Pipeline fault prediction method and device and computer equipment

Abstract

The invention relates to a pipeline fault prediction method and device and computer equipment. The method comprises the following steps: acquiring use record information, maintenance record information and environment change record information of each pipeline, and identifying pipeline state information and pipeline abnormal information of each pipeline based on the use record information and the maintenance record information of each pipeline; for each pipeline, identifying influence factor data of each pipeline fault influence factor corresponding to the pipeline based on the environment change record information of the environment where the pipeline is located, and identifying pipeline anomaly evaluation data of each pipeline anomaly type through a pipeline anomaly evaluation network based on the pipeline state information and the pipeline anomaly information of the pipeline; and on the basis of the pipeline anomaly evaluation data of each pipeline anomaly type and the influence factor data of each pipeline fault influence factor, predicting future fault information of the pipeline through a pipeline fault prediction model, thereby generating fault early warning information of the pipeline. By adopting the method, the fault prediction accuracy and timeliness of the pipeline can be improved.

Description

Technical Field

[0001] This application relates to the fields of big data analysis and artificial intelligence technology, and particularly to a pipeline fault prediction method, device, and computer equipment. Background Art

[0002] In modern urban construction, the pipeline system, as an important infrastructure, undertakes the responsibility of transporting various important resources such as water, gas, and electricity. With the development of the city and the growth of the population, the complexity and scale of the pipeline system are constantly expanding, which puts forward higher requirements for the maintenance and management of pipelines. Among them, the fault prediction of pipelines can effectively improve the effect of pipeline maintenance and management. Therefore, how to improve the fault prediction of pipelines is the current research focus.

[0003] Traditional technical solutions are to collect and analyze information such as the usage history data and maintenance records of pipelines, and establish a mathematical model to predict the remaining service life of pipelines. When it is predicted that a certain section of the pipeline may fail, the system will issue an alarm to remind the staff to conduct inspections and repairs. These methods often rely on a large amount of historical data. For newly built pipelines or pipelines lacking historical data, the accuracy of the prediction model may be affected. Moreover, the factors considered in this way are relatively single, and the deviation between the prediction result and the actual result is relatively large. As a result, the accuracy of pipeline fault prediction is relatively low. Summary of the Invention

[0004] Based on this, it is necessary to provide a pipeline fault prediction method, device, computer equipment, computer-readable storage medium, and computer program product for the above technical problems.

[0005] In a first aspect, this application provides a pipeline fault prediction method, including:

[0006] Obtain the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located, and based on the usage record information of each pipeline and the maintenance record information of each pipeline, identify the pipeline status information of each pipeline and the pipeline abnormality information of each pipeline;

[0007] For each pipeline, based on the environmental change record information of the environment where the pipeline is located, identify the influence factor data of each pipeline fault influence factor corresponding to the pipeline, and based on the pipeline status information of the pipeline and the pipeline abnormality information of the pipeline, through a pipeline abnormality evaluation network, identify the pipeline abnormality evaluation data of each pipeline abnormality type of the pipeline;

[0008] Based on the pipeline anomaly evaluation data for each of the pipeline anomaly types and the influencing factor data for each pipeline fault influencing factor corresponding to the pipeline, predict the future fault information of the pipeline through a pipeline fault prediction model, and generate a fault warning message for the pipeline based on the future fault information of the pipeline.

[0009] Optionally, the identifying the pipeline status information and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline includes:

[0010] For each pipeline, identify each pipeline usage feature of the pipeline based on the usage record information of the pipeline, and identify the current specification information of the pipeline and each abnormal maintenance result of the pipeline based on the maintenance record information of the pipeline;

[0011] Identify the pipeline status information of the pipeline based on each pipeline usage feature of the pipeline, and identify the specification change information of the pipeline based on the current specification information of the pipeline;

[0012] Identify the abnormal probability value of the pipeline in each pipeline anomaly type based on each abnormal maintenance result of the pipeline, and use the abnormal probability value of the pipeline in each pipeline anomaly type and the specification change information of the pipeline as the pipeline anomaly information of the pipeline.

[0013] Optionally, the identifying the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline based on the environmental change record information of the environment where the pipeline is located includes:

[0014] Split the environmental change record information into sub-environmental change record information of each environmental type, and extract the environmental feature data of each environmental type through a linear feature extraction network for each sub-environmental change record information of each environmental type;

[0015] In the database, query the pipeline fault influencing factors corresponding to each environmental type and the data conversion relationship between each environmental type and the pipeline fault influencing factors;

[0016] Based on the data conversion relationship between each environmental type and the pipeline fault influencing factors, convert the environmental feature data of each environmental type into the influencing factor data of each pipeline fault influencing factor.

[0017] Optionally, the identifying the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline through a pipeline anomaly evaluation network based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline includes:

[0018] Based on the specification change information of the pipeline, identify the initial pipeline remaining life range of the pipeline through the pipeline life evaluation strategy;

[0019] Based on the initial pipeline remaining life range of the pipeline, in the pipeline database, query the abnormal probability increment of each pipeline abnormal type within the initial pipeline remaining life range, and calculate the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline based on the abnormal probability value of each pipeline abnormal type of the pipeline and the abnormal probability increment of each pipeline abnormal type of the pipeline;

[0020] Based on the usage characteristics of each pipeline of the pipeline and the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline, identify the pipeline abnormal evaluation data of each pipeline abnormal type of the pipeline through the pipeline abnormal evaluation network.

