CN111472754B - Fault processing method and device for oil pumping well, storage medium and electronic equipment - Google Patents
Fault processing method and device for oil pumping well, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111472754B CN111472754B CN201911342605.8A CN201911342605A CN111472754B CN 111472754 B CN111472754 B CN 111472754B CN 201911342605 A CN201911342605 A CN 201911342605A CN 111472754 B CN111472754 B CN 111472754B
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- target
- triple
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses a fault processing method, a device, a storage medium and electronic equipment for an oil pumping well, wherein the method comprises the following steps: obtaining fault state information of a pumping well in a fault state, wherein the fault state information comprises at least one state keyword; searching at least one target triple matched with the state keyword from a plurality of triples in a pre-created knowledge map database; the triplets in the knowledge map database are generated based on historical failure data of the rod-pumped well, the historical failure data including at least: historical fault types of the pumping well, fault state data and processing measure data corresponding to the historical fault types; obtaining target fault type data and/or target treatment measure data of the rod-pumped well based on the target triples; and outputting the target fault type data and/or the target treatment measure data of the pumping well.
Description
Technical Field
The invention relates to the technical field of oil-gas exploration, in particular to a fault processing method and device for a rod-pumped well, a storage medium and electronic equipment.
Background
During the operation of the pumping well, various faults usually occur, such as the faults of load enlargement, map enlargement, working fluid level rise and the like.
At present, when a pumping well is subjected to fault treatment, on-site expert experience judgment is taken as a main part, an expert diagnoses the fault type of the pumping well, and then provides corresponding fault rescue measures and operation measures to guide maintenance personnel to carry out fault treatment on the pumping well.
Therefore, in the process of diagnosing the fault of the rod-pumped well, experts may need to refer to factors in multiple aspects, so that a great amount of time is consumed for fault diagnosis, and the fault diagnosis efficiency is low.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a storage medium, and an electronic device for handling a failure of a rod-pumped well, which overcome or at least partially solve the above problems. By pre-creating a knowledge graph database containing a plurality of triples, the triples matched with the state keywords can be searched in the knowledge graph database, and then fault type data and/or processing measure data in the triples are obtained, so that rapid fault judgment is realized.
The invention also provides a fault processing device of the pumping well, which is used for ensuring the actual realization and application of the method.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
a method of fault management in a rod-pumped well, the method comprising:
obtaining fault state information of a pumping well in a fault state, wherein the fault state information comprises at least one state keyword;
searching at least one target triple matched with the state keyword from a plurality of triples in a pre-created knowledge map database; the triplets in the knowledge map database are generated based on historical failure data of the rod-pumped well, the historical failure data including at least: historical fault types of the pumping well, fault state data and processing measure data corresponding to the historical fault types;
obtaining target fault type data and/or target treatment measure data of the rod-pumped well based on the target triples;
and outputting the target fault type data and/or the target treatment measure data of the pumping well.
In one implementation, a triplet within the knowledge-graph database includes two nodes and a relationship between the nodes, where:
two nodes in the triplet include: and the relation between the nodes in the triple is a logical relation between data corresponding to the nodes.
Optionally, a logical relationship of fault judgment is between the node of the fault state data and the node of the fault type data, and a logical relationship of fault processing is between the node of the fault state data and the node of the processing measure data.
In one implementation, searching for at least one target triple matching the state keyword from a plurality of triples in a pre-created knowledge graph database includes:
performing character comparison on the state keywords and nodes in each triple in a pre-established knowledge map database to obtain at least one target triple matched with the state keywords;
and the nodes formed by the fault state data in the target triple contain the state keywords or contain characters or character strings with similarity greater than a first threshold value with the state keywords.
In one implementation, obtaining target failure type data and/or target treatment measure data for the rod pumped well based on the target triplet includes:
obtaining a target logic relationship between nodes in the target triple;
under the condition that the target logical relationship is a logical relationship of fault judgment, acquiring node data in the target triple as target fault type data;
and under the condition that the target logical relationship is a fault processing logical relationship, acquiring node data in the target triple as target processing measure data.
