XML, JSON, or a specific GIS data format (such as Shapefile); set the data transmission protocol, which can be FTP, HTTP, or a dedicated data exchange protocol; receive pipeline measurement data through network transmission or physical media (such as USB storage devices); ensure the integrity and security of the data, and use checksums, encryption, and other means to verify the correctness of the data; check whether the received data contains necessary fields, such as the coordinates (X, Y, Z) of the pipeline points, attribute information (such as pipeline type, diameter, material, etc.); preliminarily evaluate the quality of the data, such as checking whether there are obvious outliers or errors; store the received data in an appropriate database or file system for subsequent processing and analysis.

[0070] The above step 12 specifically includes:

[0071] Remove or correct erroneous data points, such as points with incorrect coordinates, missing or inconsistent attribute information, handle duplicate data, and ensure the uniqueness of each pipeline point; convert data from the received format to the internal processing format to optimize processing speed and efficiency, and convert the coordinate system to ensure that all data points use a unified coordinate system. Apply filtering algorithms (such as Kalman filtering, median filtering, etc.) to reduce noise in the data; use smoothing techniques (such as moving average, spline interpolation, etc.) to smooth the position of pipeline points to reduce the impact of measurement errors; visit adjacent point pairs in sequence according to the order of pipeline points, and for each pair of adjacent points, use the Euclidean distance formula to calculate the distance between them; add the calculated distance to the length of the current pipeline segment, and add the length information as an attribute to the corresponding pipeline segment data; for each pipeline segment, select the starting point and the end point as reference points for calculating the direction angle; use the vector calculation method in three-dimensional space to determine the direction vector of the pipeline segment, and calculate its angle with the horizontal plane or a reference direction; add the calculated direction angle as attribute information to the corresponding pipeline segment data; define a sliding window containing multiple consecutive pipeline points along the pipeline direction.

[0072] Set the size of the sliding window, that is, the number of pipeline points contained in the window. This size should be determined according to the characteristics of the pipeline and the analysis requirements. Initialize a variable to record the cumulative value of the direction change angle and set it to 0; start from the starting point of the pipeline and put the first pipeline point into the sliding window; add subsequent pipeline points to the window in turn until the preset window size is reached; for each pair of adjacent pipeline points in the sliding window, calculate the direction change angle between them. This can be done by comparing the coordinate vectors of the two points. The direction change angle can be obtained by calculating the angle between two adjacent vectors. In two-dimensional space, the dot product and cross product formulas can be used to calculate the angle; in three-dimensional space, the dot product formula between vectors can be used; the direction change angle between each pair of adjacent pipeline points is accumulated to the cumulative value; when the direction change angles of all adjacent point pairs in the sliding window are calculated and accumulated, the accumulated value obtained is the total bending degree of the pipeline in the current window. Different thresholds can be set to judge the bending degree of the pipeline. For example, a cumulative angle less than a certain value can be considered as "slight bending", within a certain range can be considered as "medium bending", and exceeding another higher value is considered as "severe bending"; move the sliding window forward along the pipeline by one pipeline point, remove the front point of the window, and add a new point at the end of the window, and repeat the steps until the sliding window traverses the entire pipeline.

[0073] For each sliding window position, the assessment result of its curvature is recorded. Finally, a report containing the curvature of each pipeline segment can be output, and the calculated curvature value is added as feature information to the corresponding pipeline segment or pipeline point data; the elevation (Z coordinate) data is extracted from the position information of the pipeline point; for adjacent pipeline points, the elevation difference between them is calculated; the changing trend of the elevation difference, such as rising, falling or stable, and the magnitude of the change are analyzed; the assessment result of the elevation change is added as feature information to the corresponding pipeline segment or pipeline point data; after the preprocessing is completed, the data is quality checked to ensure that no new errors are introduced in the preprocessing step.

[0074] The above step 13 specifically includes:

[0075] According to engineering experience and actual needs, set an angle threshold to distinguish between straight segments and curved segments. For example, you can set that when the angle of change in direction between adjacent pipeline points is less than 5 degrees, they are considered to belong to the same straight segment. Similarly, set thresholds for bending angle and curvature radius to determine whether the degree of curvature of the curved segment meets the segmentation standard. For example, you can set segmentation when the bending angle is greater than 30 degrees or the curvature radius is less than a certain value. Get the preprocessed pipeline point data to ensure that they are arranged in the actual physical order; initialize the variables used to store the current segment information, such as the starting point, end point, type (straight line or curve), etc.

