A pipe network health evaluation method and system based on big data analysis

Abstract

The present application relates to pipe network health evaluation technical field, and discloses a kind of pipe network health evaluation method and system based on big data analysis, comprising: based on the influence score of all class failure possibility influence factors of each pipe section of pipe network at current time and the score value, obtain the failure possibility score of each pipe section of pipe network at current time;Based on the score value of all class failure consequence severity influence factors of all reference accident cases of each pipe section of pipe network at current time, obtain the failure consequence severity score of each pipe section of pipe network at current time;Based on the failure possibility score and failure consequence severity score of all pipe sections of pipe network at current time, obtain the health evaluation value of each pipe section of pipe network at current time, and then obtain the health evaluation result of pipe network at current time.The present application realizes comprehensive failure possibility and failure consequence severity, and comprehensively evaluates the running state of pipe network at current time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipe network health evaluation, and particularly relates to a pipe network health evaluation method and system based on big data analysis. BACKGROUND

[0002] At present, pipe network systems, such as water supply, gas supply, oil transportation and the like, play a vital role in modern cities and industrial facilities. The continuous, safe and efficient operation of these systems is of great significance to the protection of residents' life, industrial production and even national security. However, pipe network systems often face various failure risks, which may be caused by design and self-defects, operation and management defects, maintenance and management defects, external damage, corrosion and fouling and the like, and the real-time monitoring and data analysis capabilities of the industrial internet platform can effectively optimize the above factors. Meanwhile, the problems caused by the failure of pipe network systems include but are not limited to personnel injury, environmental damage and economic loss. Therefore, it is of great significance to prevent failure and reduce loss by comprehensively evaluating the operation state of the pipe network system through the industrial internet platform, and timely discovering and processing potential safety hazards by using the intelligent sensing and big data analysis functions of the industrial internet platform.

[0003] However, the existing industrial internet platform can only accurately identify potential problems and issue timely alarms, and generate detailed reports and recommended measures through natural language processing technology, so that managers can quickly understand the problems and take appropriate action, but it does not comprehensively consider the failure possibility and the severity of the failure consequences, and realize the comprehensive health evaluation of the operation state of the pipe network at the current moment. For example, the patent with the publication number "CN118014185A" and the patent name "A municipal pipe network health online monitoring system based on big data" includes the following steps: real-time collection of sensor data on water flow, pressure, water quality, and pipeline vibration data, the sensor is installed at the key node of the municipal pipe network; the integrated system is used to integrate data from satellite data, geographic information system GIS, and municipal maintenance records; a benchmark model of pipe network health condition is constructed based on historical data using machine learning and data mining techniques; artificial intelligence algorithms are applied to analyze the collected real-time data to predict potential problems and maintenance needs of the pipe network; a real-time monitoring platform displays the current state of the pipe network and evaluates its health, and when an abnormal state is detected, the system automatically sends warning information to the maintenance department. The above patent can accurately identify potential problems and issue timely alarms. Through natural language processing technology, detailed reports and recommended measures are generated, so that managers can quickly understand the problems and take appropriate action. However, the patent can only accurately identify potential problems and issue timely alarms, and generate detailed reports and recommended measures through natural language processing technology, so that managers can quickly understand the problems and take appropriate action, but it does not comprehensively consider the failure possibility and the severity of the failure consequences, and realize the comprehensive health evaluation of the operation state of the pipe network at the current moment.

[0004] Therefore, the present application proposes a pipe network health evaluation method and system based on big data analysis. SUMMARY

[0005] The present invention provides a pipeline health evaluation method and system based on big data analysis, which serves as an industrial Internet platform and is used to obtain the influence scores of all types of failure influencing factors of each pipeline segment of the pipeline network at the current moment according to all failure moments of each pipeline segment of the pipeline network at the current moment, accurately quantify the degree of influence of each type of failure influencing factor of each pipeline segment of the pipeline network at the current moment on the failure possibility of the corresponding pipeline segment of the pipeline network, and then obtain the failure possibility score of each pipeline segment of the pipeline network at the current moment according to the influence scores and assigned scores of all types of failure influencing factors of each pipeline segment of the pipeline network at the current moment, thereby realizing the quantification of the possibility of failure of each pipeline segment of the pipeline network at the current moment, relying on the intelligent perception and data integration capabilities of the industrial Internet platform, according to the big data analysis technology and the assigned scores of all types of failure consequence severity influencing factors of all reference accident cases of each pipeline segment of the pipeline network at the current moment, and obtaining the failure consequence severity of each pipeline segment of the pipeline network at the current moment. The score realizes the quantification of the severity of the consequences that may be caused by the failure of each pipe section of the pipeline network at the current moment. According to the failure possibility score and failure consequence severity score of all pipe sections of the pipeline network at the current moment, the comprehensive analysis matrix of the pipeline network at the current moment is obtained. Then, according to the comprehensive analysis matrix of the pipeline network at the current moment, the failure possibility score weight and failure consequence severity score weight of the pipeline network at the current moment are obtained, which is convenient for the calculation of subsequent health evaluation values. According to the failure possibility score weight and failure consequence severity score weight of the pipeline network at the current moment, the health evaluation value of each pipe section of the pipeline network at the current moment is obtained, which realizes the quantification of the healthy operation degree of each pipe section of the pipeline network at the current moment. Finally, according to the health evaluation value of all pipe sections of the pipeline network at the current moment, the health evaluation result of the pipeline network at the current moment is obtained. Comprehensive aspects of failure possibility and failure consequence severity are achieved to realize a comprehensive health evaluation of the operating status of the pipeline network at the current moment.

[0006] The present invention provides a pipeline network health assessment method based on big data analysis, comprising:

[0007] S1: Based on all failure moments of each pipe section in the pipeline network at the current moment, obtain the influence scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, and based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, obtain the failure possibility score of each pipe section in the pipeline network at the current moment;

[0008] S2: Based on big data analysis technology and the scoring of all types of failure consequence severity influencing factors of all reference accident cases for each pipe section of the pipeline network at the current moment, the failure consequence severity score of each pipe section of the pipeline network at the current moment is obtained;

[0009] S3: based on the failure possibility score and the failure consequence severity score of all pipe sections of the pipe network at the current time, obtaining a comprehensive analysis matrix of the pipe network at the current time, and based on the comprehensive analysis matrix of the pipe network at the current time, obtaining a failure possibility score weight and a failure consequence severity score weight of the pipe network at the current time, and based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time, obtaining a health evaluation value of each pipe section of the pipe network at the current time;

[0010] S4: based on the health evaluation value of all pipe sections of the pipe network at the current time, obtaining a health evaluation result of the pipe network at the current time.