In one implementation, outputting the target failure type data and/or the target treatment measure data of the rod-pumped well comprises:
and outputting the fault state information of the pumping well and the target fault type data and/or the target processing measure data of the pumping well in a preset output format.
Optionally, the processing measure data includes fault rescue measure data or fault operation measure data of the rod-pumped well.
A fault handling apparatus for a rod-pumped well, comprising:
the state obtaining unit is used for obtaining fault state information of the pumping well in a fault state, and the fault state information comprises at least one state keyword;
the triple searching unit is used for searching at least one target triple matched with the state keyword from a plurality of triples in a pre-established knowledge map database; the triplets in the knowledge map database are generated based on historical failure data of the rod-pumped well, the historical failure data including at least: historical fault types of the pumping well, fault state data and processing measure data corresponding to the historical fault types;
the target obtaining unit is used for obtaining target fault type data and/or target treatment measure data of the pumping well based on the target triple;
and the target output unit is used for outputting the target fault type data and/or the target treatment measure data of the oil pumping well.
A storage medium comprising a stored program, wherein the program performs the method of fault management in an oil well pumping well according to any of the preceding claims.
A processor for executing a program, wherein the program when executed performs a method of fault handling for a rod-pumped well as described in any preceding claim.
An electronic device comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to invoke program instructions in the memory to perform a method of fault handling for a pumped well as any of the above.
By means of the technical scheme, in the fault processing method, the fault processing device, the storage medium and the processor of the rod-pumped well, after fault state information to be processed is obtained, target triples matched with state keywords in the fault state information are searched in a knowledge map database containing a plurality of triples, and then target fault type data and/or target processing measure data in the target triples are obtained and then output, so that rapid fault judgment is achieved, corresponding processing measure data can be provided for workers, effective fault processing is conducted timely, a large amount of time consumed by expert subjective judgment is avoided, and fault judgment efficiency is improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating a method for handling a failure in a rod pumped well according to an embodiment of the present invention;
FIG. 2 is a partial flow chart of a method for fault handling in a rod pumped well according to an embodiment of the present invention;
FIG. 3 is a block diagram of a fault handling apparatus for a rod pumped well according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram of an apparatus according to an embodiment of the present invention;
FIG. 5 is a schematic diagram showing data related to failure handling in a pumped well in practice according to an embodiment of the present invention.
Detailed Description
The oil pumping well production fault disposal management is an accumulative knowledge management mode based on industry experience, and the management of the fault disposal is continuously improved along with the accumulation of the production experience.
The current knowledge management of the fault handling of the oil pumping well is mainly judged by field expert experience, and the accumulated experience of fault diagnosis is stored in a relevant fault handling summary document and a phase handling research report, so that systematic knowledge accumulation and knowledge sharing cannot be formed. Moreover, the processing mode that fault judgment can only be performed by an industry expert obviously needs to consume a large amount of time, so that the efficiency of fault judgment is obviously low, and meanwhile, the subjective judgment of the expert tends to introduce too many subjective factors, so that the accuracy of fault judgment is low.
The knowledge graph technology refers to the technology of establishing and applying the knowledge graph, and is a cross study integrating the directions of cognitive computation, knowledge representation and reasoning, information retrieval and extraction, natural language processing and semantic network, data mining, machine learning and the like. Together with big data and deep learning, the knowledge map becomes one of the core driving forces for promoting the development of internet and artificial intelligence.
The basic composition unit of the knowledge graph is an entity-relation-entity triple and a key value pair consisting of entities and related attribute values thereof, the entities are mutually connected through relations to form a reticular knowledge structure, and the knowledge graph based on a certain industry can effectively manage and apply industry knowledge to the greatest extent.
The construction of the knowledge graph refers to establishing a data mode of the graph, namely defining the structure of the whole knowledge graph. The application method of the industry knowledge graph is that an ontology and a data mode are defined for the knowledge graph based on a large amount of data, and then an entity is added into a knowledge base.
