A fault diagnosis and early warning method and system for oil pump units

Abstract

This invention discloses a fault diagnosis and early warning method and system for oil pump units, relating to the field of pipeline oil transportation equipment diagnosis technology. The method includes: collecting operating status parameter data of the oil pump unit from the SCADA system and extracting normal state characteristics of the oil pump unit; constructing an early warning model for the oil pump unit; obtaining early warning information for abnormal state parameters, wherein the abnormal state parameter early warning information includes abnormal state parameters and abnormal state parameter monitoring values; constructing an abnormal fault database for the oil pump unit and obtaining fault evaluation information; and obtaining status early warning information for the oil pump unit based on the fault evaluation information. This invention solves the technical problem in the prior art where insensitivity to changes in unit status leads to insufficient timeliness and accuracy of early warnings, thereby improving the accuracy of abnormal judgment of oil pump units and enhancing the timeliness and accuracy of oil pump fault identification.

Description

Technical Field

[0001] This invention relates to the field of diagnostic technology for pipeline oil transportation equipment, and in particular to a fault diagnosis and early warning method and system for oil pump units. Background Technology

[0002] As a key piece of equipment in pipeline oil transportation, the oil pump is crucial for ensuring the normal operation of the pipeline. Currently, oil pump diagnostic technology mainly faces the following three problems:

[0003] (1) Currently, 80% of the status monitoring of oil pump units relies on SCADA system early warning, and only two fixed alarm thresholds (high alarm and high-high alarm) are set. This early warning mechanism does not pay attention to the process of unit operation status change and individual performance, resulting in insensitivity to changes in monitoring parameters.

[0004] (2) The design of fixed threshold alarm values ​​based on the manufacturer's experience and the equipment's tolerance limit (without a unified standard reference) results in the alarm being set too high, causing the unit to alarm too late and often being on the verge of shutdown.

[0005] (3) SCADA early warning only has simple over-value alarms, while the condition monitoring system based on the addition of high-frequency vibration sensors has little fault data accumulation, and fault diagnosis usually requires manual judgment based on experience, resulting in a low level of intelligence.

[0006] Existing oil pump diagnostic technologies suffer from a lack of sensitivity to changes in unit status, resulting in insufficient timeliness and accuracy of early warnings. Summary of the Invention

[0007] The purpose of this application is to provide a fault diagnosis and early warning method and system for oil pump units, in order to address the technical problem that existing oil pump diagnosis technologies are not sensitive to changes in the unit's state, resulting in insufficient timeliness and accuracy of early warnings.

[0008] In view of the above problems, this application provides a fault diagnosis and early warning method and system for oil pump units.

[0009] In a first aspect, this application provides a fault diagnosis and early warning method for an oil pump unit. The method includes: collecting operating status parameter data of the oil pump unit from a SCADA system and extracting normal state characteristics of the oil pump unit; constructing an early warning model for the oil pump unit based on the normal state characteristics; reading monitoring data of the oil pump unit in real time through the SCADA system, inputting the data into the early warning model to obtain abnormal state parameter early warning information, wherein the abnormal state parameter early warning information includes abnormal state parameters and abnormal state parameter monitoring values; constructing an abnormal fault database for the oil pump unit; using the abnormal state parameters and abnormal state parameter monitoring values, performing fault assessment and fault tracing with the abnormal fault database to obtain fault evaluation information; and obtaining status early warning information for the oil pump unit based on the fault evaluation information.