[0021] Optionally, based on the pipeline abnormal evaluation data of each pipeline abnormal type and the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline, predict the future fault information of the pipeline through the pipeline fault prediction model, including:

[0022] Based on the actual pipeline abnormal probability of each pipeline abnormal type, screen each target pipeline abnormal type corresponding to the pipeline among each pipeline abnormal type through the pipeline abnormal screening strategy;

[0023] Based on the influencing factor data of each pipeline fault influencing factor and the pipeline abnormal evaluation data of each target pipeline abnormal type, predict the pipeline fault type of the pipeline and the pipeline fault data range corresponding to the pipeline fault type through the pipeline fault prediction model;

[0024] Take the pipeline fault type of the pipeline and the pipeline fault data range corresponding to the pipeline fault type as the future fault information of the pipeline.

[0025] Optionally, generate the fault warning information of the pipeline based on the future fault information of the pipeline, including:

[0026] Based on the pipeline fault data range corresponding to the pipeline fault type of the pipeline, identify the pipeline fault degree of the pipeline;

[0027] Based on the pipeline fault type of the pipeline and the pipeline fault degree of the pipeline, query the pipeline fault warning level of the pipeline and the pipeline fault warning method corresponding to the pipeline fault warning level in the warning database;

[0028] Generate the pipeline fault warning information of the pipeline through the pipeline fault warning method based on the pipeline fault warning level of the pipeline, the pipeline fault type of the pipeline, and the pipeline fault degree of the pipeline.

[0029] In a second aspect, the present application also provides a pipeline fault prediction device, including:

[0030] An acquisition module, configured to acquire the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located, and identify the pipeline state information of each pipeline and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline;

[0031] An identification module, configured to, for each pipeline, identify the influence factor data of each pipeline fault influence factor corresponding to the pipeline based on the environmental change record information of the environment where the pipeline is located, and identify the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline through a pipeline anomaly evaluation network based on the pipeline state information of the pipeline and the pipeline anomaly information of the pipeline;

[0032] A generation module, configured to predict the future fault information of the pipeline through a pipeline fault prediction model based on the pipeline anomaly evaluation data of each pipeline anomaly type and the influence factor data of each pipeline fault influence factor corresponding to the pipeline, and generate the fault warning information of the pipeline based on the future fault information of the pipeline.

[0033] Optionally, the acquisition module is specifically configured to:

[0034] For each pipeline, identify the usage characteristics of each pipeline based on the usage record information of the pipeline, and identify the current specification information of the pipeline and the abnormal maintenance results of each pipeline based on the maintenance record information of the pipeline;

[0035] Identify the pipeline state information of the pipeline based on the usage characteristics of each pipeline of the pipeline, and identify the specification change information of the pipeline based on the current specification information of the pipeline;

[0036] Identify the abnormal probability values of the pipeline in each pipeline anomaly type based on the abnormal maintenance results of the pipeline, and use the abnormal probability values of the pipeline in each pipeline anomaly type and the specification change information of the pipeline as the pipeline anomaly information of the pipeline.

[0037] Optionally, the identification module is specifically configured to:

[0038] Split the environmental change record information into sub-environmental change record information for each environmental type, and extract the environmental feature data for each environmental type through a linear feature extraction network;

[0039] In the database, query the pipeline failure influencing factors corresponding to each environmental type and the data conversion relationship between each environmental type and the pipeline failure influencing factors;

[0040] Based on the data conversion relationship between each environmental type and the pipeline failure influencing factors, convert the environmental feature data of each environmental type into the influencing factor data of each pipeline failure influencing factor.

[0041] Optionally, the recognition module is specifically configured to:

[0042] Based on the specification change information of the pipeline, identify the initial pipeline remaining life range of the pipeline through a pipeline life evaluation strategy;

[0043] Based on the initial pipeline remaining life range of the pipeline, query the abnormal probability increment of each pipeline abnormal type within the initial pipeline remaining life range in the pipeline database, and calculate the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline based on the abnormal probability value of each pipeline abnormal type of the pipeline and the abnormal probability increment of each pipeline abnormal type of the pipeline;

[0044] Based on the usage characteristics of each pipeline of the pipeline and the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline, identify the pipeline abnormal evaluation data of each pipeline abnormal type of the pipeline through a pipeline abnormal evaluation network.

[0045] Optionally, the generation module is specifically configured to:

[0046] Based on the actual pipeline abnormal probability of each pipeline abnormal type, screen the corresponding target pipeline abnormal types of the pipeline from each pipeline abnormal type through a pipeline abnormal screening strategy;

[0047] Based on the influencing factor data of each pipeline failure influencing factor and the pipeline abnormal evaluation data of each target pipeline abnormal type, predict the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type through a pipeline failure prediction model;

[0048] Take the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type as the future failure information of the pipeline.

[0049] Optionally, the generation module is specifically configured to:

[0050] Identify the pipeline fault degree corresponding to the pipeline fault type of the pipeline based on the pipeline fault data range of the pipeline;

[0051] Query the pipeline fault warning level of the pipeline and the corresponding pipeline fault warning method of the pipeline fault warning level in the warning database based on the pipeline fault type of the pipeline and the pipeline fault degree of the pipeline;

[0052] Generate the pipeline fault warning information of the pipeline through the pipeline fault warning method based on the pipeline fault warning level of the pipeline, the pipeline fault type of the pipeline, and the pipeline fault degree of the pipeline.

[0053] In a third aspect, the present application provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium. A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method described in any one of the first aspects are implemented.

[0055] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method described in any one of the first aspects are implemented.