Based on this, the inventors of the present invention found in their studies that: the method scheme for the fault handling of the pumping well can be effectively managed through the establishment of the knowledge map of the fault handling of the pumping well, the accumulation and the application of the fault handling knowledge of the pumping well are formed through the establishment of a knowledge map body and an entity, the original judgment mode that the handling method can only be carried out through an industry expert is changed, an iterative model for knowledge search and knowledge addition is established in a knowledge base mode, and on-site production management personnel of the pumping well can quickly carry out the suggestion and the operation of the fault handling through the search of the knowledge map, so that the efficiency and the success rate of the fault handling of the pumping well are greatly improved.
Therefore, the inventor of the present invention has further studied and proposed a technical solution capable of handling the failure of the rod-pumped well, so as to solve the above various technical problems. Specifically, after the fault state information to be processed is obtained, the target triple matched with the state keyword in the fault state information is searched in the knowledge map database containing a plurality of triples, and then the target fault type data and/or the target processing measure data in the target triple are/is obtained and then output, so that rapid fault judgment is realized, corresponding processing measure data can be provided for workers, effective fault treatment can be carried out in time, a large amount of time consumed by subjective judgment of experts is avoided, and the efficiency of fault judgment is improved.
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, a flowchart of an implementation of a method for handling a failure of a rod-pumped well according to an embodiment of the present invention is shown, where the method may be applied to a terminal or a server capable of performing data processing, such as a cloud or a local server, and is mainly used to quickly determine a failure of a rod-pumped well and provide a corresponding determination result.
Specifically, the method in this embodiment may include the following steps:
step 101: and acquiring the fault state information of the rod-pumped well in the fault state.
Wherein the fault status information comprises at least one status key. The fault state information can be generated when the rod-pumped well fails to operate normally, and the fault state information contains keywords representing the current fault state of the rod-pumped well, such as keywords of maximum load reduction, indicator diagram hypertrophy, current increase and the like.
Step 102: and searching at least one target triple matched with the state keyword from a plurality of triples in a pre-created knowledge map database.
The triple in the knowledge map database is generated based on historical fault data of the pumping unit well, and the historical fault data at least comprises the following components: historical fault types of the pumping well, fault state data corresponding to the historical fault types and processing measure data. The historical fault type refers to data of fault types such as oil well pump leakage, sucker rod breakage and the like, the fault state data refers to state data such as indicator diagram thinning, indicator diagram flattening and the like, the processing measure data can include fault rescue measure data or fault operation measure data, the fault rescue measure data refers to measure data for carrying out rescue processing on the oil pumping well such as pump bumping invalidation, micro-touch production adjustment, shallow rod breakage well and rod fishing recovery and the like, and the fault operation measure data refers to measure data for carrying out operation processing on the oil pumping well such as 'whether sand is produced in a casing of a well with serious stratum leakage', ineffective fishing rod or deeper rod breakage position, direct repair operation and the like.
It should be noted that, the triples include two nodes and a relationship between the nodes (edges of the nodes), where two nodes in one triplet may be any two of the historical failure type, the failure status data, and the handling measure data in the historical failure data, and the relationship between the nodes refers to a logical relationship between two data.
Specifically, the target triplet searched in this embodiment includes node data: and fault state data, wherein the fault state data in the target triple are matched with the state keywords.
It should be noted that, one or more target triples may be used, and in addition to the fault state data, another node data is fault type data or processing measure data.
Step 103: and obtaining target fault type data and/or target treatment measure data of the oil pumping well based on the target triple.
If the node data in the target triple except the fault state data is fault type data, acquiring the fault type data in the target triple as the target fault type data of the rod-pumped well; and if the node data except the fault state data in the target triple is the processing measure data, obtaining the processing measure data in the target triple as the target processing measure data of the rod-pumped well.
Step 104: and outputting the target fault type data and/or the target treatment measure data of the pumping well.
In this embodiment, the target fault type data and/or the target processing measure data may be output to a terminal of a worker, such as a mobile phone or a device of a monitoring center, so as to prompt the worker to perform fault processing in time.