[0010] Secondly, this application also provides a fault diagnosis and early warning system for an oil pump unit, used to execute a fault diagnosis and early warning method for an oil pump unit as described in the first aspect, wherein the system includes: a normal state feature extraction module, which is used to collect operating status parameter data of the oil pump unit in the SCADA system and extract normal state features of the oil pump unit; a unit early warning model construction module, which is used to construct an early warning model of the oil pump unit based on the normal state features of the oil pump unit; and an abnormal early warning information acquisition module, which is used to obtain abnormal early warning information through the SCADA system. The system reads monitoring data from the oil pump unit in real time, inputs it into the oil pump unit early warning model, and obtains early warning information for abnormal state parameters. This information includes abnormal state parameters and their monitoring values. A fault evaluation information acquisition module is used to construct an abnormal fault database for the oil pump unit. Using the abnormal state parameters and their monitoring values, the system performs fault assessment and source tracing against the database to obtain fault evaluation information. A unit status early warning information acquisition module is used to obtain early warning information for the oil pump unit status based on the fault evaluation information.

[0011] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0012] The technical solution provided in this application collects operating status parameter data of the oil pump unit in the SCADA system and extracts the normal state characteristics of the oil pump unit; based on the normal state characteristics of the oil pump unit, an early warning model of the oil pump unit is constructed; the monitoring data of the oil pump unit is read in real time through the SCADA system and input into the early warning model of the oil pump unit to obtain early warning information of abnormal state parameters, wherein the early warning information of abnormal state parameters includes abnormal state parameters and abnormal state parameter monitoring values; an abnormal fault database of the oil pump unit is constructed, and the abnormal state parameters and abnormal state parameter monitoring values ​​are used to perform fault assessment and fault tracing with the abnormal fault database of the oil pump unit to obtain fault evaluation information; based on the fault evaluation information, the status early warning information of the oil pump unit is obtained. This application, based on a SCADA system, extracts the normal state characteristics of oil pump units, constructs an early warning model for oil pump units based on these characteristics, and then provides early warnings of anomalies in the oil pump units. It accurately assesses the severity of anomalies in the oil pump units and traces the source of these anomalies, thereby improving the accuracy of anomaly detection and enhancing the timeliness and accuracy of oil pump fault identification.

[0013] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0015] Figure 1 A flowchart illustrating a fault diagnosis and early warning method for an oil pump unit provided in this application embodiment;

[0016] Figure 2 A flowchart illustrating the extraction of state features of an oil pump unit in a fault diagnosis and early warning method provided in this application embodiment;

[0017] Figure 3 A flowchart illustrating the process of constructing an abnormal fault database for an oil pump unit in a fault diagnosis and early warning method for an oil pump unit provided in this application embodiment;

[0018] Figure 4 A schematic diagram of a fault diagnosis and early warning system for an oil pump unit provided in this application embodiment;

[0019] Figure 5 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0020] Figure labeling: Normal state feature extraction module 11, unit early warning model construction module 12, abnormal early warning information acquisition module 13, fault evaluation information acquisition module 14, unit status early warning information acquisition module 15, electronic equipment 300, memory 301, processor 302, communication interface 303, bus architecture 304. Detailed Implementation

[0021] This application provides a fault diagnosis and early warning method and system for oil pump units, which addresses the technical problem in existing oil pump diagnosis technologies that are not sensitive to changes in unit status, resulting in insufficient timeliness and accuracy of early warnings.

[0022] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0024] Example 1

[0025] like Figure 1 As shown, this application provides a fault diagnosis and early warning method for an oil pump unit, the method comprising:

[0026] Step S100: Collect the operating status parameter data of the oil pump unit in the SCADA system and extract the normal state characteristics of the oil pump unit;

[0027] Specifically, SCADA systems are industrial process monitoring systems that can monitor the operation of oil pump units. Based on the industrial process monitoring system, they collect operating status parameter data of the oil pump units. These operating status parameter data refer to the data generated during the operation of the oil pump units. The operating status parameter data of the oil pump units is analyzed and processed to extract the normal state characteristics of the oil pump units. These normal state characteristics refer to the features that can reflect the operating status of the oil pump units.