[0056] The above pipeline fault prediction method, device and computer equipment obtain the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located, and identify the pipeline status information of each pipeline and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline; for each pipeline, based on the environmental change record information of the environment where the pipeline is located, identify the influence factor data of each pipeline fault influence factor corresponding to the pipeline, and based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline, through the pipeline anomaly evaluation network, identify the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline; based on the pipeline anomaly evaluation data of each pipeline anomaly type and the influence factor data of each pipeline fault influence factor corresponding to the pipeline, through the pipeline fault prediction model, predict the future fault information of the pipeline, and generate a fault warning information for the pipeline based on the future fault information of the pipeline. When predicting pipeline faults, this solution comprehensively considers information such as the usage records, maintenance records, and environmental change records of the pipeline, so as to comprehensively consider and analyze various factors affecting pipeline faults to identify the pipeline anomaly information, pipeline status information, and the influence factor data of the pipeline fault influence factors affecting each pipeline. Then, combined with the above information, through the pipeline anomaly evaluation network constructed by this solution, analyze the pipeline anomaly evaluation data of each pipeline anomaly type of each pipeline. Finally, predict the future fault information of the pipeline through the pipeline fault prediction model constructed by this solution. It avoids the problems of low timeliness and low accuracy of regular maintenance, and this solution does not require a large amount of historical data. Instead, by screening the record information related to pipeline faults, it can comprehensively evaluate various fault conditions of the pipeline in all aspects. Moreover, when actually analyzing, it also considers various environmental factors affecting pipeline faults, so as to predict the pipeline fault information, improve the accuracy of fault prediction, ensure real-time operation and real-time prediction, improve the timeliness and efficiency of predicting faults. Finally, this solution can generate warning information in time after identifying fault information, improve the immediacy and efficiency of manual warning, and thus comprehensively improve the accuracy and timeliness of pipeline fault prediction. Brief Description of the Drawings

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0058] Figure 1Schematic flowchart of a pipeline fault prediction method in an embodiment;

[0059] Figure 2 Schematic flowchart of a pipeline fault prediction example in an embodiment;

[0060] Figure 3 Block diagram of the structure of a pipeline fault prediction device in an embodiment;

[0061] Figure 4 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0062] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] The pipeline fault prediction method provided by the embodiments of the present application can be applied to an intelligent control system for pipeline fault prediction constructed. This system can be applied to a terminal, which can be but is not limited to various personal computers, laptop computers, medium-sized computers, etc. Among them, when predicting pipeline faults, the terminal comprehensively considers information such as the usage records, maintenance records, and environmental change records of the pipeline, so as to comprehensively consider and analyze the various factors affecting pipeline faults, in order to identify the pipeline anomaly information, pipeline status information, and the influencing factor data of the pipeline fault influencing factors affecting each pipeline. Then, combined with the above information, through the pipeline anomaly evaluation network constructed by this solution, the pipeline anomaly evaluation data of each pipeline anomaly type of each pipeline is analyzed. Finally, the future fault information of the pipeline is predicted through the pipeline fault prediction model constructed by this solution. It avoids the problems of low timeliness and low accuracy of regular maintenance, and this solution does not require a large amount of historical data. Instead, by screening the record information related to pipeline faults, the various fault conditions of the pipeline can be comprehensively evaluated in all aspects. And in actual analysis, various environmental factors affecting pipeline faults are also considered, so as to predict the pipeline fault information of the pipeline. While improving the accuracy of fault prediction, it can ensure real-time operation and real-time prediction, improving the timeliness and efficiency of predicting faults. Finally, this solution can generate warning information in time after identifying fault information, improving the immediacy and efficiency of manual warning, thus comprehensively improving the accuracy and timeliness of pipeline fault prediction.

[0064] In an exemplary embodiment, as Figure 1 shown, a pipeline fault prediction method is provided. Taking this method applied to a terminal as an example for illustration, it includes the following steps S101 to step S103. Among them:

[0065] Step S101: Obtain the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located, and identify the pipeline status information of each pipeline and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline.

[0066] In this embodiment, the terminal queries the usage record information of each pipeline and the maintenance record information of each pipeline in the historical database, and then the terminal obtains the environmental change record information of each environmental type of the environment where each pipeline is located from a third-party platform. Among them, the usage record information of each pipeline, for example, for the intelligent liquid dispenser in the production industry, every time the intelligent liquid dispenser produces a product, if the production task is applied to this pipeline, then the usage record information of this pipeline includes the production task of this product, production time, and liquid output volume and other information. And the maintenance record information of each pipeline includes various anomaly detection information when detecting this pipeline. For example, when the staff conducts maintenance on anomalies such as pipeline rust, pipeline deformation, pipeline dirt accumulation, pipeline aging, pipeline damage, pipeline fracture, and pipeline folding, the information recorded by the staff. And this third-party platform can be information from the meteorological bureau, geological monitoring bureau, etc. The various environmental types collected include but are not limited to environmental types such as temperature, meteorology, and time. Then, the terminal identifies the pipeline status information of each pipeline and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline. Among them, the pipeline status is the various usage characteristics of the pipeline. Among them, the usage characteristics are characterized as liquid output volume fluctuation characteristics, liquid output rate characteristics, liquid output quality characteristics, etc. And the pipeline anomaly information of the pipeline includes but is not limited to the anomaly probability value of each pipeline anomaly type of the pipeline and the specification change information of this pipeline. Among them, the pipeline anomaly types include but are not limited to anomaly types such as pipeline damage, pipeline deformation, pipeline foreign object accumulation, and pipeline fracture. The specific identification process will be described in detail later.

[0067] Step S102: For each pipeline, identify the influence factor data of each pipeline fault influence factor based on the environmental change record information of the environment where the pipeline is located, and identify the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline through the pipeline anomaly evaluation network based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline.