Specifically, in this embodiment, the fault status information of the rod-pumped well, the target fault type data of the rod-pumped well, and/or the target treatment measure data may be output in a preset output format. For example, the fault status information and its corresponding target fault type data and/or target treatment measure data are output to the terminal or device in a table format and in an order in the table.
According to the scheme, after the fault state information to be processed is obtained, the target triple matched with the state keyword in the fault state information is searched in the knowledge map database containing the triples, and then the target fault type data and/or the target processing measure data in the target triple are obtained and then output, so that rapid fault judgment is realized, corresponding processing measure data can be provided for a worker, effective fault processing can be performed in time, a large amount of time consumed by expert subjective judgment is avoided, and the efficiency of fault judgment is improved.
Specifically, the triples in the knowledge graph database include two nodes and a relationship between the nodes, where: two nodes in the triplet include: and the relation between the nodes in the triple is a logical relation between data corresponding to the nodes.
Wherein, the logical relationship between the node of the fault state data and the node of the fault type data is a fault judgment logical relationship, which represents that: when the oil pumping well has a fault state corresponding to the fault state data, determining the fault type of the oil pumping well as the type corresponding to the fault type data;
the node of the fault state data and the node of the processing measure data are in a logic relation of fault processing, and represent that: when the pumping well has a fault state corresponding to the fault state data, it can be determined that the pumping well can be subjected to fault treatment by adopting the treatment measures corresponding to the treatment measure data.
In an implementation manner, when at least one target triple matched with the state keyword is found in the multiple triples in the pre-created knowledge graph database in step 102, the following manner may be specifically implemented:
performing character comparison on the state keywords and nodes in each triple in a pre-established knowledge map database to obtain at least one target triple matched with the state keywords;
and the nodes formed by the fault state data in the target triple contain the state keywords or contain characters or character strings with similarity greater than a first threshold with the state keywords. For example, the node data in the target triple includes all the status keywords, or the node data in the target triple includes a part of the status keywords, or the node data in the target triple includes other characters or character strings although the status keywords themselves are not included, and the similarity between the characters or character strings and the status keywords is relatively high, i.e. higher than a first threshold, for example, the similarity between the character strings in the target triple and the status keywords reaches 90%, and exceeds the first threshold of 80%.
In one implementation, the step 103 of obtaining target failure type data and/or target treatment measure data for the rod-pumped well based on the target triplet may be implemented by:
step 201: and obtaining the target logic relationship among the nodes in the target triple.
The target logical relationship may be a logical relationship of fault judgment or a logical relationship of fault processing.
Step 202: and under the condition that the target logical relationship is a logical relationship of fault judgment, acquiring the node data in the target triple as target fault type data.
In this embodiment, the other node data except the fault state data obtained in the target triple is the target fault type data.
Step 203: and under the condition that the target logical relationship is a fault processing logical relationship, acquiring node data in the target triple as target processing measure data.
In this embodiment, the data of other nodes except the fault state data is obtained in the target triple as the target processing measure data.
Referring to fig. 3, a schematic structural diagram of a fault handling apparatus for a rod-pumped well according to a second embodiment of the present disclosure is shown, where the apparatus may be applied to a terminal or a server capable of performing data processing, such as a cloud or a local server, and is mainly used to quickly determine a fault of a rod-pumped well and provide a corresponding determination result.
Specifically, the apparatus in this embodiment may include the following units:
a state obtaining unit 301, configured to obtain fault state information of a rod-pumped well in a fault state, where the fault state information includes at least one state keyword;
a triple searching unit 302, configured to search, in a plurality of triples in a pre-created knowledge graph database, at least one target triple matched with the state keyword; the triplets in the knowledge map database are generated based on historical failure data of the rod-pumped well, the historical failure data including at least: historical fault types of the pumping well, fault state data and processing measure data corresponding to the historical fault types;
a target obtaining unit 303, configured to obtain target fault type data and/or target treatment measure data of the rod-pumped well based on the target triple;
and a target output unit 304, configured to output target fault type data and/or target treatment measure data of the rod-pumped well.