[0028] Among them, such as Figure 2As shown, step S100 in the method provided in this application embodiment includes:

[0029] Step S110: Clean and normalize the collected oil pump unit operating status parameter data to obtain preprocessed operating status parameter data;

[0030] Step S120: Based on the preprocessed operating status parameter data, construct multi-dimensional parameters of the unit status;

[0031] Step S130: Perform correlation analysis on the multidimensional parameters of the unit status, and compress the multidimensional parameters of the unit status based on the correlation analysis results;

[0032] Step S140: Based on the compressed multidimensional parameters of the unit status, extract the state characteristics of the oil pump unit that reflect the long-term and short-term historical states of the oil pump unit.

[0033] Specifically, the operating status parameter data of the oil pump unit includes vibration signals, temperature signals, flow signals, motor voltage signals, motor current signals, pressure, and mechanical seal leakage data. Examples include horizontal and vertical vibration values ​​and bearing temperatures at the pump drive end and non-drive end, as well as voltage, current, pump anomaly data, and pressure and flow signals at the pump inlet and outlet. The collected operating status parameter data of the oil pump unit is cleaned and normalized. Data cleaning involves checking for missing or redundant data, supplementing missing data, and deleting redundant data. Since different data have different dimensions, the data is normalized to convert them into dimensionless pure numerical values, thus obtaining pre-processed operating status parameter data. The preprocessed operational status parameter data contains various operational parameters. These parameters are categorized, and a multi-dimensional parameter system for the unit's status is constructed from the categorized data. This system includes multiple sets of operational status parameter data of different types. Further correlation analysis is performed on these multi-dimensional parameters, indicating that they are correlated; for example, a change in one dimension's parameter will cause a change in another dimension's parameter. Based on the correlation analysis results, the multi-dimensional parameters are compressed, grouping highly correlated parameters together to reduce the data volume. Based on the compressed multi-dimensional parameters, outlier data is removed, and the operational status characteristics of the oil pump unit, reflecting its long-term and short-term historical states, are extracted.

[0034] Step S140 in the method provided in this application embodiment includes:

[0035] Step S141: Obtain preset long and short term information;

[0036] Step S142: Analyze the abnormal state data volume based on the preset long-term and short-term information to determine the long-term and short-term weights;

[0037] Step S143: Based on the long-term and short-term weights, extract the state features of the oil pump unit that reflect the long-term and short-term historical states of the oil pump unit.

[0038] Specifically, preset long-term and short-term information is obtained. This preset long-term and short-term information refers to the time constraint information of the transition characteristics, which can be set according to the actual situation, such as one month, three months, six months, or one year. Abnormal state data volume analysis is performed based on the preset long-term and short-term information, which involves analyzing the quantity of abnormal state data within the preset long-term and short-term timeframes. Based on this, long-term and short-term weights are set; for example, data more recently in operation can be given a higher weight. Abnormal data is then removed, and based on the long-term and short-term weights, the state characteristics of the oil pump unit reflecting its long-term and short-term historical states are extracted.

[0039] Step S200: Based on the normal state characteristics of the oil pump unit, construct an early warning model for the oil pump unit;

[0040] Step S200 in the method provided in this application embodiment includes:

[0041] Step S210: Build a model using one or more of the following analytical methods: cluster analysis, long and short time memory, neural networks, regression modeling, and outlier detection.

[0042] Specifically, based on the normal state characteristics of the oil pump unit, an early warning model for the oil pump unit is constructed. Generally, early warning models often use abnormal data for modeling, issuing warnings by monitoring abnormal data. However, abnormal state parameters are diverse, and the abnormal state database cannot completely exhaust all abnormal states. Such models lack accuracy and timeliness in their early warnings, often issuing warnings only after the abnormal data has been running for a period of time. This invention uses normal data for modeling. An early warning is issued whenever the unit's operating data differs from the normal state characteristics of the oil pump unit. Based on this, an early warning model for the oil pump unit is constructed. That is, the early warning model includes the normal state characteristics of the oil pump unit. The monitored operating data of the oil pump unit is input into the early warning model, which compares the monitored operating data with the normal state characteristics. If they are inconsistent, an early warning is issued, achieving the technical effect of improving the accuracy and timeliness of early warnings.