[0068] In this embodiment, for each pipeline, the terminal identifies the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline based on the environmental change record information of the environment where the pipeline is located, and identifies the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline through the pipeline anomaly evaluation network based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline. Among them, each pipeline fault influencing factor is a factor that affects pipeline faults in different environmental types. For example, the pipeline fault influencing factors include temperature expansion factor, humid corrosion factor, sand abrasion factor, high-frequency use influencing factor, etc. Among them, in the case of too high temperature, too frequent rain, etc., the liquid discharge task volume of the intelligent liquid dispenser or the usage frequency of urban pipelines may increase, thereby increasing the pipeline usage frequency. Among them, the pipeline anomaly evaluation network is an artificial neural network based on the pipeline anomaly evaluation index strategy. The specific evaluation process will be described in detail later.

[0069] Step S103: Based on the pipeline anomaly evaluation data of each pipeline anomaly type and the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline, predict the future fault information of the pipeline through the pipeline fault prediction model, and generate a fault warning message for the pipeline based on the future fault information of the pipeline.

[0070] In this embodiment, the terminal predicts the future fault information of the pipeline through the pipeline fault prediction model based on the pipeline anomaly evaluation data of each pipeline anomaly type and the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline, and generates a fault warning message for the pipeline based on the future fault information of the pipeline. Among them, the pipeline fault prediction model is a neural network based on reinforcement learning. The generated pipeline fault prediction information includes the pipeline fault warning level, pipeline fault type, and pipeline fault degree of the pipeline for warning. The specific generation process will be described in detail later.

[0071] Based on the above solution, when predicting pipeline failures, by comprehensively considering information such as the pipeline's usage records, maintenance records, and environmental change records, etc., a comprehensive consideration and analysis of various factors affecting pipeline failures is carried out to identify pipeline anomaly information, pipeline status information, and factor data of the pipeline failure influencing factors affecting each pipeline. Then, combined with the above information, through the pipeline anomaly evaluation network constructed by this solution, the pipeline anomaly evaluation data of each pipeline anomaly type of each pipeline is analyzed. Finally, through the pipeline failure prediction model constructed by this solution, the future failure information of the pipeline is predicted. This avoids the problems of low timeliness and low accuracy of regular maintenance. Moreover, this solution does not require a large amount of historical data, but by screening the record information related to pipeline failures, a comprehensive evaluation of various failure conditions of the pipeline can be carried out in all aspects. And in actual analysis, various aspects of the environmental factors affecting pipeline failures are also considered, so as to predict the pipeline failure information of the pipeline. While improving the accuracy of failure prediction, it can ensure real-time operation and real-time prediction, improving the timeliness and efficiency of predicting failures. Finally, this solution can generate early warning information in a timely manner after identifying failure information, improving the immediacy and efficiency of manual early warning, thus comprehensively improving the accuracy and timeliness of pipeline failure prediction.

[0072] Optionally, based on the usage record information of each pipeline and the maintenance record information of each pipeline, identify the pipeline status information of each pipeline and the pipeline anomaly information of each pipeline, including: for each pipeline, based on the usage record information of the pipeline, identify each pipeline usage feature of the pipeline, and based on the maintenance record information of the pipeline, identify the current specification information of the pipeline and each abnormal maintenance result of the pipeline; based on each pipeline usage feature of the pipeline, identify the pipeline status information of the pipeline, and based on the current specification information of the pipeline, identify the specification change information of the pipeline; based on each abnormal maintenance result of the pipeline, identify the abnormal probability value of the pipeline in each pipeline anomaly type, and use the abnormal probability value of the pipeline in each pipeline anomaly type and the specification change information of the pipeline as the pipeline anomaly information of the pipeline.

[0073] In this embodiment, for each pipeline, the terminal, based on the usage record information of the pipeline, identifies each pipeline usage feature of the pipeline, and based on the maintenance record information of the pipeline, identifies the current specification information of the pipeline and each abnormal maintenance result of the pipeline. Among them, the current specification information of the pipeline includes but is not limited to the current pipe diameter size, the current pipeline flow rate, the current remaining pipeline life value, and the current pipeline operation amplitude value, etc.

[0074] Then, the terminal identifies the pipeline status information of the pipeline based on the usage characteristics of each pipeline in the pipeline. Among them, in the pipeline feature database, the corresponding relationship between different pipeline statuses and the ranges of usage characteristics of each pipeline is stored. The terminal queries the pipeline status information corresponding to the usage characteristics of each pipeline through the usage characteristics of each pipeline. Among them, the pipeline status information includes the normal status of the pipeline and the abnormal status of the pipeline, etc.

[0075] After that, the terminal identifies the specification change information of the pipeline based on the current specification information of the pipeline. Among them, the specification change information includes the change values of the specifications of each pipeline.

[0076] The terminal identifies the abnormal probability values of the pipeline for each pipeline abnormal type based on the abnormal maintenance results of the pipeline. Among them, in the pipeline status database, the corresponding relationship between different abnormal maintenance results and the ranges of abnormal probability values of the pipeline abnormal type is stored. Then, the terminal identifies the abnormal probability values of the pipeline for each pipeline abnormal type adapted to the pipeline through the range adaptation strategy.

[0077] Finally, the terminal takes the abnormal probability values of the pipeline for each pipeline abnormal type and the specification change information of the pipeline as the pipeline abnormal information.

[0078] Based on the above solution, by analyzing the usage records and maintenance records of the pipeline, the status information and pipeline abnormal information of the pipeline are identified, improving the accuracy of abnormal identification and status identification of the pipeline.