According to the scheme, after the fault state information to be processed is obtained, the target triple matched with the state keyword in the fault state information is searched in the knowledge map database containing the triples, and then the target fault type data and/or the target processing measure data in the target triple are obtained and then output, so that rapid fault judgment is realized, corresponding processing measure data can be provided for a worker, effective fault treatment can be timely performed, a large amount of time consumed by expert subjective judgment is avoided, and the efficiency of fault judgment is improved.
Wherein a triplet within the knowledge graph database comprises two nodes and a relationship between the nodes, wherein:
two nodes in the triplet include: and the relation between the nodes in the triple is a logical relation between data corresponding to the nodes.
Specifically, a logical relationship of fault judgment is between the node of the fault state data and the node of the fault type data, and a logical relationship of fault processing is between the node of the fault state data and the node of the processing measure data.
In one implementation manner, when the triple searching unit searches for at least one target triple matching the state keyword from a plurality of triples in a pre-created knowledge graph database, the triple searching unit may be implemented by:
performing character comparison on the state keywords and nodes in each triple in a pre-established knowledge map database to obtain at least one target triple matched with the state keywords; and the nodes formed by the fault state data in the target triple contain the state keywords or contain characters or character strings with similarity greater than a first threshold with the state keywords.
In one implementation, the target obtaining unit, when obtaining the target failure type data and/or the target treatment measure data of the rod-pumped well based on the target triplet, may be implemented by:
obtaining a target logic relationship between nodes in the target triple; under the condition that the target logical relationship is a logical relationship of fault judgment, acquiring node data in the target triple as target fault type data; and under the condition that the target logical relationship is a fault processing logical relationship, acquiring node data in the target triple as target processing measure data.
In one implementation, the target output unit, when outputting the target fault type data and/or the target treatment measure data of the rod-pumped well, may implement the following steps:
and outputting the fault state information of the pumping well and the target fault type data and/or the target processing measure data of the pumping well in a preset output format.
Optionally, the processing measure data includes fault rescue measure data or fault operation measure data of the rod-pumped well.
It should be noted that the failure handling apparatus for a rod-pumped well in this embodiment may include a processor and a memory, where the off-state obtaining unit, the triple searching unit, the target obtaining unit, the target outputting unit, and the like are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, and fault treatment of the rod-pumped well is realized by adjusting kernel parameters.
An embodiment of the present invention provides a storage medium having a program stored thereon, where the program, when executed by a processor, implements a method of handling a fault in an oil pumping well.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute the fault processing method of the oil pumping well.
An embodiment of the present invention provides an electronic device, as shown in fig. 4, the device includes at least one processor 401, and at least one memory 402 and a bus connected to the processor 401; 403, the processor 401 and the memory 402 complete communication with each other through the bus 403; processor 401 is operative to call program instructions in memory 402 to perform the above-described method of adjusting the price of a search keyword. The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
obtaining fault state information of a pumping well in a fault state, wherein the fault state information comprises at least one state keyword;
searching at least one target triple matched with the state keyword from a plurality of triples in a pre-created knowledge map database; the triplets in the knowledge map database are generated based on historical failure data of the rod-pumped well, the historical failure data including at least: historical fault types of the pumping well, fault state data and processing measure data corresponding to the historical fault types;
obtaining target fault type data and/or target treatment measure data of the rod-pumped well based on the target triples;
and outputting the target fault type data and/or the target treatment measure data of the pumping well.
Optionally, the triples in the knowledge graph database include two nodes and a relationship between the nodes, where:
two nodes in the triplet include: and the relation between the nodes in the triple is a logical relation between data corresponding to the nodes.
And the node of the fault state data and the node of the processing measure data are in a logical relationship of fault judgment, and the node of the fault state data and the node of the processing measure data are in a logical relationship of fault processing.
In one implementation, searching for at least one target triple matching the state keyword from a plurality of triples in a pre-created knowledge graph database includes:
performing character comparison on the state keywords and nodes in each triple in a pre-established knowledge map database to obtain at least one target triple matched with the state keywords;
and the nodes formed by the fault state data in the target triple contain the state keywords or contain characters or character strings with similarity greater than a first threshold value with the state keywords.