[0011] Preferably, based on the big data analysis, the pipe network health evaluation method S1: based on all failure times of each pipe section of the pipe network at the current time, obtaining an influence score of all failure-related influencing factors of each pipe section of the pipe network at the current time, and based on the influence score of all failure-related influencing factors of each pipe section of the pipe network at the current time and the assigned score, obtaining a failure possibility score of each pipe section of the pipe network at the current time, comprising:

[0012] all times from the start of operation to the current time of each pipe section of the pipe network, the pipe failure time of the corresponding pipe section of the pipe network is regarded as the predicted failure time of the corresponding pipe section of the pipe network at the current time;

[0013] all predicted failure times of each pipe section of the pipe network at the current time, any two consecutive predicted failure times are regarded as a predicted failure time group of the corresponding pipe section of the pipe network at the current time, if the time interval between the two predicted failure times in each predicted failure time group of each pipe section of the pipe network at the current time is greater than the preset time interval, the time midpoint of the two predicted failure times in the corresponding predicted failure time group of the corresponding pipe section of the pipe network at the current time is regarded as a segmentation time of the corresponding pipe section of the pipe network at the current time;

[0014] based on all segmentation times of each pipe section of the pipe network at the current time, grouping all predicted failure times of the corresponding pipe section of the pipe network at the current time, obtaining all predicted failure time groups of each pipe section of the pipe network at the current time, and the first predicted failure time in each predicted failure time group of each pipe section of the pipe network at the current time is regarded as the failure time of the corresponding pipe section of the pipe network at the current time, obtaining all failure times of each pipe section of the pipe network at the current time;

[0015] based on all failure times of each pipe section of the pipe network at the current time, obtaining an influence score of all failure-related influencing factors of each pipe section of the pipe network at the current time;

[0016] Based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, the failure possibility score of each pipe section in the pipeline network at the current moment is obtained.

[0017] Preferably, the pipeline network health assessment method based on big data analysis obtains the impact scores of all failure-related factors of each pipeline segment at the current moment based on all failure moments of each pipeline segment at the current moment, including:

[0018] Obtain the categories of failure influencing factors for each pipe section in the pipeline network at each failure moment at the current moment, and all categories of failure influencing factors include design and inherent defect influencing factors, operation and management defect influencing factors, maintenance and management defect influencing factors, external force damage influencing factors, and corrosion and scaling influencing factors;

[0019] The quotient of the number of occurrences of each type of failure influencing factor in all failure moments of each pipe section of the pipeline network at the current moment and the total number of all failure moments of the corresponding pipe section of the pipeline network at the current moment is taken as the influence score of the corresponding type of failure influencing factor of the corresponding pipe section of the pipeline network at the current moment.

[0020] Preferably, the pipeline network health assessment method based on big data analysis obtains the failure possibility score of each pipeline section in the pipeline network at the current moment based on the influence scores and assigned scores of all types of failure influencing factors of each pipeline section in the pipeline network at the current moment, including:

[0021] Obtain the score values ​​of all failure influencing factors for each pipe section of the pipe network at the current moment;

[0022] Based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, the failure possibility score of each pipe section in the pipeline network at the current moment is obtained, which is:

[0023]

[0024] Among them, β is the failure probability score of the currently calculated pipe section of the pipe network at the current moment, α i is the impact score of the i-th type of failure influencing factor of the currently calculated pipe section of the pipe network at the current moment, γ i is the score of the i-th type of failure influencing factor of the currently calculated pipe section of the pipe network at the current moment, α max is the maximum value of the influence scores of all types of failure influencing factors of the currently calculated pipe section of the pipe network at the current moment, γ max It is the maximum value of the scores of all types of failure influencing factors of the currently calculated pipe section of the pipe network at the current moment, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0025] Preferably, the pipe network health evaluation method based on big data analysis, S2: based on big data analysis technology and all reference accident cases of each pipe segment of the pipe network at the current time, all class failure consequence severity influence factor score assignment values are obtained, including:

[0026] Based on big data analysis technology and all reference accident cases of each pipe segment of the pipe network at the current time, all class failure consequence severity influence factor score assignment values of each reference accident case of each pipe segment of the pipe network at the current time are obtained, wherein all class failure consequence severity influence factor score assignment values include personnel injury factor score assignment values, environmental damage factor score assignment values, and economic loss factor score assignment values.

[0027] Based on all class failure consequence severity influence factor score assignment values of all reference accident cases of each pipe segment of the pipe network at the current time, failure consequence severity score values of each pipe segment of the pipe network at the current time are obtained, that is:

[0028]

[0029] Wherein, δ is the failure consequence severity score value of the current calculated pipe segment of the pipe network at the current time, A max is the maximum value of the personnel injury factor score assignment values of all reference accident cases of the current calculated pipe segment of the pipe network at the current time, A0 is the average value of the personnel injury factor score assignment values of all reference accident cases of the current calculated pipe segment of the pipe network at the current time, B max is the maximum value of the environmental damage factor score assignment values of all reference accident cases of the current calculated pipe segment of the pipe network at the current time, B0 is the average value of the environmental damage factor score assignment values of all reference accident cases of the current calculated pipe segment of the pipe network at the current time, C max is the maximum value of the economic loss factor score assignment values of all reference accident cases of the current calculated pipe segment of the pipe network at the current time, C0 is the average value of the economic loss factor score assignment values of all reference accident cases of the current calculated pipe segment of the pipe network at the current time, n is the number of cases of all reference accident cases of the current calculated pipe segment of the pipe network at the current time, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0030] Preferably, the pipe network health evaluation method based on big data analysis, based on the failure possibility score values and the failure consequence severity score values of all pipe segments of the pipe network at the current time, a comprehensive analysis matrix of the pipe network at the current time is obtained, including:

[0031] According to the failure possibility score values of all pipe segments of the pipe network at the current time from large to small, the ordinal definition of all pipe segments of the pipe network is defined from 1 incrementally, and the ordinal definition result of all pipe segments of the pipe network at the current time is obtained.

[0032] Based on the failure possibility score, failure consequence severity score and ordinal number of all pipe segments of the pipe network at the current time, the comprehensive analysis matrix of the pipe network at the current time is obtained, that is:

[0033]

[0034] Wherein, E is the comprehensive analysis matrix of the pipe network at the current time, σ1 is the failure possibility score of the pipe segment with ordinal number 1 of the pipe network at the current time, σ2 is the failure possibility score of the pipe segment with ordinal number 2 of the pipe network at the current time, σ m is the failure possibility score of the pipe segment with ordinal number m of the pipe network at the current time, τ1 is the failure consequence severity score of the pipe segment with ordinal number 1 of the pipe network at the current time, τ2 is the failure consequence severity score of the pipe segment with ordinal number 2 of the pipe network at the current time, τ m is the failure consequence severity score of the pipe segment with ordinal number m of the pipe network at the current time, and m is the number of all pipe segments of the pipe network.

[0035] Preferably, based on the comprehensive analysis matrix of the pipe network at the current time, the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time are obtained, including:

[0036] The product of the rank of the comprehensive analysis matrix of the pipe network at the current time and the average of all matrix elements of the comprehensive analysis matrix of the pipe network at the current time is taken as the first analysis coefficient of the pipe network at the current time;

[0037] The quotient value between the first analysis coefficient of the pipe network at the current time and the number of all matrix elements of the comprehensive analysis matrix of the pipe network at the current time is taken as the second analysis coefficient of the pipe network at the current time;

[0038] The difference value between the failure possibility score of each pipe segment of the pipe network at the current time and the second analysis coefficient of the pipe network at the current time is taken as the failure possibility score difference value of each pipe segment of the pipe network at the current time, and the difference value between the failure consequence severity score of each pipe segment of the pipe network at the current time and the second analysis coefficient of the pipe network at the current time is taken as the failure consequence severity score difference value of each pipe segment of the pipe network at the current time;

[0039] It is judged whether the failure possibility score difference value of each pipe segment of the pipe network at the current time is greater than the failure consequence severity score of the corresponding pipe segment of the pipe network at the current time, if yes, the corresponding pipe segment of the pipe network is taken as the failure weight analysis pipe segment of the pipe network at the current time, otherwise, the corresponding pipe segment of the pipe network is taken as the consequence weight analysis pipe segment of the pipe network at the current time;

[0040] The quotient value between the total number of all failure weight analysis pipe sections of the pipe network at the current time and the total number of all pipe sections of the pipe network is taken as the failure possibility score weight of the pipe network at the current time, and the quotient value between the total number of all consequence weight analysis pipe sections of the pipe network at the current time and the total number of all pipe sections of the pipe network is taken as the failure consequence severity score weight of the pipe network at the current time.