[0043] Specifically, the model is constructed using one or more of the following analytical methods: cluster analysis, long short-term memory (LSTM), neural networks, regression modeling, and outlier detection. Cluster analysis involves dividing the modeling data into multiple groups of different types according to defined classification criteria, and then analyzing and modeling based on these different data types. LSTM is a type of recurrent neural network, and like neural networks, it's a machine learning algorithm that mimics the behavioral characteristics of animal neural networks to perform distributed parallel information processing. Regression modeling is a mathematical model that quantitatively describes statistical relationships. Outlier detection is the process of identifying objects whose behavior differs from expected data; these objects are called outliers or anomalies. In other words, normal data is often similar, while anomalous data usually appears singly and is distinct from other normal data. The model is constructed by selecting one or more of these analytical methods: cluster analysis, LSTM, neural networks, regression modeling, and outlier detection.

[0044] Step S300: Read the monitoring data of the oil pump unit in real time through the SCADA system, input the early warning model of the oil pump unit, and obtain the early warning information of abnormal state parameters, wherein the early warning information of abnormal state parameters includes abnormal state parameters and abnormal state parameter monitoring values;

[0045] Specifically, the SCADA system reads the monitoring data of the oil pump unit in real time, inputs the monitoring data into the early warning model of the oil pump unit, and outputs early warning information for abnormal state parameters. The early warning information for abnormal state parameters refers to the monitoring data of the oil pump unit that is different from the normal state characteristics of the oil pump unit. The early warning information for abnormal state parameters includes abnormal state parameters and abnormal state parameter monitoring values. Abnormal state parameters refer to the type of parameters, such as voltage and current, while abnormal state parameter monitoring values ​​refer to the characteristic values ​​of the parameters, such as abnormal voltage values.

[0046] Step S400: Construct an abnormal fault database for the oil pump unit, and use the abnormal state parameters and abnormal state parameter monitoring values ​​to perform fault assessment and fault tracing with the abnormal fault database for the oil pump unit to obtain fault evaluation information;

[0047] This includes building a database of abnormal faults for oil pump units, such as... Figure 3 As shown, step S400 in the method provided in this application embodiment further includes:

[0048] Step S410: Record the time of the fault occurrence in the SCADA system and establish a fault tag;

[0049] Step S420: Analyze the operating status parameter data of the oil pump unit in the monitoring data of the SCADA system at the corresponding time.

[0050] Step S430: Based on the fault information and the operating status parameter data of the oil pump unit, construct a relational rule database for the abnormal status level, the operating status parameter data of the oil pump unit, and the faulty equipment information. The relational rule database includes fault tags, unit number, traceability information, abnormal status level, operating status parameter data of the oil pump unit, and their mapping relationships.

[0051] Specifically, by utilizing the abnormal state parameters and their monitoring values, and comparing them with the abnormal fault database of the oil pump unit to perform fault assessment and fault tracing to obtain fault evaluation information, step S400 of the method provided in this application embodiment further includes:

[0052] Step S450: Based on the abnormal state parameters and the abnormal fault database of the oil pump unit, perform fault tracing to determine the tracing information;

[0053] Step S460: Based on the source tracing information, use the abnormal fault database of the oil pump unit to determine the fault tag, locate the fault occurrence time according to the fault tag, and obtain the source tracing result;

[0054] Step S470: Match the abnormal status level with the abnormal fault database of the oil pump unit based on the abnormal status parameter monitoring value;

[0055] Step S480: Obtain the fault evaluation information based on the abnormal state level and the source tracing result.

[0056] Specifically, the abnormal fault database of the oil pump unit includes the operating status parameter data of the oil pump unit at the time of the fault, the corresponding abnormal level, and the faulty equipment information. Further, based on the abnormal status parameters and the monitoring values ​​of the abnormal status parameters, combined with the abnormal fault database of the oil pump unit, fault assessment and fault tracing are carried out to obtain fault evaluation information. Fault assessment is to evaluate the abnormal level, and fault tracing is to determine the location of the abnormality in the unit, such as motor abnormality, bearing abnormality, etc. The fault assessment results and fault tracing results constitute the fault evaluation information.

[0057] Specifically, the process of constructing the abnormal fault database of the oil pump unit is as follows: Based on the SCADA system, the time of each fault occurrence is recorded and a fault label is established. The fault label marks the time of each fault occurrence and the fault information. The operating status parameter data of the oil pump unit in the monitoring data of the SCADA system corresponding to the time of the fault occurrence is analyzed. In other words, the operating status parameter data of the oil pump unit at this time is abnormal data. Further, based on fault information and oil pump unit operating status parameter data, a database of association rules is constructed for abnormal state levels, oil pump unit operating status parameter data, and faulty equipment information. Simply put, faulty equipment information refers to the unit equipment that has malfunctioned. Different oil pump unit operating status parameter data and faulty equipment information correspond to different abnormal state levels, including mild, moderate, and severe abnormalities. The association rule database includes fault tags, unit numbers, traceability information, abnormal state levels, oil pump unit operating status parameter data, and their mapping relationships. The unit number is a unique identifier for the oil pump unit; that is, a station may have multiple oil pump units, and each unit is assigned a different number to facilitate fault warnings for different units. Traceability information refers to the abnormal state parameters. In other words, the association rule database includes multiple sets of data, each containing a fault tag, unit number, traceability information, abnormal state level, and oil pump unit operating status parameter data, with each set having a corresponding relationship.

[0058] Furthermore, after the abnormal fault database of the oil pump unit is constructed, fault tracing is performed based on the abnormal state parameters and the database. In other words, the abnormal state parameters of the unit are determined, and these parameters are used as tracing information. Based on this information, fault tags are identified using the database, and the fault occurrence time is located using these tags to obtain the tracing results. These results include the time and location of the abnormality. The abnormal state parameter monitoring values ​​are then matched with the database to determine the abnormal state level. Normal state levels include mild, moderate, and severe abnormalities. The abnormal state level and the tracing results are used as fault evaluation information.

[0059] Step S500: Obtain the status warning information of the oil pump unit based on the fault evaluation information.

[0060] Specifically, based on the fault evaluation information, the status warning information of the oil pump unit is obtained. The status warning information of the oil pump unit includes the abnormal status level and the source tracing results. The status warning information of the oil pump unit is sent to the staff to assist them in carrying out equipment inspection and maintenance.

[0061] Step S600 in the method provided in this application embodiment includes:

[0062] Step S610: Read the operating status parameter data in real time through the SCADA system's pi database;

[0063] Step S620: Process the real-time read operating status parameter data according to the normal state characteristics of the oil pump unit to obtain model update data;

[0064] Step S630: Dynamically update the early warning model of the oil pump unit using the model update data.

[0065] Specifically, the SCADA system is used to monitor the operation of the oil pump unit in real time, and it continuously generates operating status parameter data. The operating status parameter data is read in real time through the SCADA system's PI database, and processed in the same way as in step S100 to extract the normal state characteristics of the oil pump unit. This data is then used as model update data to dynamically update the early warning model of the oil pump unit, thereby optimizing the early warning model and improving the accuracy and sensitivity of abnormal early warnings.

[0066] In summary, the fault diagnosis and early warning method for oil pump units provided in this application has the following technical effects:

[0067] This application proposes a fault diagnosis and early warning method for oil pump units. Based on a SCADA system, it extracts the normal state characteristics of the oil pump unit, constructs an early warning model for the oil pump unit based on these characteristics, and then provides early warnings for abnormalities. It accurately assesses the severity of abnormalities and traces the source of these abnormalities, thereby improving the accuracy of abnormality judgment and enhancing the timeliness and accuracy of fault identification in oil pump units.

[0068] Example 2

[0069] Based on the same inventive concept as the fault diagnosis and early warning method for an oil pump unit in the foregoing embodiments, such as Figure 4 As shown, this application also provides a fault diagnosis and early warning system for an oil pump unit, the system comprising:

[0070] Normal state feature extraction module 11 is used to collect operating status parameter data of oil pump unit in SCADA system and extract normal state features of oil pump unit.

[0071] The unit early warning model construction module 12 is used to construct an early warning model for the oil pumping unit based on the normal state characteristics of the oil pumping unit.

[0072] An abnormal warning information acquisition module 13 is used to read the monitoring data of the oil pump unit in real time through the SCADA system, input the oil pump unit warning model, and obtain abnormal state parameter warning information, wherein the abnormal state parameter warning information includes abnormal state parameters and abnormal state parameter monitoring values.

[0073] The fault evaluation information acquisition module 14 is used to construct an abnormal fault database of the oil pump unit, and to use the abnormal state parameters and abnormal state parameter monitoring values ​​to perform fault assessment and fault tracing with the abnormal fault database of the oil pump unit to obtain fault evaluation information.

[0074] Unit status early warning information acquisition module 15, the unit status early warning information acquisition module 15 is used to obtain oil pump unit status early warning information based on the fault evaluation information.

[0075] Furthermore, the system also includes:

[0076] The data cleaning and processing module is used to clean and normalize the collected operating status parameter data of the oil pump unit to obtain pre-processed operating status parameter data.

[0077] A multi-dimensional parameter construction module for unit status is used to construct multi-dimensional parameters for unit status based on the preprocessed operating status parameter data.

[0078] A correlation analysis module is used to perform correlation analysis on the multidimensional parameters of the unit's state, and to compress the multidimensional parameters of the unit's state based on the correlation analysis results.

[0079] The unit status feature extraction module is used to extract the oil pump unit status features that reflect the long-term and short-term historical status of the oil pump unit based on the compressed multi-dimensional parameters of the unit status.

[0080] Furthermore, the system also includes:

[0081] A preset long-term and short-term information acquisition module is used to acquire preset long-term and short-term information.

[0082] A long-term and short-term weight determination module is used to analyze the abnormal state data volume based on the preset long-term and short-term information and determine the long-term and short-term weights.

[0083] The second unit state feature extraction module is used to extract the state features of the oil pump unit based on the long-term and short-term weights, representing the historical long-term and short-term states of the reaction oil pump unit.

[0084] Furthermore, the system also includes:

[0085] A fault tag establishment module is used to record the time of fault occurrence in the SCADA system and establish fault tags.

[0086] The status parameter analysis module is used to analyze the operating status parameter data of the oil pump unit in the monitoring data of the SCADA system at the corresponding time.

[0087] The association rule database construction module is used to construct an association rule database of abnormal status level, oil pump unit operating status parameter data and fault equipment information based on fault information and oil pump unit operating status parameter data. The association rule database includes fault tags, unit number, traceability information, abnormal status level, oil pump unit operating status parameter data and their mapping relationship.

[0088] Furthermore, the system also includes:

[0089] The fault tracing module is used to trace the fault based on the abnormal state parameters and the abnormal fault database of the oil pump unit to determine the tracing information.

[0090] The fault occurrence time location module is used to determine fault tags based on the source tracing information and the abnormal fault database of the oil pump unit, and to locate the fault occurrence time according to the fault tags to obtain the source tracing results.

[0091] The abnormal state level determination module is used to match the abnormal state parameter monitoring value with the abnormal fault database of the oil pump unit to determine the abnormal state level.

[0092] The second fault evaluation information acquisition module is used to obtain the fault evaluation information based on the abnormal state level and the source tracing result.

[0093] Furthermore, the system also includes:

[0094] A real-time running data acquisition module is used to read running status parameter data in real time through the SCADA system's pi database.

[0095] The model update data acquisition module is used to process the real-time read operating status parameter data according to the normal state characteristics of the oil pump unit to obtain model update data.

[0096] A dynamic update module is used to dynamically update the early warning model of the oil pump unit using the model update data.

[0097] Furthermore, the system also includes:

[0098] The model building module is used to build a model using one or more of the following analytical methods: cluster analysis, long and short time memory, neural networks, regression modeling, and outlier detection.

[0099] Example 3

[0100] Based on the same inventive concept as the fault diagnosis and early warning method for an oil pump unit in the foregoing embodiments, such as Figure 5 As shown, this application also provides an electronic device 300, which includes a memory 301 and a processor 302. The memory 301 stores a computer program, and when the calculator program is executed by the processor 302, it implements the steps of a method of the embodiment.

[0101] The electronic device 300 includes a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, processor 302, and memory 301 can be interconnected via the bus architecture 304; the bus architecture 304 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus architecture 304 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0102] Processor 302 may be a CPU, microprocessor, ASIC, or one or more integrated circuits used to control the execution of programs according to the present application.

[0103] Communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0104] Memory 301 may be ROM or other types of static storage devices capable of storing static information and instructions, RAM or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory may exist independently and be connected to the processor via bus architecture 304. Memory may also be integrated with the processor.

[0105] The memory 301 stores computer execution instructions for implementing the scheme of this application, and its execution is controlled by the processor 302. The processor 302 executes the computer execution instructions stored in the memory 301, thereby implementing the steps of the method in the above embodiment one of this application.

[0106] Example 4

[0107] Based on the same inventive concept as the fault diagnosis and early warning method for an oil pump unit in the foregoing embodiments, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method in Embodiment 1.

[0108] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The fault diagnosis and early warning method and specific examples of an oil pump unit in Embodiment 1 are also applicable to the fault diagnosis and early warning system of an oil pump unit in this embodiment. Through the foregoing detailed description of the fault diagnosis and early warning method for an oil pump unit, those skilled in the art can clearly understand the fault diagnosis and early warning system of an oil pump unit in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0109] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fault diagnosis and early warning method for an oil pump unit, characterized in that, The method includes: Collect operating status parameter data of oil pump units in the SCADA system and extract normal state characteristics of oil pump units; Based on the normal state characteristics of the oil pump unit, an early warning model for the oil pump unit is constructed. The SCADA system reads the monitoring data of the oil pump unit in real time, inputs it into the early warning model of the oil pump unit, and obtains early warning information of abnormal state parameters. The early warning information of abnormal state parameters includes abnormal state parameters and abnormal state parameter monitoring values. A fault database for oil pump units is constructed. The abnormal state parameters and their monitoring values ​​are used to perform fault assessment and fault tracing with the fault database for oil pump units to obtain fault evaluation information. Based on the fault evaluation information, early warning information on the status of the oil pump unit is obtained; The process of collecting operating status parameter data of the oil pump unit in the SCADA system and extracting normal state characteristics of the oil pump unit includes: The collected operating status parameter data of the oil pump unit is cleaned and normalized to obtain pre-processed operating status parameter data; Based on the preprocessed operating status parameter data, a multi-dimensional parameter of the unit status is constructed. A correlation analysis was performed on the multidimensional parameters of the unit's status, and the multidimensional parameters of the unit's status were compressed based on the correlation analysis results. Based on the compressed multidimensional parameters of the unit status, the state characteristics of the oil pump unit that reflect the long-term and short-term historical states of the oil pump unit are extracted. The extracted oil pump unit's long- and short-term historical state characteristics include: Obtain preset short-term and long-term information; Based on the preset long-term and short-term information, analyze the amount of abnormal state data to determine the long-term and short-term weights; Based on the aforementioned long-term and short-term weights, the state characteristics of the oil pump unit are extracted from the long-term and short-term historical states of the reaction oil pump unit.