[0079] Optionally, based on the environmental change record information of the environment where the pipeline is located, the influence factor data of each pipeline fault influence factor corresponding to the pipeline is identified, including: splitting the environmental change record information into sub-environmental change record information of each environmental type, and passing the sub-environmental change record information of each environmental type through a linear feature extraction network to extract the environmental feature data of each environmental type; querying in the database the pipeline fault influence factors corresponding to each environmental type and the data conversion relationship between each environmental type and the pipeline fault influence factors; based on the data conversion relationship between each environmental type and the pipeline fault influence factors, splitting the environmental feature data of each environmental type into the influence factor data of each pipeline fault influence factor.

[0080] In this embodiment, the terminal splits the environmental change record information into sub-environmental change record information for each environmental type, and extracts the environmental feature data for each environmental type through a linear feature extraction network. Among them, the linear feature extraction network is a convolutional neural network based on principal component analysis technology. In the database, the terminal queries the pipeline fault influencing factors corresponding to each environmental type and the data conversion relationship between each environmental type and the pipeline fault influencing factors. Among them, the data conversion relationship is the conversion relationship for converting the environmental change data of the environmental type into the influencing factor data of the pipeline fault influencing factors. Among them, the conversion relationship is preset in the database by the staff and obtained after a large number of experimental verifications, theoretical analyses, and result statistical analyses.

[0081] Finally, based on the data conversion relationship between each environmental type and the pipeline fault influencing factors, the terminal converts the environmental feature data of each environmental type into the influencing factor data of each pipeline fault influencing factor.

[0082] Based on the above solution, by analyzing the environmental change information, the influencing factor data of each pipeline fault influencing factor affecting the pipeline fault is identified, improving the comprehensiveness and accuracy of the analysis of the pipeline affected by the environment.

[0083] Optionally, based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline, through the pipeline anomaly evaluation network, the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline is identified, including: based on the specification change information of the pipeline, through the pipeline life evaluation strategy, the initial pipeline remaining life range of the pipeline is identified; based on the initial pipeline remaining life range of the pipeline, in the pipeline database, the anomaly probability increment of each pipeline anomaly type within the initial pipeline remaining life range is queried, and based on the anomaly probability value of each pipeline anomaly type of the pipeline and the anomaly probability increment of each pipeline anomaly type of the pipeline, the actual pipeline anomaly probability value of each pipeline anomaly type of the pipeline is calculated; based on the usage characteristics of each pipeline of the pipeline and the actual pipeline anomaly probability value of each pipeline anomaly type of the pipeline, through the pipeline anomaly evaluation network, the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline is identified.

[0084] In this embodiment, the terminal identifies the initial pipeline remaining life range of the pipeline based on the specification change information of the pipeline through the pipeline life evaluation strategy. Among them, the specification change information includes sub-change information of each pipeline specification type. The pipeline life evaluation strategy includes the corresponding relationship between each life range and the sub-change range of each pipeline specification type. Among them, the pipeline specification type includes but is not limited to the pipe diameter specification type, the pipeline flow velocity specification type, the pipeline operation amplitude specification type, etc.

[0085] Subsequently, based on the initial remaining life range of the pipeline, the key and difficult point management queries the abnormal probability increment of each pipeline abnormal type within the initial remaining life range of the pipeline in the pipeline database, and calculates the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline based on the abnormal probability value of each pipeline abnormal type of the pipeline and the abnormal probability increment of each pipeline abnormal type of the pipeline. This calculation process is to add the abnormal probability increment of each pipeline abnormal type to the abnormal probability value of each pipeline abnormal type, and the obtained probability value is used as the actual pipeline abnormal probability value.

[0086] Finally, based on the usage characteristics of each pipeline of the pipeline and the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline, the terminal identifies the pipeline abnormal evaluation data of each pipeline abnormal type of the pipeline through the pipeline abnormal evaluation network. Among them, the identification process of this abnormal evaluation network is to evaluate each pipeline abnormal type through the usage characteristics of each pipeline and the actual pipeline abnormal probability value of each pipeline abnormal type, and the obtained pipeline abnormal evaluation data can represent the abnormal evaluation value of this pipeline abnormal type. This abnormal evaluation value is used to feedback the adaptation situation between this pipeline abnormal type and the current usage characteristics of this pipeline. Among them, the higher the degree of adaptation, the faster the situation of this pipeline abnormal type occurring in this pipeline is characterized. And the lower the degree of adaptation, the slower the situation of this pipeline abnormal type occurring in this pipeline is characterized.

[0087] Based on the above solution, by comprehensively analyzing each pipeline abnormal type, the actual pipeline abnormal probability value of each pipeline abnormal type is identified, improving the identification accuracy of each pipeline abnormal type. Finally, through the abnormal evaluation network, the evaluation value of each pipeline abnormal type is identified, thereby improving the comprehensiveness and accuracy of the pipeline abnormal analysis of each pipeline.

[0088] Optionally, based on the pipeline abnormal evaluation data of each pipeline abnormal type and the influencing factor data of each pipeline failure influencing factor corresponding to the pipeline, the future failure information of the pipeline is predicted through the pipeline failure prediction model, including: based on the actual pipeline abnormal probability of each pipeline abnormal type, through the pipeline abnormal screening strategy, among each pipeline abnormal type, the corresponding target pipeline abnormal types of the pipeline are screened; based on the influencing factor data of each pipeline failure influencing factor and the pipeline abnormal evaluation data of each target pipeline abnormal type, through the pipeline failure prediction model, the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type are predicted; the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type are used as the future failure information of the pipeline.