In one implementation, obtaining target failure type data and/or target treatment measure data for the rod pumped well based on the target triplet includes:
obtaining a target logic relationship between nodes in the target triple;
under the condition that the target logical relationship is a logical relationship of fault judgment, acquiring node data in the target triple as target fault type data;
and under the condition that the target logical relationship is a fault processing logical relationship, acquiring node data in the target triple as target processing measure data.
In one implementation, outputting the target failure type data and/or the target treatment measure data of the rod-pumped well comprises:
and outputting the fault state information of the pumping well and the target fault type data and/or the target processing measure data of the pumping well in a preset output format.
Optionally, the processing measure data includes fault rescue measure data or fault operation measure data of the rod-pumped well.
The following will illustrate the technical solution of the present invention by taking the fault handling of the rod-pumped well in oil exploration as an example with reference to the information related to the fault shown in fig. 5:
firstly, in the invention, triple creation is carried out on fault related data of the oil pumping well based on a knowledge graph in the oil exploration process, design and implementation are carried out according to scientific and rigorous ideas, and the triple creation is carried out according to three process nodes of body modeling, knowledge loading and knowledge searching. The following were used:
1. ontology modeling: on the basis of a knowledge system of the fault type, the fault confirmation (fault state), the rescue measures and the operation measures of the pumping well, a business model is expressed through an ontology according to the idea of a knowledge map, wherein the business model refers to that if a fault occurs in one pumping well, different fault confirmation methods exist according to different fault types, and meanwhile, different rescue measures and operation measures correspond to the different fault types, the specific expression means that the fault type, the fault confirmation, the rescue measures and the operation measures are considered to be the ontology, and the expression relationship among the fault type, the fault confirmation, the rescue measures and the operation measures is as described above. And then the fault type, the fault confirmation, the rescue measure and the operation measure (represented by the nodes of the knowledge graph) and the relationship between the fault type and the operation measure (represented by the nodes of the knowledge graph) are expressed by the nodes and the edges of the triples of the knowledge graph (the nodes and the edges of the triples of the knowledge graph are nodes, the relationship is described as that the fault type, the fault confirmation, the rescue measure and the operation measure are nodes, the fault state is specifically confirmed and then respectively corresponds to the fault type and the corresponding node for carrying out the rescue measure or the operation measure, only one node is arranged between the fault type and the corresponding node for carrying out the rescue measure or the operation measure), the relationship between the fault type, the fault confirmation, the rescue measure and the operation measure (represented by the edges of the knowledge graph, the specific relationship is represented by the different fault types corresponding to the different fault confirmation methods, and after the fault type is confirmed, the rescue measure or the, judging the concrete scheme of taking rescue measures and operation measures at the same time);
2. knowledge loading: knowledge is loaded in two ways, one way is to import structured data of knowledge according to standard formats of fault types, fault confirmation, rescue measures and operation measures, for example, importing a graph database of a knowledge graph, and when importing, importing according to the standard format, wherein the relationship of triples is included, and the construction process of the triples is the relationship process before the specific types, confirmation and measures. The second way is to extract knowledge from the unstructured document and load the knowledge into a knowledge map library by a manual labeling method.
3. Knowledge search: in the field production management of the oil pumping well, a user can search a knowledge result (target triple) which takes a fault type, fault confirmation, a rescue measure or an operation measure comprising keywords (keywords) as navigation through searching the state keywords in the triple of the knowledge graph, wherein the main keywords are shown in the following table 1, and after searching the state keywords, the knowledge graph model can find corresponding knowledge items and related knowledge items corresponding to the knowledge items and having ontology relations according to the keywords to display the corresponding knowledge items.