[0076] For each pair of adjacent pipeline points, calculate the direction vector between them, and use the angle formula between vectors to calculate the angle difference between adjacent direction vectors. If the direction change angle is less than the set straight line threshold, add the current point to the current straight line segment. If the direction change angle is greater than the straight line threshold, start a new curve segment and use the current point as the starting point of the curve segment.

[0077] For each identified curve segment, calculate the bending angle and curvature between adjacent pipeline points. The bending angle can be approximately calculated by the angle formed by three adjacent points. Use a curve fitting algorithm (such as the least squares method) to fit the current curve segment, and extract the curvature information from the fitting result. According to the set bending degree threshold, determine whether the bending angle and curvature of the current curve segment meet the segmentation criteria. If the segmentation criteria are met, segmentation is performed at the pipeline points that meet the conditions, the current segment is marked as completed, and a new pipeline segment is started.

[0078] After each segmentation, the information of the current segment is updated, including the starting point, end point, type, and calculated properties such as bending angle and curvature, and the data of each segmented pipeline is stored in a database or file.

[0079] In a preferred embodiment of the present invention, the above step 14, for each pipeline section, randomly selecting two symbolic points as reference points, may include:

[0080] Step 141, determine all the symbolic points in each pipeline section, randomly select two symbolic points from the candidate point set as a particle, repeat to initialize multiple particles, specifically including: for each pipeline section, determine a set of symbolic points that can represent the characteristics of the pipeline section based on its geometric features and attribute information. These symbolic points can be key nodes and turning points on the pipeline. Randomly select two points from the symbolic point set as a particle. These two points will serve as a solution candidate in the subsequent optimization process, representing two reference points on the pipeline section. Repeat the above random selection process, initialize multiple particles, and form a particle group. Each particle represents a possible combination of reference points.

[0081] Step 142, determining a fitness function for evaluating the quality of the two selected symbol points, and calculating the fitness value of each initialized particle;

[0082] Step 143, for each particle, calculate the gravitational force between it and all the remaining particles; according to Newton's second law, use the calculated gravitational force to update the speed and position of each particle;

[0083] The updating of position means selecting a new symbol point and making sure that the updated particle is within the candidate point set. If it exceeds the boundary, an adjustment is made. After each position update, the fitness value of the particle is recalculated, which specifically includes: for each particle, Newton's second law is used to calculate its new position according to its current position and velocity, as well as the influence of gravity. The updating of position may be manifested as a change in coordinates in physical space, but in this problem it is manifested as the selection of a new symbol point as a component of the particle. After updating the particle position, it is necessary to check whether the new position (i.e., the newly selected symbol point) is within the predefined candidate point set. If the new position exceeds the boundary of the candidate point set, it means that a symbol point that is not within the valid range is selected, and an adjustment is required. The adjustment strategy can be to reset the particle position to a valid point within the boundary, or to map it back to the valid area according to some rule (such as reflection, random redistribution, etc.). After each particle position update, the fitness value of the particle needs to be recalculated to evaluate the pros and cons of the new position (the newly selected symbol point). The new position is evaluated using the previously defined fitness function, and the calculated fitness value is updated to the relevant properties of the particle.

[0084] Step 144, if the preset number of iterations is reached, the iteration is stopped and the corresponding particle is selected as the final result. The final result is that two symbol points in the particle are selected as reference points, which specifically includes:

[0085] In the main loop of the algorithm, an iteration counter is maintained to record the current number of iterations; at the end of each loop, the value of the iteration counter is increased; before each iteration starts, check whether the value of the iteration counter has reached the preset maximum number of iterations. If the value of the iteration counter reaches the preset maximum number of iterations, it means that the algorithm has run enough iteration steps, and the iteration should be stopped at this time. Stopping the iteration means no longer updating the position and velocity of the particle, and no longer calculating the new fitness value. After stopping the iteration, a particle with the best fitness value (the highest or lowest, depending on the definition of the fitness function) is selected from the current particle group as the final result. This optimal particle represents the best solution found by the algorithm during the search process, that is, the most suitable two symbolic points as reference points. Two symbolic points are extracted from the selected optimal particle. These two points are the final results selected as reference points. These two reference points are output or saved to an appropriate data structure for subsequent use.