2. The method as described in claim 1, characterized in that, The construction of the abnormal fault database for oil pump units includes: Record the time of the fault occurrence in the SCADA system and establish a fault label; Analyze the operating status parameter data of the oil pump unit in the monitoring data of the SCADA system at the corresponding time. Based on the fault information and the operating status parameter data of the oil pump unit, a database of association rules is constructed for the abnormal status level, the operating status parameter data of the oil pump unit, and the fault equipment information. The database of association rules includes fault tags, unit number, traceability information, abnormal status level, operating status parameter data of the oil pump unit, and their mapping relationships.

3. The method as described in claim 2, characterized in that, Using the aforementioned abnormal state parameters and their monitoring values, fault assessment and source tracing are performed against the fault database of the oil pump unit to obtain fault evaluation information, including: Based on the abnormal state parameters and the abnormal fault database of the oil pump unit, fault tracing is performed to determine the tracing information; Based on the source tracing information, the fault label is determined using the abnormal fault database of the oil pump unit, and the fault occurrence time is located according to the fault label to obtain the source tracing result; The abnormal state level is determined by matching the abnormal state parameter monitoring values ​​with the abnormal fault database of the oil pump unit. Based on the abnormal state level and the source tracing results, the fault evaluation information is obtained.

4. The method as described in claim 1, characterized in that, The method further includes: Real-time reading of operational status parameter data is achieved through the SCADA system's pi database. The real-time read operating status parameter data is processed according to the normal state characteristics of the oil pump unit to obtain model update data; The early warning model of the oil pump unit is dynamically updated using the model update data.

5. The method as described in claim 1, characterized in that, The construction of the early warning model for the oil pumping unit includes: The model is constructed using one or more of the following analytical methods: cluster analysis, long and short time memory, neural networks, regression modeling, and outlier detection.

6. A fault diagnosis and early warning system for an oil pump unit, characterized in that, The system includes: A normal state feature extraction module is used to collect operating status parameter data of oil pump units in the SCADA system and extract normal state features of the oil pump units. The unit early warning model construction module is used to construct an early warning model for the oil pumping unit based on the normal state characteristics of the oil pumping unit. An abnormality warning information acquisition module is used to read the monitoring data of the oil pump unit in real time through the SCADA system, input the oil pump unit warning model, and obtain abnormality status parameter warning information, wherein the abnormality status parameter warning information includes abnormality status parameters and abnormality status parameter monitoring values. The fault evaluation information acquisition module is used to construct an abnormal fault database of the oil pump unit, and to use the abnormal state parameters and abnormal state parameter monitoring values ​​to perform fault assessment and fault tracing with the abnormal fault database of the oil pump unit to obtain fault evaluation information. A unit status early warning information acquisition module is used to obtain oil pump unit status early warning information based on the fault evaluation information. The process of collecting operating status parameter data of the oil pump unit in the SCADA system and extracting normal state characteristics of the oil pump unit includes: The collected operating status parameter data of the oil pump unit is cleaned and normalized to obtain preprocessed operating status parameter data; Based on the preprocessed operating status parameter data, a multi-dimensional parameter of the unit status is constructed. A correlation analysis was performed on the multidimensional parameters of the unit's status, and the multidimensional parameters of the unit's status were compressed based on the correlation analysis results. Based on the compressed multidimensional parameters of the unit status, the state characteristics of the oil pump unit that reflect the long-term and short-term historical states of the oil pump unit are extracted. The extracted oil pump unit's long- and short-term historical state characteristics include: Obtain preset short-term and long-term information; Based on the preset long-term and short-term information, analyze the amount of abnormal state data to determine the long-term and short-term weights; Based on the aforementioned long-term and short-term weights, the state characteristics of the oil pump unit are extracted from the long-term and short-term historical states of the reaction oil pump unit.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the steps of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of any one of claims 1-5.

Images