TABLE 1 keywords
In conclusion, the knowledge map technology is used for effectively managing and applying the fault handling knowledge of the oil pumping well, and the fault diagnosis efficiency and accuracy of the oil pumping well are greatly improved.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (9)
1. A method of fault management in a rod-pumped well, the method comprising:
obtaining fault state information of a pumping well in a fault state, wherein the fault state information comprises at least one state keyword;
performing character comparison on a node in each triple and the state keyword in a plurality of triples in a pre-created knowledge graph database, and determining the triple as a target triple when the node in the triple contains the state keyword or when a character or a character string with similarity greater than a first threshold value to the state keyword exists in the node in the triple; the triplets in the knowledge map database are generated based on historical failure data of the rod-pumped well, the historical failure data including at least: historical fault types of the pumping well, fault state data and processing measure data corresponding to the historical fault types; the triplets in the database comprise a triplet of fault type and fault state data, and a triplet of fault state data and processing measure data;
obtaining target fault type data and/or target treatment measure data of the rod-pumped well based on the target triples;
and outputting the target fault type data and/or the target treatment measure data of the pumping well.
2. The method of claim 1, wherein a triplet within the knowledge graph database comprises two nodes and a relationship between the nodes, wherein:
two nodes in the triplet include: and the relation between the nodes in the triple is a logical relation between data corresponding to the nodes.
3. The method of claim 2, wherein the node of the fault status data and the node of the fault type data are in a logical relationship of fault determination, and the node of the fault status data and the node of the processing measure data are in a logical relationship of fault processing.
4. The method of claim 1 or 2, wherein obtaining target failure type data and/or target treatment measure data for the rod pumped well based on the target triplet comprises:
obtaining a target logic relationship between nodes in the target triple;
under the condition that the target logical relationship is a logical relationship of fault judgment, acquiring node data in the target triple as target fault type data;
and under the condition that the target logical relationship is a fault processing logical relationship, acquiring node data in the target triple as target processing measure data.
5. The method of claim 1 or 2, wherein outputting the target failure type data and/or the target treatment measure data for the rod pumped well comprises:
and outputting the fault state information of the pumping well and the target fault type data and/or the target processing measure data of the pumping well in a preset output format.
6. The method of claim 2, wherein the treatment measure data comprises a fault rescue measure data or a fault operational measure data for the rod pumped well.
7. A fault handling device for a rod-pumped well, comprising:
the state obtaining unit is used for obtaining fault state information of the pumping well in a fault state, and the fault state information comprises at least one state keyword;
the triple searching unit is used for performing character comparison on a node in each triple and the state keyword in a plurality of triples in a pre-created knowledge map database, and determining the triple as a target triple when the node in the triple contains the state keyword or when a character or a character string with similarity greater than a first threshold value with the state keyword exists in the node in the triple; the triplets in the knowledge map database are generated based on historical failure data of the rod-pumped well, the historical failure data including at least: historical fault types of the pumping well, fault state data and processing measure data corresponding to the historical fault types; the triplets in the database comprise a triplet of fault type and fault state data, and a triplet of fault state data and processing measure data;
the target obtaining unit is used for obtaining target fault type data and/or target treatment measure data of the pumping well based on the target triple;
and the target output unit is used for outputting the target fault type data and/or the target treatment measure data of the oil pumping well.
8. A storage medium comprising a stored program, wherein the program performs the method of fault management in an oil well pumping according to any of claims 1 to 6.