[0086] In the embodiment of the present invention, by randomly selecting symbolic points as reference points, it can be ensured that the selected points are more representative and can more comprehensively reflect the characteristics and status of each section of the pipeline, which is helpful to improve the accuracy and reliability in subsequent analysis and decision-making. Using multiple particles for initialization and continuously updating the position and velocity of the particles during the iteration process enables the optimization algorithm to maintain strong robustness when facing complex and changeable pipeline data. This means that the algorithm can stably find suitable reference points in different scenarios. By evaluating the particles through the fitness function, particles with excellent performance can be quickly screened out, thereby reducing unnecessary calculations. At the same time, the method of updating the position and velocity of particles using Newton's second law ensures the convergence speed and calculation efficiency of the algorithm. After the particle position is updated, the legitimacy and effectiveness of the algorithm are ensured by checking whether the particle is in the candidate point set and adjusting the particles that exceed the boundary. This mechanism avoids erroneous results caused by particles crossing the boundary and improves the stability of the algorithm.

[0087] In a preferred embodiment of the present invention, the calculation formula of the fitness function is:

[0088] ;

[0089] in, Represents particles The total fitness value of and represents the weight coefficient; Indicates the total number of symbol points; Symbol point and The distance between Represents the maximum value of the distance between all pairs of symbolic points; Indicates the amount of attribute information; Symbol point No. attribute value; Indicates Reference value of each attribute value; and Respectively represent The maximum and minimum values ​​of the attribute values; , and Indicates the index value.

[0090] In the embodiment of the present invention, the function can optimize two main objectives at the same time. The first part focuses on the average distance between the symbol points, which helps to maintain the distribution and diversity of the point set; the second part focuses on the closeness of the attribute value to the reference value, which helps to ensure that the selected symbol points have the required attribute characteristics. and , which can flexibly control the balance between the two optimization objectives. The distance calculation and attribute value normalization in the function help reduce the impact of data scale and dimension on the optimization results. This means that the function can show relatively stable performance on different data sets.

[0091] In a preferred embodiment of the present invention, the above step 143, for each particle, calculates the gravitational force between it and all the remaining particles, including:

[0092] Step 1431, for each particle, by Calculate the gravitational force between it and all remaining particles;

[0093] in, Represents particles The magnitude of the combined gravitational force of all other particles; is a summation symbol, indicating that except for the particle All particles except Perform summation; is the total number of particles; is the gravitational constant; It is a particle Quality, It is a particle quality; Represents particles and particles The distance between Represents the particle Pointing to particles The unit vector of .

[0094] In an embodiment of the present invention, the method is based on the law of universal gravitation and can accurately simulate the gravitational effect between particles. By calculating the gravitational force of all other particles on each particle, the force of the particle in the physical space can be more realistically reflected, thereby improving the accuracy and authenticity of the simulation. In the optimization algorithm, the gravitational calculation between particles can prompt the particles to approach the global optimal solution. Each particle is affected by the gravitational force of other particles, which helps the particle group to conduct global exploration in the search space and avoid falling into the local optimal solution, thereby improving the global optimization ability of the algorithm. Since the gravitational force is dynamically calculated based on the distance and mass between particles, the algorithm can adaptively adjust the trajectory and speed of the particles. This dynamic adjustment capability enables the algorithm to better adapt to different optimization problems and search spaces, and improves the flexibility and versatility of the algorithm. The gravitational calculation of each particle in the method is independent, so it has a high potential for parallel computing. In practical applications, parallel computing technology can be used to accelerate the calculation process of gravity, thereby improving the operation efficiency of the algorithm.

[0095] In a preferred embodiment of the present invention, according to Newton's second law, the calculated gravitational force is used to update the velocity and position of each particle, and the velocity update formula is:

[0096] ;

[0097] in, It is a particle Speed ​​at the next moment; It is a particle Speed ​​at the current moment It is a particle quality; is the time step, representing the time interval between two updates;

[0098] The update formula of position is:

[0099] ;

[0100] in, It is a particle The position at the next moment; It is a particle The location at the current moment.

[0101] In the embodiment of the present invention, the speed and position of particles are updated by Newton's second law, which can more realistically simulate the dynamic behavior in the physical world. Using Newton's second law for updating, the speed and position of particles can be adjusted in real time according to the changes in the gravitational force between particles. This dynamic response capability enables the algorithm to quickly adapt to changes in the environment, thereby more effectively searching and optimizing. By setting an appropriate time step , we can control the update amplitude of particle speed and position, and ensure the stability and controllability of the algorithm. Newton's second law is a basic principle in physics. Using this principle to update makes the behavior of the algorithm more intuitive and easy to explain.