[0089] In this embodiment, based on the actual pipeline anomaly probabilities of each pipeline anomaly type, the terminal screens each target pipeline anomaly type corresponding to the pipeline among each pipeline anomaly type through a pipeline anomaly screening strategy. Among them, the target pipeline anomaly type is the one with an actual pipeline anomaly probability greater than the anomaly probability threshold preset by the staff for the terminal.

[0090] Subsequently, based on the influencing factor data of each pipeline fault influencing factor and the pipeline anomaly evaluation data of each target pipeline anomaly type, the terminal predicts the pipeline fault type of the pipeline and the pipeline fault data range corresponding to the pipeline fault type through a pipeline fault prediction model. Finally, the terminal takes the pipeline fault type of the pipeline and the pipeline fault data range corresponding to the pipeline fault type as the future fault information of the pipeline.

[0091] Based on the above solution, after analyzing each target pipeline anomaly type and then combining the influencing factor data of each pipeline fault influencing factor, the pipeline fault type of the pipeline and the pipeline fault data range are comprehensively analyzed, improving the accuracy and comprehensiveness of pipeline fault analysis.

[0092] Optionally, based on the future fault information of the pipeline, a fault warning information of the pipeline is generated, including: identifying the pipeline fault degree based on the pipeline fault data range corresponding to the pipeline fault type of the pipeline; querying the pipeline fault warning level of the pipeline and the pipeline fault warning method corresponding to the pipeline fault warning level in the warning database based on the pipeline fault type of the pipeline and the pipeline fault degree of the pipeline; generating the pipeline fault warning information of the pipeline through the pipeline fault warning method based on the pipeline fault warning level, the pipeline fault type of the pipeline, and the pipeline fault degree of the pipeline.

[0093] In this embodiment, the terminal identifies the pipeline fault degree based on the pipeline fault data range corresponding to the pipeline fault type of the pipeline. Among them, different pipeline fault data ranges of different pipeline fault types correspond to different pipeline fault degrees. Then, the terminal queries the pipeline fault degree of the pipeline based on the pipeline fault data range corresponding to the pipeline fault type of the pipeline, where the pipeline fault degree is the pipeline fault degree value when the pipeline has this pipeline fault type.

[0094] Finally, the terminal queries the pipeline fault warning level of the pipeline and the pipeline fault warning method corresponding to the pipeline fault warning level in the warning database based on the pipeline fault type of the pipeline and the pipeline fault degree of the pipeline. Among them, the pipeline fault level can be divided into first-level pipeline fault, second-level pipeline fault, third-level pipeline fault, fourth-level pipeline fault, and fifth-level pipeline fault, and the pipeline fault warning method includes but is not limited to warning light warning, SMS / prompt information warning, emergency call warning, and special information warning, etc.

[0095] Finally, based on the pipeline fault warning level of the pipeline, the pipeline fault type of the pipeline, and the pipeline fault degree of the pipeline, the terminal generates pipeline fault warning information for the pipeline through the pipeline fault warning method. Among them, the generated pipeline fault warning information for the pipeline includes the specific warning content of the pipeline fault warning method. The warning content includes the pipeline fault warning level, pipeline fault type, and pipeline fault degree of the modified pipeline.

[0096] Based on the above solution, by analyzing the pipeline fault warning level, pipeline fault type, and pipeline fault degree of the pipeline, warnings are issued through different warning methods, which improves the flexibility, intelligence, and warning effect of pipeline fault warning.

[0097] This application also provides an example of pipeline fault prediction, as Figure 2 shown, and the specific processing process includes the following steps:

[0098] Step S201, obtain the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located.

[0099] Step S202, for each pipeline, based on the usage record information of the pipeline, identify each pipeline usage feature of the pipeline, and based on the maintenance record information of the pipeline, identify the current specification information of the pipeline and each abnormal maintenance result of the pipeline.

[0100] Step S203, based on each pipeline usage feature of the pipeline, identify the pipeline state information of the pipeline, and based on the current specification information of the pipeline, identify the specification change information of the pipeline.

[0101] Step S204, based on each abnormal maintenance result of the pipeline, identify the abnormal probability value of the pipeline in each pipeline abnormal type, and use the abnormal probability value of the pipeline in each pipeline abnormal type and the specification change information of the pipeline as the pipeline abnormal information of the pipeline.

[0102] Step S205, split the environmental change record information into sub-environmental change record information of each environmental type, and use the sub-environmental change record information of each environmental type to extract environmental feature data of each environmental type through a linear feature extraction network.

[0103] Step S206, in the database, query the pipeline fault influencing factors corresponding to each environmental type and the data conversion relationship between each environmental type and the pipeline fault influencing factors.

[0104] Step S207, based on the data conversion relationship between each environmental type and the pipeline fault influencing factors, convert the environmental feature data of each environmental type into influencing factor data of each pipeline fault influencing factor.

[0105] Step S208, based on the pipeline specification change information, identify the initial pipeline remaining life range of the pipeline through the pipeline life evaluation strategy.

[0106] Step S209, based on the initial pipeline remaining life range of the pipeline, query the abnormal probability increment of each pipeline abnormal type within the initial pipeline remaining life range in the pipeline database, and calculate the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline based on the abnormal probability value of each pipeline abnormal type of the pipeline and the abnormal probability increment of each pipeline abnormal type of the pipeline.

[0107] Step S210, based on each pipeline usage feature of the pipeline and the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline, identify the pipeline abnormal evaluation data of each pipeline abnormal type of the pipeline through the pipeline abnormal evaluation network.

[0108] Step S211, based on the actual pipeline abnormal probability of each pipeline abnormal type, screen the corresponding target pipeline abnormal types of the pipeline among each pipeline abnormal type through the pipeline abnormal screening strategy.

[0109] Step S212, based on the influencing factor data of each pipeline failure influencing factor and the pipeline abnormal evaluation data of each target pipeline abnormal type, predict the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type through the pipeline failure prediction model.

[0110] Step S213, take the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type as the future failure information of the pipeline.

[0111] Step S214, based on the actual pipeline abnormal probability of each pipeline abnormal type, screen the corresponding target pipeline abnormal types of the pipeline among each pipeline abnormal type through the pipeline abnormal screening strategy.

[0112] Step S215, based on the influencing factor data of each pipeline failure influencing factor and the pipeline abnormal evaluation data of each target pipeline abnormal type, predict the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type through the pipeline failure prediction model.

[0113] Step S216, take the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type as the future failure information of the pipeline.

[0114] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0115] Based on the same inventive concept, an embodiment of the present application further provides a pipeline fault prediction device for implementing the pipeline fault prediction method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the pipeline fault prediction device provided below can refer to the limitations on the pipeline fault prediction method in the above text, and will not be repeated here.

[0116] In an exemplary embodiment, as Figure 3 shown, a pipeline fault prediction device is provided, including: an acquisition module 310, an identification module 320, and a generation module 330, where:

[0117] The acquisition module 310 is configured to acquire the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located, and identify the pipeline status information of each pipeline and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline;

[0118] The identification module 320 is configured to, for each pipeline, identify the influence factor data of each pipeline fault influence factor corresponding to the pipeline based on the environmental change record information of the environment where the pipeline is located, and identify the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline through a pipeline anomaly evaluation network based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline;

[0119] The generation module 330 is configured to predict the future fault information of the pipeline through a pipeline fault prediction model based on the pipeline anomaly evaluation data of each pipeline anomaly type and the influence factor data of each pipeline fault influence factor corresponding to the pipeline, and generate a fault warning information of the pipeline based on the future fault information of the pipeline.

[0120] Optionally, the acquisition module 310 is specifically configured to:

[0121] For each pipeline, based on the usage record information of the pipeline, identify each pipeline usage feature of the pipeline, and based on the maintenance record information of the pipeline, identify the current specification information of the pipeline and each abnormal maintenance result of the pipeline;

[0122] Based on each pipeline usage feature of the pipeline, identify the pipeline status information of the pipeline, and based on the current specification information of the pipeline, identify the specification change information of the pipeline;

[0123] Based on each abnormal maintenance result of the pipeline, identify the abnormal probability value of the pipeline in each pipeline abnormal type, and use the abnormal probability value of the pipeline in each pipeline abnormal type and the specification change information of the pipeline as the pipeline abnormal information of the pipeline.

[0124] Optionally, the identification module 320 is specifically configured to:

[0125] Split the environmental change record information into sub-environmental change record information of each environmental type, and extract the environmental feature data of each environmental type through a linear feature extraction network for each sub-environmental change record information of each environmental type;

[0126] In the database, query the pipeline fault influencing factors corresponding to each environmental type and the data conversion relationship between each environmental type and the pipeline fault influencing factors;

[0127] Based on the data conversion relationship between each environmental type and the pipeline fault influencing factors, convert the environmental feature data of each environmental type into the influencing factor data of each pipeline fault influencing factor.

[0128] Optionally, the identification module 320 is specifically configured to:

[0129] Based on the specification change information of the pipeline, identify the initial pipeline remaining life range of the pipeline through a pipeline life evaluation strategy;

[0130] Based on the initial pipeline remaining life range of the pipeline, query the abnormal probability increment of each pipeline abnormal type within the initial pipeline remaining life range in the pipeline database, and calculate the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline based on the abnormal probability value of each pipeline abnormal type of the pipeline and the abnormal probability increment of each pipeline abnormal type of the pipeline;

[0131] Based on each pipeline usage feature of the pipeline and the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline, identify the pipeline abnormal evaluation data of each pipeline abnormal type of the pipeline through a pipeline abnormal evaluation network.

[0132] Optionally, the generating module 330 is specifically configured to:

[0133] Based on the actual pipeline anomaly probabilities of each of the pipeline anomaly types, through a pipeline anomaly screening strategy, screen out each target pipeline anomaly type corresponding to the pipeline among each of the pipeline anomaly types;

[0134] Based on the influencing factor data of each pipeline fault influencing factor and the pipeline anomaly evaluation data of each of the target pipeline anomaly types, through a pipeline fault prediction model, predict the pipeline fault type of the pipeline and the pipeline fault data range corresponding to the pipeline fault type;

[0135] Take the pipeline fault type of the pipeline and the pipeline fault data range corresponding to the pipeline fault type as the future fault information of the pipeline.

[0136] Optionally, the generating module 330 is specifically configured to:

[0137] Based on the pipeline fault data range corresponding to the pipeline fault type of the pipeline, identify the pipeline fault degree of the pipeline;

[0138] Based on the pipeline fault type of the pipeline and the pipeline fault degree of the pipeline, query the pipeline fault warning level of the pipeline and the pipeline fault warning method corresponding to the pipeline fault warning level in the warning database;

[0139] Based on the pipeline fault warning level of the pipeline, the pipeline fault type of the pipeline, and the pipeline fault degree of the pipeline, generate the pipeline fault warning information of the pipeline through the pipeline fault warning method.

[0140] Each module in the above pipeline fault prediction device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0141] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 4As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a pipeline fault prediction method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0142] Those skilled in the art can understand that Figure 4 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0143] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps of the pipeline fault prediction method.

[0144] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, it implements the steps of the pipeline fault prediction method.

[0145] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, it implements the steps of the pipeline fault prediction method.

[0146] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0147] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0148] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0149] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A pipeline fault prediction method, characterized in that, The method includes: Obtaining the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located, and identifying the pipeline status information of each pipeline and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline; For each pipeline, based on the environmental change record information of the environment where the pipeline is located, identifying the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline, and based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline, through a pipeline anomaly evaluation network, identifying the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline; Based on the pipeline anomaly evaluation data of each pipeline anomaly type and the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline, through a pipeline fault prediction model, predicting the future fault information of the pipeline, and based on the future fault information of the pipeline, generating a fault warning message for the pipeline.

2. The method according to claim 1, wherein The identifying the pipeline status information of each pipeline and the pipeline anomaly information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline includes: For each pipeline, based on the usage record information of the pipeline, identifying the usage characteristics of each pipeline of the pipeline, and based on the maintenance record information of the pipeline, identifying the current specification information of the pipeline and the abnormal maintenance results of each pipeline of the pipeline; Based on the usage characteristics of each pipeline of the pipeline, identifying the pipeline status information of the pipeline, and based on the current specification information of the pipeline, identifying the specification change information of the pipeline; Based on the abnormal maintenance results of each pipeline of the pipeline, identifying the abnormal probability values of the pipeline in each pipeline anomaly type, and using the abnormal probability values of the pipeline in each pipeline anomaly type and the specification change information of the pipeline as the pipeline anomaly information of the pipeline.

3. The method according to claim 1, wherein The identifying the influencing factor data of each pipeline fault influencing factor corresponding to the pipeline based on the environmental change record information of the environment where the pipeline is located includes: Splitting the environmental change record information into sub-environmental change record information of each environmental type, and extracting the environmental feature data of each environmental type through a linear feature extraction network for each sub-environmental change record information of each environmental type; Querying in the database the pipeline fault influencing factors corresponding to each environmental type and the data conversion relationship between each environmental type and the pipeline fault influencing factors; Based on the data conversion relationship between each environmental type and the pipeline fault influencing factors, converting the environmental feature data of each environmental type into the influencing factor data of each pipeline fault influencing factor.

4. The method according to claim 2, wherein The identifying the pipeline anomaly evaluation data of each pipeline anomaly type of the pipeline through a pipeline anomaly evaluation network based on the pipeline status information of the pipeline and the pipeline anomaly information of the pipeline includes: Based on the specification change information of the pipeline, identifying the initial pipeline remaining life range through a pipeline life evaluation strategy; Based on the initial pipeline remaining life range of the pipeline, in the pipeline database, query the abnormal probability increment of each pipeline abnormal type within the initial pipeline remaining life range, and calculate the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline based on the abnormal probability value of each pipeline abnormal type of the pipeline and the abnormal probability increment of each pipeline abnormal type of the pipeline; Based on the usage characteristics of each pipeline of the pipeline and the actual pipeline abnormal probability value of each pipeline abnormal type of the pipeline, through the pipeline abnormal evaluation network, identify the pipeline abnormal evaluation data of each pipeline abnormal type of the pipeline.

5. The method according to claim 4, wherein Based on the pipeline abnormal evaluation data of each pipeline abnormal type and the influencing factor data of each pipeline failure influencing factor corresponding to the pipeline, through the pipeline failure prediction model, predict the future failure information of the pipeline, including: Based on the actual pipeline abnormal probability of each pipeline abnormal type, through the pipeline abnormal screening strategy, screen each target pipeline abnormal type corresponding to the pipeline among each pipeline abnormal type; Based on the influencing factor data of each pipeline failure influencing factor and the pipeline abnormal evaluation data of each target pipeline abnormal type, through the pipeline failure prediction model, predict the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type; Take the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type as the future failure information of the pipeline.

6. The method according to claim 5, wherein Based on the future failure information of the pipeline, generate the failure warning information of the pipeline, including: Based on the actual pipeline abnormal probability of each pipeline abnormal type, through the pipeline abnormal screening strategy, screen each target pipeline abnormal type corresponding to the pipeline among each pipeline abnormal type; Based on the influencing factor data of each pipeline failure influencing factor and the pipeline abnormal evaluation data of each target pipeline abnormal type, through the pipeline failure prediction model, predict the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type; Take the pipeline failure type of the pipeline and the pipeline failure data range corresponding to the pipeline failure type as the future failure information of the pipeline.

7. A pipeline fault prediction device, characterized in that, The device includes: An acquisition module, configured to acquire the usage record information of each pipeline, the maintenance record information of each pipeline, and the environmental change record information of the environment where each pipeline is located, and identify the pipeline status information of each pipeline and the pipeline abnormal information of each pipeline based on the usage record information of each pipeline and the maintenance record information of each pipeline; An identification module, configured to, for each pipeline, identify the influencing factor data of each pipeline failure influencing factor corresponding to the pipeline based on the environmental change record information of the environment where the pipeline is located, and identify the pipeline abnormal evaluation data of each pipeline abnormal type of the pipeline through the pipeline abnormal evaluation network based on the pipeline status information of the pipeline and the pipeline abnormal information of the pipeline; A generation module is configured to predict future fault information of the pipeline through a pipeline fault prediction model based on pipeline anomaly evaluation data of each of the pipeline anomaly types and influence factor data of each pipeline fault influencing factor corresponding to the pipeline, and generate fault warning information of the pipeline based on the future fault information of the pipeline.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images