[0041] Preferably, based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time, the health evaluation value of each pipe section of the pipe network at the current time is obtained, including:

[0042]

[0043] Wherein, μ is the health evaluation value of the currently calculated pipe section of the pipe network at the current time, is the failure possibility score weight of the pipe network at the current time, is the failure consequence severity score weight of the pipe network at the current time, β is the failure possibility score of the currently calculated pipe section of the pipe network at the current time, δ is the failure consequence severity score of the currently calculated pipe section of the pipe network at the current time, β max is the maximum value in the failure possibility scores of all pipe sections of the pipe network at the current time, δ max is the maximum value in the failure consequence severity scores of all pipe sections of the pipe network at the current time, m is the number of all pipe sections of the pipe network, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0044] Preferably, the pipe network health evaluation method based on big data analysis, S4: based on the health evaluation value of all pipe sections of the pipe network at the current time, the health evaluation result of the pipe network at the current time is obtained, including:

[0045] Based on the health evaluation value of all pipe sections of the pipe network at the current time, the visualization result of the pipe network at the current time is obtained, and the visualization result of the pipe network at the current time is taken as the health evaluation result of the pipe network at the current time.

[0046] The application provides a pipe network health evaluation system based on big data analysis, which is used for executing any one of the pipe network health evaluation methods based on big data analysis in embodiments 1 to 9, and includes:

[0047] The first calculation module is used for obtaining the influence score of all failure-like influence factors of each pipe section of the pipe network at the current time based on all failure time of each pipe section of the pipe network at the current time, and obtaining the failure possibility score of each pipe section of the pipe network at the current time based on the influence score of all failure-like influence factors of each pipe section of the pipe network at the current time and the assigned score.

[0048] a second calculation module, configured to obtain a failure consequence severity score of each pipe section of the pipe network at the current time based on the big data analysis technology and score values of all class failure consequence severity influence factors of all reference accident cases of each pipe section of the pipe network at the current time;

[0049] an evaluation module, configured to obtain a comprehensive analysis matrix of the pipe network at the current time based on the failure possibility score and the failure consequence severity score of all pipe sections of the pipe network at the current time, and obtain a failure possibility score weight and a failure consequence severity score weight of the pipe network at the current time based on the comprehensive analysis matrix of the pipe network at the current time, and obtain a health evaluation value of each pipe section of the pipe network at the current time based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time;

[0050] a generation module, configured to obtain a health evaluation result of the pipe network at the current time based on the health evaluation value of all pipe sections of the pipe network at the current time.

[0051] The beneficial effects generated by the present application relative to the prior art are: as an industrial internet platform, according to all failure time points of each pipe section of the pipe network at the current time, the influence score of all failure-like influence factors of each pipe section of the pipe network at the current time is obtained, the influence degree of each failure-like influence factor of each pipe section of the pipe network at the current time on the failure possibility of the corresponding pipe section of the pipe network is accurately quantified, and then according to the influence score and the score value of all failure-like influence factors of each pipe section of the pipe network at the current time, the failure possibility score value of each pipe section of the pipe network at the current time is obtained, based on the intelligent perception and data integration capability of the industrial internet platform, the possibility of failure of each pipe section of the pipe network at the current time is quantified, according to the big data analysis technology and the score value of all failure consequence severity influence factors of all reference accident cases of each pipe section of the pipe network at the current time, the failure consequence severity score value of each pipe section of the pipe network at the current time is obtained, the consequence severity of the failure of each pipe section of the pipe network at the current time is quantified, according to the failure possibility score value and the failure consequence severity score value of all pipe sections of the pipe network at the current time, the comprehensive analysis matrix of the pipe network at the current time is obtained, and then according to the comprehensive analysis matrix of the pipe network at the current time, the failure possibility score value weight and the failure consequence severity score value weight of the pipe network at the current time are obtained, which is convenient for subsequent calculation of the health evaluation value, according to the failure possibility score value weight and the failure consequence severity score value weight of the pipe network at the current time, the health evaluation value of each pipe section of the pipe network at the current time is obtained, the health running degree of each pipe section of the pipe network at the current time is quantified, and finally according to the health evaluation value of all pipe sections of the pipe network at the current time, the health evaluation result of the pipe network at the current time is obtained, the failure possibility and the failure consequence severity are comprehensively evaluated, and the running state of the pipe network at the current time is comprehensively evaluated.

[0052] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the structure particularly pointed out in the written description and claims hereof.

[0053] The technical solutions of the present application will be further described in detail below with the help of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0054] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate embodiments of the present application and are used to explain the present application, and do not constitute a limitation on the present application. In the drawings:

[0055] Figure 1 A flow chart of a pipe network health evaluation method based on big data analysis in an embodiment of the present application;

[0056] Figure 2 Fig. 1 is a schematic diagram of a pipe network health evaluation system based on big data analysis according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are merely intended to illustrate and explain the present application, and are not intended to limit the present application.

[0058] Embodiment 1

[0059] The present application provides a pipe network health evaluation method based on big data analysis, referring to Figure 1 , comprising:

[0060] S1: obtaining an influence score of all failure-like influencing factors of each pipe segment of the pipe network at the current time based on all failure times of each pipe segment of the pipe network at the current time, and obtaining a failure possibility score of each pipe segment of the pipe network at the current time based on the influence score of all failure-like influencing factors of each pipe segment of the pipe network at the current time and the assigned score;

[0061] S2: obtaining a failure consequence severity score of each pipe segment of the pipe network at the current time based on big data analysis technology and all reference accident case failure-like consequence severity influencing factor assigned scores of each pipe segment of the pipe network at the current time;

[0062] S3: obtaining a comprehensive analysis matrix of the pipe network at the current time based on the failure possibility score and the failure consequence severity score of all pipe segments of the pipe network at the current time, obtaining a failure possibility score weight and a failure consequence severity score weight of the pipe network at the current time based on the comprehensive analysis matrix of the pipe network at the current time, and obtaining a health evaluation value of each pipe segment of the pipe network at the current time based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time;

[0063] S4: obtaining a health evaluation result of the pipe network at the current time based on the health evaluation value of all pipe segments of the pipe network at the current time.

[0064] In this embodiment, the pipe segment is a pipe segment after the pipeline of the pipe network is segmented.

[0065] In this embodiment, the failure time is the initial time of the corresponding pipe segment of the pipe network when each pipe failure event (the present application refers to the reference accident case) occurs, which is selected from all times between the start of the operation of each pipe segment of the pipe network and the current time.

[0066] In this embodiment, the influence score of the failure influencing factor is a numerical value that can reflect the influence degree of each failure influencing factor on the failure possibility of the corresponding pipe segment of the pipe network at the current time, which is obtained based on all failure time points of each pipe segment of the pipe network at the current time.

[0067] In this embodiment, the score value of the failure influencing factor is a score value given to each pipe segment of the pipe network at the current time for each type of failure influencing factor. In this application, the score value of each type of failure influencing factor is determined by AI technology and relevant data collected by multiple sensors in each pipe segment of the pipe network, for example, the score value of the corrosion and scaling influencing factor is determined by the corrosion and scaling data collected by multiple sensors in each pipe segment of the pipe network at the current time and the preset corrosion and scaling influencing factor score model (AI technology, a neural network model that can input the corrosion and scaling data of each pipe segment of the pipe network at the current time and output the score value of the corrosion and scaling influencing factor of the corresponding pipe segment of the pipe network at the corresponding time is trained by a large amount of corrosion and scaling data of a large number of pipe segments of a large number of pipe networks at a plurality of time points as input and the score value of the corrosion and scaling influencing factor of the corresponding pipe segment of the pipe network at the corresponding time annotated by a person as output).

[0068] In this embodiment, the failure possibility score is a numerical value representing the possibility of failure (failure is the state of being unable to work normally or achieving the expected function) of each pipe segment of the pipe network at the current time.

[0069] In this embodiment, the big data analysis technology is a series of technologies that use advanced algorithms, tools and methods to extract valuable information and knowledge from a large amount of, complex and rapidly changing data. In this application, the big data analysis technology is used to extract relevant data of all types of failure consequence severity influencing factors of each reference accident case of each pipe segment of the pipe network at the current time, for example, the relevant data of the personnel injury factor is the number of deaths and the number of injuries.

[0070] In this embodiment, the reference accident case is all the accident cases that have occurred before the current time and have caused the pipe failure of the corresponding pipe segment of the pipe network.

[0071] In this embodiment, the score value of each type of failure consequence severity influencing factor is a score value obtained based on the relevant data of each type of failure consequence severity influencing factor of each reference accident case of each pipe segment of the pipe network at the current time, which is used to represent the consequence severity of each type of failure consequence severity influencing factor of each reference accident case of each pipe segment of the pipe network at the current time.

[0072] In this embodiment, the failure consequence severity score is a numerical value that can represent the consequence severity that may be caused by the failure of each pipe segment of the pipe network at the current time.

[0073] In this embodiment, the comprehensive analysis matrix of the pipeline network at the current moment is a matrix used to analyze the failure possibility score weights and failure consequence severity score weights of the pipeline network at the current moment.

[0074] In this embodiment, the failure probability score weight is the failure probability score of each pipe segment of the pipeline network at the current moment, obtained based on the comprehensive analysis matrix of the pipeline network at the current moment, and the influence weight on the calculated health evaluation value of each pipe segment of the pipeline network at the current moment.

[0075] In this embodiment, the failure consequence severity score weight is the failure consequence severity score of each pipe section of the pipeline network at the current moment, obtained based on the comprehensive analysis matrix of the pipeline network at the current moment, and the influence weight on the calculated health evaluation value of each pipe section of the pipeline network at the current moment.

[0076] In this embodiment, the health evaluation value is an evaluation value obtained based on the failure possibility score weight and failure consequence severity score weight of the pipeline network at the current moment, which can characterize the health operation level of each pipe section in the pipeline network at the current moment.

[0077] In this embodiment, the health evaluation result of the pipeline network at the current moment is a visualization result of the pipeline network at the current moment, and the visualization result of the pipeline network at the current moment is a table containing health evaluation values ​​of all pipe sections of the pipeline network at the current moment.

[0078] The beneficial effects of the above technology are: according to all failure moments of each pipe section of the pipeline network at the current moment, the influence score of all types of failure influencing factors of each pipe section of the pipeline network at the current moment is obtained, and the degree of influence of each type of failure influencing factor of each pipe section of the pipeline network at the current moment on the failure possibility of the corresponding pipe section of the pipeline network is accurately quantified. Then, according to the influence score and assigned value of all types of failure influencing factors of each pipe section of the pipeline network at the current moment, the failure possibility score of each pipe section of the pipeline network at the current moment is obtained, and the possibility of failure of each pipe section of the pipeline network at the current moment is quantified. According to big data analysis technology and the assigned value of all types of failure consequence severity influencing factors of all reference accident cases of each pipe section of the pipeline network at the current moment, the failure consequence severity score of each pipe section of the pipeline network at the current moment is obtained, and the failure probability of each pipe section of the pipeline network at the current moment is quantified. The severity of the consequences that may be caused by failure is quantified. According to the failure possibility scores and failure consequence severity scores of all pipe sections in the pipeline network at the current moment, the comprehensive analysis matrix of the pipeline network at the current moment is obtained. Then, according to the comprehensive analysis matrix of the pipeline network at the current moment, the failure possibility score weight and failure consequence severity score weight of the pipeline network at the current moment are obtained, which is convenient for the calculation of subsequent health evaluation values. According to the failure possibility score weight and failure consequence severity score weight of the pipeline network at the current moment, the health evaluation value of each pipe section in the pipeline network at the current moment is obtained, which realizes the quantification of the healthy operation degree of each pipe section in the pipeline network at the current moment. Finally, according to the health evaluation values ​​of all pipe sections in the pipeline network at the current moment, the health evaluation result of the pipeline network at the current moment is obtained. Comprehensive aspects of failure possibility and failure consequence severity are achieved to realize a comprehensive health evaluation of the operating status of the pipeline network at the current moment.

[0079] Example 2:

[0080] Based on Example 1, a pipeline network health assessment method based on big data analysis, S1: Based on all failure moments of each pipeline segment in the pipeline network at the current moment, obtain the influence score of all types of failure influencing factors for each pipeline segment in the pipeline network at the current moment, and based on the influence score and assigned value of all types of failure influencing factors for each pipeline segment in the pipeline network at the current moment, obtain the failure possibility score of each pipeline segment in the pipeline network at the current moment, including:

[0081] The time when the pipeline of each pipe section of the pipe network fails during all the time periods from the start of operation to the current time is regarded as the predicted failure time of the corresponding pipe section of the pipe network at the current time;

[0082] each pipe segment of the pipe network at the current time is regarded as a segmentation time of the corresponding pipe segment of the pipe network at the current time, and if the time interval between the two predicted failure time points in each predicted failure time point group of each pipe segment of the pipe network at the current time is greater than the preset time interval, the time point midpoint between the two predicted failure time points in the corresponding predicted failure time point group of the corresponding pipe segment of the pipe network at the current time is regarded as a segmentation time of the corresponding pipe segment of the pipe network at the current time;

[0083] Based on all the segmentation times of each pipe segment of the pipe network at the current time, all the predicted failure time points of the corresponding pipe segment of the pipe network at the current time are grouped and divided to obtain all the predicted failure time point segmentation groups of each pipe segment of the pipe network at the current time, and the first predicted failure time point in each predicted failure time point segmentation group of each pipe segment of the pipe network at the current time is regarded as a failure time of the corresponding pipe segment of the pipe network at the current time to obtain all the failure times of each pipe segment of the pipe network at the current time.

[0084] Based on all the failure times of each pipe segment of the pipe network at the current time, the influence scores of all the failure-likeness influencing factors of each pipe segment of the pipe network at the current time are obtained.

[0085] Based on the influence scores and the assigned scores of all the failure-likeness influencing factors of each pipe segment of the pipe network at the current time, the failure possibility scores of each pipe segment of the pipe network at the current time are obtained.

[0086] In this embodiment, the running start is the time point at which the installation of each pipe segment of the pipe network is completed and normal work is started.

[0087] In this embodiment, the preset time interval is a time interval that is set in advance and used to determine the segmentation times of each pipe segment of the pipe network at the current time, and in this embodiment, the preset time interval is the time interval between any two adjacent time points among all the time points from the running start to the current time of the pipe segment of the pipe network.

[0088] In this embodiment, the time point midpoint is the time midpoint between the two predicted failure time points in each predicted failure time point group of each pipe segment of the pipe network at the current time.

[0089] In this embodiment, the grouping and division is a grouping process of obtaining all the predicted failure time point segmentation groups of each pipe segment of the pipe network at the current time based on all the segmentation times of each pipe segment of the pipe network at the current time, and in this embodiment, the grouping and division process is that all the predicted failure time points between two adjacent segmentation times are regarded as a predicted failure time point segmentation group.

[0090] The beneficial effect of the above technology is that all failure time points of each pipe section of the pipe network at the current time are obtained according to all predicted failure time points of each pipe section of the pipe network at the current time, and then the influence score and failure possibility score of all failure time points of each pipe section of the pipe network at the current time are obtained according to all failure time points of each pipe section of the pipe network at the current time, and a specific method for determining all failure time points of each pipe section of the pipe network at the current time is given in detail.

[0091] Embodiment 3:

[0092] Based on embodiment 2, the pipe network health evaluation method based on big data analysis obtains the influence score of all failure time points of each pipe section of the pipe network at the current time, including:

[0093] The category of the failure influencing factor of each failure time point of each pipe section of the pipe network at the current time is obtained, and all categories of the failure influencing factor include design and self-defect influencing factor, operation and management defect influencing factor, maintenance and management defect influencing factor, external force damage influencing factor, and corrosion and scaling influencing factor.

[0094] The quotient value between the occurrence number of each category of failure influencing factor in all failure time points of each pipe section of the pipe network at the current time and the total number of time points of all failure time points of the corresponding pipe section of the pipe network at the current time is taken as the influence score of the corresponding category of failure influencing factor of the corresponding pipe section of the pipe network at the current time.

[0095] In this embodiment, the design and self-defect influencing factor is that the pipeline of each pipe section of the pipe network fails due to the unreasonable risk of the design scheme of the pipe network itself.

[0096] In this embodiment, the operation and management defect influencing factor is that the pipeline of each pipe section of the pipe network fails due to unreasonable operation and management of the pipe network.

[0097] In this embodiment, the maintenance and management defect influencing factor is that the pipeline of each pipe section of the pipe network fails due to the failure of maintenance of the maintenance management of the pipe network.

[0098] In this embodiment, the external force damage influencing factor is that the pipeline of each pipe section of the pipe network fails due to the external force damage to the pipe network.

[0099] In this embodiment, the corrosion and scaling influencing factor is that the pipeline of each pipe section of the pipe network fails due to the corrosion and scaling in the pipeline of each pipe section of the pipe network.

[0100] In this embodiment, the category of the failure influencing factor of each pipe section of the pipe network at each failure time of the current time is the category of the most important influencing factor causing the pipe failure of the corresponding pipe section of the pipe network at each failure time of the current time (the category of the failure influencing factor of each pipe section of the pipe network at each failure time of the current time is only one category).

[0101] In this embodiment, the occurrence frequency is the number of times that each category of the failure influencing factor causes the pipe failure of the corresponding pipe section of the pipe network at all failure times of the current time.

[0102] The above technology has the beneficial effects that all categories of the failure influencing factor are determined, the influence score of each category of the failure influencing factor of each pipe section of the pipe network at all failure times of the current time is obtained, and the influence degree of each category of the failure influencing factor of each pipe section of the pipe network at the current time on the failure possibility of the corresponding pipe section of the pipe network is accurately quantified.

[0103] Embodiment 4:

[0104] Based on the pipe network health evaluation method based on big data analysis in Embodiment 2, the failure possibility score of each pipe section of the pipe network at the current time is obtained based on the influence score and the assigned score of each category of the failure influencing factor of each pipe section of the pipe network at the current time, and includes the following steps.

[0105] Obtaining the assigned score of each category of the failure influencing factor of each pipe section of the pipe network at the current time;

[0106] Obtaining the failure possibility score of each pipe section of the pipe network at the current time based on the influence score and the assigned score of each category of the failure influencing factor of each pipe section of the pipe network at the current time, that is,

[0107]

[0108] Wherein, β is the failure possibility score of the currently calculated pipe section of the pipe network at the current time, α i is the influence score of the i-th category of the failure influencing factor of the currently calculated pipe section of the pipe network at the current time, γ i is the assigned score of the i-th category of the failure influencing factor of the currently calculated pipe section of the pipe network at the current time, α max is the maximum value of the influence score of all categories of the failure influencing factor of the currently calculated pipe section of the pipe network at the current time, γ max is the maximum value of the assigned score of all categories of the failure influencing factor of the currently calculated pipe section of the pipe network at the current time, and ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0109] The beneficial effect of the above technology is: based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, the failure possibility score of each pipe section in the pipeline network at the current moment is obtained, thereby quantifying the possibility of failure of each pipe section in the pipeline network at the current moment. This embodiment provides in detail a specific method for quantifying the possibility of failure of each pipe section in the pipeline network at the current moment.

[0110] Example 5:

[0111] Based on Example 1, a pipeline network health assessment method based on big data analysis, S2: Based on the big data analysis technology and all types of failure consequence severity influencing factors of all reference accident cases for each pipeline section of the pipeline network at the current moment, a failure consequence severity score for each pipeline section of the pipeline network at the current moment is obtained, including:

[0112] Based on big data analysis technology and all reference accident cases at the current moment for each pipe section of the pipeline network, the scoring values ​​of all types of failure consequence severity influencing factors for each reference accident case at the current moment are obtained for each pipe section of the pipeline network. The scoring values ​​of all types of failure consequence severity influencing factors include the scoring values ​​of personnel injury factors, environmental damage factors, and economic loss factors.

[0113] Based on the scores of all types of failure consequence severity influencing factors of all reference accident cases for each pipe section of the pipeline network at the current moment, the failure consequence severity score of each pipe section of the pipeline network at the current moment is obtained, which is:

[0114]

[0115] Among them, δ is the failure consequence severity score of the currently calculated pipe section of the pipe network at the current moment, A max is the maximum value of the personnel injury factor score of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, A0 is the mean value of the personnel injury factor score of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, B max is the maximum value of the environmental damage factor scores of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, B0 is the mean value of the environmental damage factor scores of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, C max is the maximum value of the economic loss factor scores of all reference accident cases of the currently calculated pipe section of the pipeline network at the current moment, C0 is the mean value of the economic loss factor scores of all reference accident cases of the currently calculated pipe section of the pipeline network at the current moment, n is the number of cases of all reference accident cases of the currently calculated pipe section of the pipeline network at the current moment, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0116] In this embodiment, the personnel injury factor score value is the score value of the consequence severity of the personnel injury caused by the pipeline failure of the corresponding pipe segment in each reference accident case of each pipe segment of the pipe network at the current time.

[0117] In this embodiment, the environmental damage factor score value is the score value of the consequence severity of the environmental damage caused by the pipeline failure of the corresponding pipe segment in each reference accident case of each pipe segment of the pipe network at the current time.

[0118] In this embodiment, the economic loss factor score value is the score value of the consequence severity of the economic loss caused by the pipeline failure of the corresponding pipe segment in each reference accident case of each pipe segment of the pipe network at the current time.

[0119] The beneficial effects of the above technology are that the specific items of the score values of all types of failure consequence severity influencing factors are determined, and then the score values of the failure consequence severity of each pipe segment of the pipe network at the current time are obtained according to the big data analysis technology and the score values of all types of failure consequence severity influencing factors of all reference accident cases of each pipe segment of the pipe network at the current time, so as to realize the quantification of the consequence severity that may be caused by the failure of each pipe segment of the pipe network at the current time.

[0120] Embodiment 6:

[0121] On the basis of embodiment 1, the pipe network health evaluation method based on big data analysis obtains a comprehensive analysis matrix of the pipe network at the current time based on the failure possibility score values and the failure consequence severity score values of all pipe segments of the pipe network at the current time, including:

[0122] According to the failure possibility score values of all pipe segments of the pipe network at the current time from large to small, the ordinal numbers of all pipe segments of the pipe network are defined starting from 1 in ascending order, and the ordinal number definition results of all pipe segments of the pipe network at the current time are obtained.

[0123] Based on the failure possibility score values, the failure consequence severity score values and the ordinal number definition results of all pipe segments of the pipe network at the current time, the comprehensive analysis matrix of the pipe network at the current time is obtained, that is:

[0124]

[0125] Wherein, E is the comprehensive analysis matrix of the pipe network at the current time, σ1 is the failure possibility score value of the pipe segment with the ordinal number 1 of the pipe network at the current time, σ2 is the failure possibility score value of the pipe segment with the ordinal number 2 of the pipe network at the current time, σ mis a failure possibility score of a pipe segment with a serial number of m of the pipe network at the current time, τ1 is a failure consequence severity score of a pipe segment with a serial number of 1 of the pipe network at the current time, τ2 is a failure consequence severity score of a pipe segment with a serial number of 2 of the pipe network at the current time, τ m is a failure consequence severity score of a pipe segment with a serial number of m of the pipe network at the current time, and m is a number of all pipe segments of the pipe network.

[0126] The above technology has the beneficial effect that the comprehensive analysis matrix of the pipe network at the current time is obtained according to the failure possibility score and the failure consequence severity score of all pipe segments of the pipe network at the current time, facilitating the determination of the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time, and the embodiment specifically provides a specific method for constructing the comprehensive analysis matrix of the pipe network at the current time.

[0127] Embodiment 7:

[0128] Based on the pipe network health evaluation method based on big data analysis, the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time are obtained based on the comprehensive analysis matrix of the pipe network at the current time, including:

[0129] The product of the rank of the comprehensive analysis matrix of the pipe network at the current time and the average of all matrix elements of the comprehensive analysis matrix of the pipe network at the current time is taken as a first analysis coefficient of the pipe network at the current time;

[0130] The quotient value of the first analysis coefficient of the pipe network at the current time and the number of all matrix elements of the comprehensive analysis matrix of the pipe network at the current time is taken as a second analysis coefficient of the pipe network at the current time;

[0131] The difference value between the failure possibility score of each pipe segment of the pipe network at the current time and the second analysis coefficient of the pipe network at the current time is taken as a failure possibility score difference value of each pipe segment of the pipe network at the current time, and the difference value between the failure consequence severity score of each pipe segment of the pipe network at the current time and the second analysis coefficient of the pipe network at the current time is taken as a failure consequence severity score difference value of each pipe segment of the pipe network at the current time;

[0132] It is judged whether the failure possibility score difference value of each pipe segment of the pipe network at the current time is greater than the failure consequence severity score of the corresponding pipe segment of the pipe network at the current time, if yes, the corresponding pipe segment of the pipe network is taken as a failure weight analysis pipe segment of the pipe network at the current time, otherwise, the corresponding pipe segment of the pipe network is taken as a consequence weight analysis pipe segment of the pipe network at the current time;

[0133] The quotient value between the total number of pipe sections analyzed by all failure weights of the pipe network at the current time and the total number of all pipe sections of the pipe network is taken as the failure possibility score weight of the pipe network at the current time, and the quotient value between the total number of pipe sections analyzed by all consequence weights of the pipe network at the current time and the total number of all pipe sections of the pipe network is taken as the failure consequence severity score weight of the pipe network at the current time.

[0134] The above technology has the beneficial effect that the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time are obtained according to the comprehensive analysis matrix of the pipe network at the current time, which facilitates the calculation of the subsequent health evaluation value.

[0135] Embodiment 8:

[0136] Based on the pipe network health evaluation method based on big data analysis in Embodiment 1, the health evaluation value of each pipe section of the pipe network at the current time is obtained based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time, including:

[0137]

[0138] wherein μ is the health evaluation value of the currently calculated pipe section of the pipe network at the current time, is the failure possibility score weight of the pipe network at the current time, is the failure consequence severity score weight of the pipe network at the current time, β is the failure possibility score value of the currently calculated pipe section of the pipe network at the current time, δ is the failure consequence severity score value of the currently calculated pipe section of the pipe network at the current time, β max is the maximum value in the failure possibility score values of all pipe sections of the pipe network at the current time, δ max is the maximum value in the failure consequence severity score values of all pipe sections of the pipe network at the current time, m is the number of all pipe sections of the pipe network, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0139] The above technology has the beneficial effect that the health evaluation value of each pipe section of the pipe network at the current time is obtained based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time, which realizes the quantification of the health running degree of each pipe section of the pipe network at the current time. Embodiment 1 specifically provides a method for obtaining the health evaluation value of each pipe section of the pipe network at the current time based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time.

[0140] Embodiment 9:

[0141] On the basis of embodiment 1, the pipe network health evaluation method based on big data analysis, S4: based on the health evaluation value of all pipe sections of the pipe network at the current time, obtaining the health evaluation result of the pipe network at the current time, including:

[0142] Based on the health evaluation value of all pipe sections of the pipe network at the current time, the visualization result of the pipe network at the current time is obtained, and the visualization result of the pipe network at the current time is taken as the health evaluation result of the pipe network at the current time.

[0143] In this embodiment, the visualization result of the pipe network at the current time is a table containing the health evaluation value of all pipe sections of the pipe network at the current time.

[0144] The beneficial effects of the above technology are: based on the health evaluation value of all pipe sections of the pipe network at the current time, the health evaluation result of the pipe network at the current time is obtained, and the failure possibility and the failure consequence severity are comprehensively evaluated to realize the comprehensive health evaluation of the running state of the pipe network at the current time.

[0145] Embodiment 10:

[0146] The present application provides a pipe network health evaluation system based on big data analysis, which is used to execute any one of the pipe network health evaluation methods based on big data analysis in embodiments 1-9, and refers to Figure 2 , including:

[0147] The first calculation module is used to obtain the influence score of all failure-like influence factors of each pipe section of the pipe network at the current time based on all failure time of each pipe section of the pipe network at the current time, and obtain the failure possibility score of each pipe section of the pipe network at the current time based on the influence score of all failure-like influence factors of each pipe section of the pipe network at the current time and the score value.

[0148] The second calculation module is used to obtain the failure consequence severity score of each pipe section of the pipe network at the current time based on big data analysis technology and all failure consequence severity influence factor score values of all reference accident cases of each pipe section of the pipe network at the current time.

[0149] The evaluation module is used to obtain the comprehensive analysis matrix of the pipe network at the current time based on the failure possibility score and the failure consequence severity score of all pipe sections of the pipe network at the current time, and obtain the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time based on the comprehensive analysis matrix of the pipe network at the current time, and obtain the health evaluation value of each pipe section of the pipe network at the current time based on the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time.

[0150] The generating module is configured to obtain a health evaluation result of the pipe network at the current time based on the health evaluation values of all pipe sections of the pipe network at the current time.

[0151] The above technology has the beneficial effects that: according to all failure time points of each pipe section of the pipe network at the current time, the influence scores of all failure-likelihood influencing factors of each pipe section of the pipe network at the current time are obtained, the influence degree of each failure-likelihood influencing factor of each pipe section of the pipe network at the current time on the failure possibility of the corresponding pipe section of the pipe network is accurately quantified, then according to the influence scores and the assigned scores of all failure-likelihood influencing factors of each pipe section of the pipe network at the current time, the failure possibility score of each pipe section of the pipe network at the current time is obtained, the possibility of the failure of each pipe section of the pipe network at the current time is quantified, according to the big data analysis technology and the assigned scores of all failure consequence severity influencing factors of all reference accident cases at the current time, the failure consequence severity score of each pipe section of the pipe network at the current time is obtained, the severity of the consequences that may be caused by the failure of each pipe section of the pipe network at the current time is quantified, according to the failure possibility scores and the failure consequence severity scores of all pipe sections of the pipe network at the current time, the comprehensive analysis matrix of the pipe network at the current time is obtained, then according to the comprehensive analysis matrix of the pipe network at the current time, the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time are obtained, the calculation of the health evaluation value is facilitated, according to the failure possibility score weight and the failure consequence severity score weight of the pipe network at the current time, the health evaluation value of each pipe section of the pipe network at the current time is obtained, the health running degree of each pipe section of the pipe network at the current time is quantified, finally, according to the health evaluation values of all pipe sections of the pipe network at the current time, the health evaluation result of the pipe network at the current time is obtained, the running state of the pipe network at the current time is comprehensively evaluated from the failure possibility aspect and the failure consequence severity aspect.

[0152] Obviously, persons having ordinary skill in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application, and it is intended to include these modifications and variations.

Claims

1. A pipeline network health assessment method based on big data analysis, characterized in that: include: S1: Based on all failure moments of each pipe section in the pipeline network at the current moment, obtain the influence scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, and based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, obtain the failure possibility score of each pipe section in the pipeline network at the current moment; S2: Based on big data analysis technology and the scoring of all types of failure consequence severity influencing factors of all reference accident cases for each pipe section of the pipeline network at the current moment, the failure consequence severity score of each pipe section of the pipeline network at the current moment is obtained; S3: Based on the failure probability scores and failure consequence severity scores of all pipe sections in the pipeline network at the current moment, a comprehensive analysis matrix of the pipeline network at the current moment is obtained. Based on the comprehensive analysis matrix of the pipeline network at the current moment, the failure probability score weights and failure consequence severity score weights of the pipeline network at the current moment are obtained. Based on the failure probability score weights and failure consequence severity score weights of the pipeline network at the current moment, the health evaluation value of each pipe section in the pipeline network at the current moment is obtained. S4: Based on the health evaluation values ​​of all pipe sections in the pipeline network at the current moment, obtain the health evaluation result of the pipeline network at the current moment; The failure probability score of each pipe section in the pipeline network at the current moment is obtained based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, including: Obtain the score values ​​of all failure influencing factors for each pipe section of the pipe network at the current moment; Based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, the failure possibility score of each pipe section in the pipeline network at the current moment is obtained, which is: Among them, β is the failure probability score of the currently calculated pipe section of the pipe network at the current moment, α i is the impact score of the i-th type of failure influencing factor of the currently calculated pipe section of the pipe network at the current moment, γ i is the score of the i-th type of failure influencing factor of the currently calculated pipe section of the pipe network at the current moment, α max is the maximum value of the influence scores of all types of failure influencing factors of the currently calculated pipe section of the pipe network at the current moment, γ max is the maximum value of the scores of all failure influencing factors of the currently calculated pipe section of the pipe network at the current moment, ln is the natural logarithm, and the value of the natural constant e is 2.718; Among them, S2: Based on big data analysis technology and the scoring of all types of failure consequence severity influencing factors of all reference accident cases for each pipe section of the pipeline network at the current moment, the failure consequence severity score of each pipe section of the pipeline network at the current moment is obtained, including: Based on big data analysis technology and all reference accident cases at the current moment for each pipe section of the pipeline network, the scoring values ​​of all types of failure consequence severity influencing factors for each reference accident case at the current moment are obtained for each pipe section of the pipeline network. The scoring values ​​of all types of failure consequence severity influencing factors include the scoring values ​​of personnel injury factors, environmental damage factors, and economic loss factors. Based on the scores of all types of failure consequence severity influencing factors of all reference accident cases for each pipe section of the pipeline network at the current moment, the failure consequence severity score of each pipe section of the pipeline network at the current moment is obtained, which is: Among them, δ is the failure consequence severity score of the currently calculated pipe section of the pipe network at the current moment, A max is the maximum value of the personnel injury factor score of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, A0 is the mean value of the personnel injury factor score of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, B max is the maximum value of the environmental damage factor scores of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, B0 is the mean value of the environmental damage factor scores of all reference accident cases in the current calculated pipe section of the pipe network at the current moment, C max is the maximum value of the economic loss factor scores of all reference accident cases of the currently calculated pipe section of the pipeline network at the current moment, C0 is the mean value of the economic loss factor scores of all reference accident cases of the currently calculated pipe section of the pipeline network at the current moment, n is the number of cases of all reference accident cases of the currently calculated pipe section of the pipeline network at the current moment, ln is the natural logarithm, and the value of the natural constant e is 2.

718.

2. The pipeline network health assessment method based on big data analysis according to claim 1 is characterized in that: S1: Based on all failure moments of each pipe section in the pipeline network at the current moment, obtain the influence score of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, and based on the influence score and assigned value of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, obtain the failure possibility score of each pipe section in the pipeline network at the current moment, including: The time when the pipeline of each pipe section of the pipe network fails during all the time periods from the start of operation to the current time is regarded as the predicted failure time of the corresponding pipe section of the pipe network at the current time; Any two consecutive predicted failure moments of each pipe section of the pipeline network at the current moment in all predicted failure moments are regarded as a predicted failure moment group of the corresponding pipe section of the pipeline network at the current moment. If the time interval between the two predicted failure moments in each predicted failure moment group of each pipe section of the pipeline network at the current moment is greater than a preset time interval, the midpoint of the two predicted failure moments in the corresponding predicted failure moment group of the corresponding pipe section of the pipeline network at the current moment is regarded as the splitting moment of the corresponding pipe section of the pipeline network at the current moment. Based on all the segmentation moments of each pipe section of the pipe network at the current moment, all the predicted failure moments of the corresponding pipe section of the pipe network at the current moment are grouped and divided to obtain all the segmentation groups of all the predicted failure moments of each pipe section of the pipe network at the current moment, and the first predicted failure moment in each predicted failure moment segmentation group of each pipe section of the pipe network at the current moment is regarded as the failure moment of the corresponding pipe section of the pipe network at the current moment, to obtain all the failure moments of each pipe section of the pipe network at the current moment; Based on all failure moments of each pipe section in the pipeline network at the current moment, the influence scores of all failure-related influencing factors of each pipe section in the pipeline network at the current moment are obtained; Based on the influence scores and assigned scores of all types of failure influencing factors of each pipe section in the pipeline network at the current moment, the failure possibility score of each pipe section in the pipeline network at the current moment is obtained.

3. The pipeline network health assessment method based on big data analysis according to claim 2 is characterized in that: Based on all failure moments of each pipe section in the pipeline network at the current moment, the impact scores of all failure-related factors of each pipe section in the pipeline network at the current moment are obtained, including: Obtain the categories of failure influencing factors for each pipe section in the pipeline network at each failure moment at the current moment, and all categories of failure influencing factors include design and inherent defect influencing factors, operation and management defect influencing factors, maintenance and management defect influencing factors, external force damage influencing factors, and corrosion and scaling influencing factors; The quotient of the number of occurrences of each type of failure influencing factor in all failure moments of each pipe section of the pipeline network at the current moment and the total number of all failure moments of the corresponding pipe section of the pipeline network at the current moment is taken as the influence score of the corresponding type of failure influencing factor of the corresponding pipe section of the pipeline network at the current moment.

4. The pipeline network health assessment method based on big data analysis according to claim 1 is characterized in that: Based on the failure probability scores and failure consequence severity scores of all pipe sections in the pipeline network at the current moment, a comprehensive analysis matrix of the pipeline network at the current moment is obtained, including: According to the order of the failure probability scores of all pipe sections in the pipe network at the current moment from large to small, all pipe sections in the pipe network are defined with ordinal numbers increasing from 1, and the ordinal definition results of all pipe sections in the pipe network at the current moment are obtained; Based on the failure probability scores, failure consequence severity scores, and ordinal definition results of all pipe sections in the pipeline network at the current moment, the comprehensive analysis matrix of the pipeline network at the current moment is obtained, which is: Among them, E is the comprehensive analysis matrix of the pipe network at the current moment, σ1 is the failure probability score of the pipe section with sequence number 1 in the pipe network at the current moment, σ2 is the failure probability score of the pipe section with sequence number 2 in the pipe network at the current moment, and σ m is the failure probability score of the pipe section with sequence number m at the current moment, τ1 is the failure consequence severity score of the pipe section with sequence number 1 at the current moment, τ2 is the failure consequence severity score of the pipe section with sequence number 2 at the current moment, τ m is the failure consequence severity score of the pipe segment with sequence number m in the pipe network at the current moment, and m is the number of all pipe segments in the pipe network.

5. The pipeline network health assessment method based on big data analysis according to claim 1 is characterized in that: Based on the comprehensive analysis matrix of the pipeline network at the current moment, the failure probability score weight and failure consequence severity score weight of the pipeline network at the current moment are obtained, including: The product of the rank of the comprehensive analysis matrix of the pipe network at the current moment and the mean of all matrix elements of the comprehensive analysis matrix of the pipe network at the current moment is regarded as the first analysis coefficient of the pipe network at the current moment; The quotient of the first analysis coefficient of the pipe network at the current moment and the number of all matrix elements of the comprehensive analysis matrix of the pipe network at the current moment is regarded as the second analysis coefficient of the pipe network at the current moment; The difference between the failure probability score of each pipe section of the pipeline network at the current moment and the second analysis coefficient of the pipeline network at the current moment is regarded as the failure probability score difference of each pipe section of the pipeline network at the current moment, and the difference between the failure consequence severity score of each pipe section of the pipeline network at the current moment and the second analysis coefficient of the pipeline network at the current moment is regarded as the failure consequence severity score difference of each pipe section of the pipeline network at the current moment; Determine whether the failure probability score difference of each pipe section of the pipeline network at the current moment is greater than the failure consequence severity score of the corresponding pipe section of the pipeline network at the current moment. If so, the corresponding pipe section of the pipeline network is regarded as the failure weight analysis pipe section of the pipeline network at the current moment; otherwise, the corresponding pipe section of the pipeline network is regarded as the consequence weight analysis pipe section of the pipeline network at the current moment; The quotient of the total number of all failure weight analysis pipe sections in the pipeline network at the current moment and the total number of all pipe sections in the pipeline network is used as the failure possibility score weight of the pipeline network at the current moment, and the quotient of the total number of all consequence weight analysis pipe sections in the pipeline network at the current moment and the total number of all pipe sections in the pipeline network is used as the failure consequence severity score weight of the pipeline network at the current moment.

6. The pipeline network health assessment method based on big data analysis according to claim 1 is characterized in that: Based on the failure probability score weight and failure consequence severity score weight of the pipeline network at the current moment, the health evaluation value of each pipeline section in the pipeline network at the current moment is obtained, including: Among them, μ is the health evaluation value of the current calculated pipe section of the pipe network at the current moment, is the failure probability score weight of the pipeline network at the current moment, is the failure consequence severity score weight of the pipeline network at the current moment, β is the failure possibility score of the currently calculated pipe section of the pipeline network at the current moment, δ is the failure consequence severity score of the currently calculated pipe section of the pipeline network at the current moment, β max is the maximum value of the failure probability scores of all pipe sections in the pipe network at the current moment, δ max is the maximum value of the failure consequence severity scores of all pipe sections in the pipe network at the current moment, m is the number of all pipe sections in the pipe network, ln is the natural logarithm, and the value of the natural constant e is 2.

718.

7. The pipeline network health assessment method based on big data analysis according to claim 1 is characterized in that: S4: Based on the health evaluation values ​​of all pipe sections in the pipeline network at the current moment, obtain the health evaluation result of the pipeline network at the current moment, including: Based on the health evaluation values ​​of all pipe sections of the pipeline network at the current moment, a visualization result of the pipeline network at the current moment is obtained, and the visualization result of the pipeline network at the current moment is used as the health evaluation result of the pipeline network at the current moment.

8. A pipeline network health assessment system based on big data analysis, characterized in that: A method for evaluating the health of a pipe network based on big data analysis according to any one of claims 1 to 7, comprising: A first calculation module is configured to obtain, based on all failure moments of each pipe section in the pipe network at the current moment, an influence score of all types of failure influencing factors for each pipe section in the pipe network at the current moment, and obtain, based on the influence scores and assigned scores of all types of failure influencing factors for each pipe section in the pipe network at the current moment, a failure probability score for each pipe section in the pipe network at the current moment; The second calculation module is used to assign scores to all types of failure consequence severity influencing factors of all reference accident cases for each pipe section of the pipeline network at the current moment, thereby obtaining the failure consequence severity score of each pipe section of the pipeline network at the current moment; An evaluation module is used to obtain a comprehensive analysis matrix of the pipeline network at the current moment based on the failure probability scores and failure consequence severity scores of all pipeline sections in the pipeline network at the current moment, obtain the failure probability score weights and failure consequence severity score weights of the pipeline network at the current moment based on the comprehensive analysis matrix of the pipeline network at the current moment, and obtain a health evaluation value of each pipeline section in the pipeline network at the current moment based on the failure probability score weights and failure consequence severity score weights of the pipeline network at the current moment; The generation module is used to obtain the health evaluation result of the pipeline network at the current moment based on the health evaluation values ​​of all pipe sections of the pipeline network at the current moment.

Images