[0102] In a preferred embodiment of the present invention, the qualified rate of each pipeline section is The calculation formula is:

[0103] ;

[0104] in, Indicates the total number of pipeline sections; Indicates Importance coefficient of pipeline segment; Indicates The number of reference points in the segment pipeline; Indicates The weight coefficient of each benchmark point; and Respectively represent Section 1 The weight of the location information and attribute information of each benchmark point; and Respectively represent Section 1 The number of benchmarks with qualified locations and qualified attributes; Indicates Section 1 The total number of benchmarks.

[0105] In the embodiment of the present invention, this formula not only takes into account the number of pipeline segments and the number of reference points, but also introduces the importance coefficient, weight coefficient, and the number of qualified positions and attributes, so as to comprehensively evaluate the overall quality of each pipeline segment. This comprehensive evaluation method helps to more accurately reflect the actual qualified status of the pipeline. By adjusting the weight coefficient and , the weight of location information and attribute information in the qualified rate calculation can be flexibly adjusted. This formula takes into account every section of pipeline and every benchmark in detail, which helps to achieve refined management. Because this formula takes into account multiple dimensions and factors and calculates in a digital way, it can reduce the influence of subjective judgment to a certain extent and improve the objectivity and fairness of the evaluation.

[0106] In a preferred embodiment of the present invention, the above step 15, analyzing the similarity of the reference points between the multiple pipeline sections, by comparing the positions and attribute information of the reference points of different pipeline sections, and combining the qualified rate of each pipeline section, comprehensively evaluating the quality of the entire pipeline to obtain the evaluation result, may include:

[0107] Step 151, for each pipeline section, determine the number and position of its reference points, specifically including: obtaining relevant data of each pipeline section, including coordinate information and attribute information of the reference points; identifying the reference points of each pipeline section from the data, recording their number and position coordinates (x, y, z); storing the number and position information of the reference points of each pipeline section in an appropriate data structure;

[0108] Step 152, for two reference points A and B, their position coordinates are respectively ( x 1 , y 1 , z 1 )and( x 2 , y 2 , z 2 ), calculate the Euclidean distance d1 between the two reference points A and B; take the reciprocal of the Euclidean distance d1 as the position similarity score S1; convert the attributes of the reference points into numerical vectors, and for the attribute vectors of the two reference points and , calculate the Euclidean distance d2, and take the reciprocal of the Euclidean distance d2 as the attribute similarity score S2;

[0109] Step 153, weighted summing the location similarity score S1 and the attribute similarity score S2 to obtain a comprehensive similarity score, specifically including: setting the weights of location similarity and attribute similarity in the comprehensive evaluation according to actual needs; weighted summing the location similarity score S1 and the attribute similarity score S2 according to the set weights to obtain a comprehensive similarity score.

[0110] Step 154, calculates the weighted sum of the comprehensive similarity scores and uses it as the corresponding aggregate score of each pipeline segment, specifically including: for each pipeline segment, weightedly accumulating the comprehensive similarity scores of all its reference point pairs; normalizing the accumulated scores so that the scores between different pipeline segments can be directly compared; and storing the aggregate score of each pipeline segment in a data structure.

[0111] Step 155 compares the aggregate scores of all pipeline segments, and evaluates the quality of the entire pipeline according to the aggregate scores to obtain an evaluation result, which specifically includes: sorting the aggregate scores of all pipeline segments; and evaluating the quality of each pipeline segment according to the aggregate scores. A high score indicates a high-quality pipeline segment, and a low score indicates a pipeline segment that may need improvement or attention.

[0112] In an embodiment of the present invention, by comprehensively considering the location and attribute information of the benchmark points, the method can more comprehensively evaluate the quality of the pipeline. Not only the spatial distribution of the benchmark points is paid attention to, but also their attribute characteristics are taken into account, thereby providing a more accurate pipeline quality assessment. The Euclidean distance is used to calculate the similarity between the benchmark points. This quantitative method reduces the influence of subjective judgment. By weighted summation of the location similarity score and the attribute similarity score, a comprehensive similarity score is obtained. This method can comprehensively consider multiple factors, provide a more comprehensive assessment, and help to more accurately reflect the overall quality of the pipeline. By calculating the aggregate score of each pipeline segment and comparing the aggregate scores of all pipeline segments, the quality differences between different pipeline segments can be clearly seen. The weights in this method can be adjusted according to actual needs to adapt to different evaluation focuses.

[0113] In a preferred embodiment of the present invention, the above step 16, based on the evaluation result, identifying abnormal points of the pipeline segment, includes:

[0114] Step 161 : Count the aggregate scores of all pipeline segments. For each pipeline segment, if its aggregate score is lower than a set abnormal threshold, mark it as an abnormal point.

[0115] In the embodiment of the present invention, by setting the abnormal threshold and comparing it with the aggregate score, the pipeline section that is below the standard can be quickly identified, thereby realizing the rapid location of the abnormal point. Accurately marking the abnormal point helps maintenance personnel directly locate the problem, avoiding the tedious process of full-line investigation, and significantly improving the efficiency and accuracy of maintenance. By identifying and handling abnormal points at an early stage, potential safety risks can be reduced, the implementation of preventive maintenance strategies can be supported, and the occurrence of sudden failures can be reduced.

[0116] When it comes to specific applications, first, make sure that the aggregate scores of all pipeline segments have been obtained, which are obtained through comprehensive evaluation in the previous steps. According to historical data, industry standards or expert experience, set a reasonable abnormal threshold, which represents the minimum acceptable level of pipeline segment quality. Traverse the aggregate scores of all pipeline segments and compare them with the abnormal threshold one by one. For each pipeline segment, if its aggregate score is lower than the set abnormal threshold, it means that the quality of the pipeline segment is lower than the acceptable level, so it is marked as an abnormal point. All pipeline segments marked as abnormal are sorted into a list, including the number, location, aggregate score and other information of the pipeline segment for subsequent processing and analysis.

[0117] like Figure 2 As shown, an embodiment of the present invention further provides an intelligent optimization processing system for pipeline measurement data, comprising:

[0118] An acquisition module, configured to receive pipeline measurement data, wherein the pipeline measurement data includes location information and attribute information of a plurality of pipeline points;

[0119] A preprocessing module, used for preprocessing the pipeline measurement data to obtain preprocessed measurement data;

[0120] The segmentation module is used to segment the pre-processed measurement data and divide the pipeline into multiple segments according to the direction and curvature of the pipeline. Each segment contains several continuous pipeline points.

[0121] The calculation module is used to randomly select two symbolic points as reference points for each section of pipeline; calculate the qualified rate of each section of pipeline according to the position information and attribute information of the reference points and the preset quality standards;

[0122] The analysis module is used to analyze the similarity of the reference points between multiple pipeline sections. By comparing the location and attribute information of the reference points of different pipeline sections and combining the qualified rate of each pipeline section, the quality of the entire pipeline is comprehensively evaluated to obtain the evaluation results;

[0123] The identification module is used to identify abnormal points of the pipeline segment based on the evaluation results.

[0124] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0125] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0126] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0127] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent optimization processing method for pipeline measurement data, characterized in that: The method comprises: receiving pipeline measurement data, wherein the pipeline measurement data includes location information and attribute information of a plurality of pipeline points; Preprocessing the pipeline measurement data to obtain preprocessed measurement data; The pre-processed measurement data is segmented, and the pipeline is divided into multiple segments according to the direction and curvature of the pipeline, and each segment contains several continuous pipeline points; For each section of pipeline, two symbolic points are randomly selected as reference points; based on the location information and attribute information of the reference points and the preset quality standards, the qualified rate of each section of pipeline is calculated; Analyze the similarity of the benchmarks between multiple pipeline sections, compare the location and attribute information of the benchmarks of different pipeline sections, and combine the qualified rate of each pipeline section to comprehensively evaluate the quality of the entire pipeline to obtain the evaluation results; Based on the evaluation results, abnormal points in the pipeline segment are identified; For each pipeline section, two symbolic points are randomly selected as reference points, including: Determine all the symbolic points in each pipeline segment, randomly select two symbolic points from the candidate point set as a particle, and repeat to initialize multiple particles; Determine the fitness function used to evaluate the quality of the two selected symbol points, and calculate the fitness value of each initialized particle; For each particle, calculate the gravitational force between it and all the remaining particles; According to Newton's second law, the calculated gravity is used to update the speed and position of each particle. The position update means selecting a new symbol point and making sure that the updated particle is within the candidate point set. If it is beyond the boundary, it is adjusted. After each position update, the fitness value of the particle is recalculated. If the preset number of iterations is reached, the iteration is stopped and the corresponding particle is selected as the final result. The final result is that two symbolic points in the particle are selected as reference points; The calculation formula of the fitness function is: ； in, Represents particles The total fitness value of represents the weight coefficient; Indicates the total number of symbol points; Symbol point and The distance between Represents the maximum value of the distance between all pairs of symbolic points; Indicates the amount of attribute information; Symbolic point No. attribute value; Indicates Reference value of each attribute value; Respectively represent The maximum and minimum values ​​of the attribute values; Indicates the index value.

2. The intelligent optimization processing method for pipeline measurement data according to claim 1 is characterized in that: For each particle, calculate the gravitational force between it and all the remaining particles, including: For each particle, Calculate the gravitational force between it and all remaining particles; in, Represents particles The magnitude of the combined gravitational force of all other particles; is a summation symbol, indicating that except for the particle All particles except Perform summation; is the total number of particles; is the gravitational constant; It is a particle Quality, It is a particle quality; Represents particles and particles The distance between Represents the particle Pointing to particles The unit vector of .

3. The intelligent optimization processing method for pipeline measurement data according to claim 2 is characterized in that: According to Newton's second law, the calculated gravity is used to update the velocity and position of each particle. The velocity update formula is: ； in, It is a particle Speed ​​at the next moment; It is a particle Speed ​​at the current moment; It is a particle quality; is the time step, representing the time interval between two updates; The update formula of position is: ； in, It is a particle The position at the next moment; It is a particle The location at the current moment.

4. The intelligent optimization processing method for pipeline measurement data according to claim 3 is characterized in that: The qualified rate of each pipeline The calculation formula is: ； in, Indicates the total number of pipeline sections; Indicates Importance coefficient of pipeline segment; Indicates The number of reference points in the segment pipeline; Indicates The weight coefficient of each benchmark point; Respectively represent Section 1 The weight of the location information and attribute information of each benchmark point; Respectively represent Section 1 The number of benchmarks with qualified locations and qualified attributes; Indicates Section 1 The total number of benchmarks.

5. The intelligent optimization processing method for pipeline measurement data according to claim 4 is characterized in that: Analyze the similarity of the benchmarks between multiple pipeline sections, compare the location and attribute information of the benchmarks of different pipeline sections, and combine the qualified rate of each pipeline section to comprehensively evaluate the quality of the entire pipeline to obtain the evaluation results, including: For each pipeline section, determine the number and location of its reference points; For two reference points A and B, their position coordinates are , calculate the Euclidean distance d1 between the two reference points A and B; take the reciprocal of the Euclidean distance d1 as the position similarity score S1; convert the attributes of the reference points into numerical vectors, and for the attribute vectors of the two reference points , calculate the Euclidean distance d2, and take the reciprocal of the Euclidean distance d2 as the attribute similarity score S2; The location similarity score S1 and the attribute similarity score S2 are weighted and summed to obtain a comprehensive similarity score; Calculate the weighted sum of the comprehensive similarity scores and use it as the corresponding aggregate score for each pipeline segment; The aggregate scores of all pipeline segments are compared, and the quality of the entire pipeline is evaluated based on the aggregate scores to obtain an evaluation result.

6. The intelligent optimization processing method for pipeline measurement data according to claim 5 is characterized in that: Based on the evaluation results, abnormal points in the pipeline segment are identified, including: The aggregated scores of all pipeline segments are obtained. For each pipeline segment, if its aggregated score is lower than the set abnormal threshold, it is marked as an abnormal point.

7. An intelligent optimization processing system for pipeline measurement data, characterized in that: Applied to the method according to any one of claims 1 to 6, comprising: An acquisition module, configured to receive pipeline measurement data, wherein the pipeline measurement data includes location information and attribute information of a plurality of pipeline points; A preprocessing module, used for preprocessing the pipeline measurement data to obtain preprocessed measurement data; The segmentation module is used to segment the preprocessed measurement data and divide the pipeline into multiple segments according to the direction and curvature of the pipeline. Each segment contains several continuous pipeline points. The calculation module is used to randomly select two symbolic points as reference points for each section of pipeline; calculate the qualified rate of each section of pipeline according to the position information and attribute information of the reference points and the preset quality standards; The analysis module is used to analyze the similarity of the reference points between multiple pipeline sections. By comparing the location and attribute information of the reference points of different pipeline sections and combining the qualified rate of each pipeline section, the quality of the entire pipeline is comprehensively evaluated to obtain the evaluation results; The identification module is used to identify abnormal points of the pipeline segment based on the evaluation results.

8. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 6.

Images