9. An electronic device comprising at least one processor, and at least one memory, bus connected to the processor; the processor and the memory complete mutual communication through the bus; the processor is configured to invoke the program instructions in the memory to perform the method of fault handling for a rod-pumped well according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911342605.8A CN111472754B (en) | 2019-12-23 | 2019-12-23 | Fault processing method and device for oil pumping well, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911342605.8A CN111472754B (en) | 2019-12-23 | 2019-12-23 | Fault processing method and device for oil pumping well, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111472754A CN111472754A (en) | 2020-07-31 |
| CN111472754B true CN111472754B (en) | 2021-01-22 |
Family
ID=71746192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911342605.8A Active CN111472754B (en) | 2019-12-23 | 2019-12-23 | Fault processing method and device for oil pumping well, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111472754B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672670A (en) * | 2021-07-23 | 2021-11-19 | 中国航空工业集团公司上海航空测控技术研究所 | Aircraft CAS alarm message-based aircraft structured manual display method |
| CN113792344A (en) * | 2021-09-17 | 2021-12-14 | 平安国际智慧城市科技股份有限公司 | Data desensitization processing method, device, equipment and storage medium |
| CN116644810B (en) * | 2023-05-06 | 2024-04-05 | 国网冀北电力有限公司信息通信分公司 | Power grid fault risk treatment method and device based on knowledge graph |
| CN116893924B (en) * | 2023-09-11 | 2023-12-01 | 江西南昌济生制药有限责任公司 | Equipment fault processing method, device, electronic equipment and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255134B (en) * | 2017-07-12 | 2021-08-31 | 中国石油天然气股份有限公司 | Method for acquiring fault condition of pumping well |
| US10536294B2 (en) * | 2017-07-17 | 2020-01-14 | Midea America Corp. | Computer-based platform for quality management of home devices |
| CN108509483A (en) * | 2018-01-31 | 2018-09-07 | 北京化工大学 | The mechanical fault diagnosis construction of knowledge base method of knowledge based collection of illustrative plates |
| CN109947898B (en) * | 2018-11-09 | 2021-03-05 | 中国电子科技集团公司第二十八研究所 | Equipment fault testing method based on intellectualization |
| CN109460010B (en) * | 2018-12-18 | 2020-11-17 | 彩虹无线（北京）新技术有限公司 | Vehicle fault detection method and device based on knowledge graph and storage medium |
| CN110033101B (en) * | 2019-03-07 | 2021-02-12 | 华中科技大学 | Hydroelectric generating set fault diagnosis method and system based on knowledge graph of fusion features |
| CN109992673A (en) * | 2019-04-10 | 2019-07-09 | 广东工业大学 | A kind of knowledge mapping generation method, device, equipment and readable storage medium storing program for executing |
| CN110543546B (en) * | 2019-07-18 | 2022-03-22 | 华瑞新智科技（北京）有限公司 | Method and device for inquiring hidden danger problems in industrial equipment |
-
2019
- 2019-12-23 CN CN201911342605.8A patent/CN111472754B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111472754A (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111472754B (en) | Fault processing method and device for oil pumping well, storage medium and electronic equipment | |
| CN108197132B (en) | Graph database-based electric power asset portrait construction method and device | |
| US10019516B2 (en) | System and method for fuzzy ontology matching and search across ontologies | |
| EP3916584A1 (en) | Information processing method and apparatus, electronic device and storage medium | |
| CN103678277A (en) | Theme-vocabulary distribution establishing method and system based on document segmenting | |
| CN110019842A (en) | A kind of method and device for establishing knowledge mapping | |
| CN111538794A (en) | Data fusion method, device and equipment | |
| CN114579584B (en) | Data table processing method and device, computer equipment and storage medium | |
| US20220121823A1 (en) | System and method for artificial intelligence driven document analysis, including searching, indexing, comparing or associating datasets based on learned representations | |
| CN113360676A (en) | Method and device for determining potential relation of enterprise based on knowledge graph | |
| CN112800197A (en) | Method and device for determining target fault information | |
| CN111435410A (en) | Relationship extraction method and device for medical texts | |
| CN111768096A (en) | Rating method and device based on algorithm model, electronic equipment and storage medium | |
| CN111475604A (en) | Data processing method and device | |
| CN113767403B (en) | Automatic resolution of over-and under-designations in knowledge graphs | |
| CN112883192A (en) | Heterogeneous field user and resource association mining method and system | |
| CN107562703B (en) | Dictionary tree reconstruction method and system | |
| CN111767406B (en) | Knowledge representation method and device for PLC engineering | |
| CN111125087A (en) | Data storage method and device | |
| CN113705201B (en) | Text-based event probability prediction evaluation algorithm, electronic device and storage medium | |
| CN113868254B (en) | Method, device and storage medium for removing duplication of entity node in graph database | |
| CN115186738A (en) | Model training method, device and storage medium | |
| CN114817223A (en) | Service data extraction method and device, electronic equipment and storage medium | |
| JP2016091529A (en) | Hybrid rule reasoning apparatus and method thereof | |
| CN114780021B (en) | Copy repairing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |