CN112393931B - Detection method, detection device, electronic equipment and computer readable medium - Google Patents
Detection method, detection device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN112393931B CN112393931B CN201910746127.0A CN201910746127A CN112393931B CN 112393931 B CN112393931 B CN 112393931B CN 201910746127 A CN201910746127 A CN 201910746127A CN 112393931 B CN112393931 B CN 112393931B
- Authority
- CN
- China
- Prior art keywords
- health degree
- historical
- oilfield
- operation data
- detection
- 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
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Abstract
The embodiment of the application discloses a detection method, a detection device, electronic equipment and a computer readable medium. An embodiment of the method comprises: acquiring operation data to be detected of the oilfield mobile equipment during production or self-inspection; inputting the operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield mobile equipment, wherein the health degree detection model is a health degree detection model for detecting the health degree of the oilfield mobile equipment, which is obtained by training the historical operation data and the historical detection data of the oilfield mobile equipment as training samples by using a machine learning method. The implementation method can improve the accuracy of the health degree detection of the oilfield dynamic equipment and provide powerful technical support for predictive maintenance.
Description
Technical Field
The embodiment of the application relates to the field of data processing, in particular to a detection method, a detection device, electronic equipment and a computer readable medium.
Background
Various oilfield tools are typically used during the production of the oil well. The oilfield driving equipment refers to rotating equipment (namely equipment with energy consumption) which is suitable for an oilfield and is driven by a driving machine, such as a pump, a compressor, a fan and the like. The energy source may be electric power, pneumatic power, steam power, etc.
At present, the fault diagnosis of the oil field power equipment generally judges the health degree of the oil field power equipment manually according to the fluctuation condition of a sensor signal, and then performs predictive maintenance on the oil field power equipment. The health degree is determined according to the experience of people, and the experience cannot be quantized, so the accuracy of the health degree detection of the oilfield operation equipment is low, and the predictive maintenance of the oilfield operation equipment cannot be accurately performed.
Disclosure of Invention
The embodiment of the application provides a detection method, a detection device, electronic equipment and a computer readable medium, and aims to solve the technical problem that in the prior art, the accuracy of health degree detection of oilfield moving equipment is low.
In a first aspect, an embodiment of the present application provides a detection method, where the method includes: acquiring operation data to be detected of the oilfield mobile equipment during production or self-inspection; inputting the operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield mobile equipment, wherein the health degree detection model is a health degree detection model for detecting the health degree of the oilfield mobile equipment, which is obtained by training the historical operation data and the historical detection data of the oilfield mobile equipment as training samples by using a machine learning method.
In a second aspect, an embodiment of the present application provides a detection apparatus, including: the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is configured to acquire operation data to be detected of the oilfield equipment during production or self-inspection; the detection unit is configured to input operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield mobile equipment, wherein the health degree detection model is the health degree detection model which is obtained by taking historical operation data and historical detection data of the oilfield mobile equipment as training samples and training the historical operation data and the historical detection data by using a machine learning method and is used for detecting the health degree of the oilfield mobile equipment.
In a third aspect, an embodiment of the present application provides an apparatus, including: one or more processors; storage means having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement a method as in any one of the embodiments of the first aspect described above.
In a fourth aspect, the present application provides a computer-readable medium, on which a computer program is stored, which when executed by a processor implements the method according to any one of the embodiments of the first aspect.
According to the detection method, the detection device, the electronic equipment and the computer readable medium, the health degree detection result of the oilfield movable equipment is obtained by acquiring the operation data to be detected of the oilfield movable equipment during production or self-inspection and then inputting the operation data to be detected into a health degree detection model which is constructed in advance. The health degree detection model is obtained by taking historical operation data and historical detection data of the oilfield moving equipment as training samples and training by using a machine learning method and is used for detecting the health degree of the oilfield moving equipment. Therefore, the health degree of the oil field power equipment is detected through the health degree detection model, the accuracy of the health degree detection of the oil field power equipment can be improved, and powerful technical support is provided for predictive maintenance.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is a flow diagram of one embodiment of a detection method according to the present application;
FIG. 2 is a flow chart of yet another embodiment of a detection method according to the present application;
FIG. 3 is a schematic structural diagram of one embodiment of a detection device according to the present application;
FIG. 4 is a block diagram of a computer system suitable for use in implementing the apparatus of an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, a flow 100 of one embodiment of a detection method according to the present application is shown. The detection method comprises the following steps:
In this embodiment, an execution subject of the detection method (e.g., a server, an intelligent model training platform for training a health detection model, etc.) may obtain operation data to be detected of the oilfield mobile equipment during production or self-test. The oilfield driving equipment is rotating equipment (namely equipment with energy consumption) which is suitable for the oilfield and driven by a driving machine, such as a pump, a compressor, a fan and the like. The energy source may be electric power, pneumatic power, steam power, etc.
Optionally, the oilfield power plant is provided with a plurality of sensors. The plurality of sensors may include, but are not limited to: temperature sensor, pressure sensor, ampere meter, voltmeter, sound signal collector etc.. The execution main body can periodically or in real time acquire the operation data to be detected of the oilfield equipment during production or self-inspection through the plurality of sensors.
Specifically, the execution main body may be configured such that each sensor in the oilfield equipment is communicatively connected to the execution main body via an RTU (Remote Terminal Control Unit), a DCS (Distributed Control System), a PLC (Programmable Logic Controller), or the like. At this time, the execution main body can acquire the operation data to be detected, which is acquired by each sensor, through the RTU, the DCS, or the PLC.
Optionally, the operation data to be detected may include, but is not limited to, at least one of the following: frequency spectrum, audio, current, voltage, flow, temperature, picture.
Optionally, the executing body may further store the acquired operation data to be detected in a database, so as to provide data support for subsequent fault analysis.
And 102, inputting the operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield moving equipment.
In this embodiment, the operation data to be detected is input into a pre-constructed health degree detection model, so as to obtain a health degree detection result of the oilfield equipment. The health degree detection model is obtained by taking historical operation data and historical detection data of the oilfield mobile equipment as training samples and training the training samples by using a machine learning method and is used for detecting the health degree of the oilfield mobile equipment.
Here, the historical operation data may be data generated by the oilfield equipment during historical operation or self-test. The historical operating data and the operating data to be detected may be the same in terms of specific items (such as frequency spectrum, audio frequency, voltage, current, temperature, etc.), and will not be described herein again.
Here, the history detection data may be data generated when the device is regularly inspected and when it is out of order. This data can be manually recorded by the inspector. For example, the historical inspection data may include a fault identification indicating whether the oilfield equipment has failed, a fault type, an alarm amount, a lifetime or a number of months of use of the oilfield equipment, and the like. In practice, the oilfield equipment may be tested at regular intervals (e.g., a day, a week, etc.) to determine if it is malfunctioning, and test data may be recorded for each test.
Here, the health degree detection result may include a value of the health degree. In practice, the health degree may be a value within a preset value range (e.g., [0,10 ]). The larger the value of the health degree is, the better the running condition of the oil field power plant is.
In this embodiment, the health detection model may be generated by training in advance. Before training the health detection model, the historical operating data may be labeled by using the acquired historical detection data. Therefore, the health degree detection model can be obtained by training with a machine learning method (such as a supervised learning method) by taking the historical operation data as input and the input historical operation data as output. In practice, the fitness detection model may be trained using a variety of commonly used models that process large data. Such as Convolutional Neural Networks (CNN) and the like.
Note that, various preset labeling rules may be used to label the historical operating data. As an example, after detecting the oilfield equipment in a certain time period, if the detection result indicates that the oilfield equipment has a fault, the historical operating data acquired in the time period may be marked as 1; if the detection result indicates that the oilfield equipment has not failed, the historical operating data acquired in the time period can be marked as 0.
It should be noted that, before training, data processing (such as numerical value conversion, feature extraction, and the like) may be performed on the collected operation data in advance to facilitate model training. In the process of training the health degree detection model, each historical operation data can be input one by one, or a plurality of historical operation data can be input in batches each time. After the training of the model is completed (for example, after preset training end conditions such as the number of times of training reaching a preset number of times, the accuracy of model prediction reaching a preset value, and the like are met), the trained model can be determined as the health degree detection model. Therefore, the health degree of the oil field power equipment can be detected in real time through the health degree detection model.
In some optional implementation manners of this embodiment, after obtaining the health degree detection result, the executing main body may further perform the following steps:
first, a target health level corresponding to the current health level indicated by the health level detection result is searched from a preset first corresponding relation table. The first corresponding relation table is used for representing the corresponding relation between the health grade and the health degree range. Wherein different health levels (e.g., class a, class B, class C) may correspond to different ranges of health. For example, the health degree range for the a-stage is (8, 10), the health degree range for the B-stage is (6, 8), and the health degree range for the C-stage is [0, 6 ].
And then, searching a target maintenance mode corresponding to the target health grade from a preset second corresponding relation table. The second corresponding relation table is used for representing the corresponding relation between the health level and the maintenance mode. For example, the maintenance mode corresponding to the level a is to record real-time operation data, the maintenance mode corresponding to the level B is to perform manual inspection, and the maintenance mode corresponding to the level C is to suspend the operation of the oilfield equipment and perform manual inspection.
And finally, maintaining the oilfield equipment by using the target maintenance mode. Therefore, in the process of detecting the health degree of the oilfield equipment in real time, the execution main body can select a maintenance mode based on the health grade corresponding to the detected health degree. And then, maintaining the oil field power equipment by using the selected maintenance mode. Because the maintenance mode is selected according to the health degree grade and is not determined according to the experience of maintenance personnel, the accuracy of predictive maintenance can be improved.
According to the method provided by the embodiment of the application, the health degree detection result of the oilfield mobile equipment is obtained by acquiring the operation data to be detected of the oilfield mobile equipment during production or self-inspection and inputting the operation data to be detected into the pre-constructed health degree detection model. The health degree detection model is obtained by taking historical operation data and historical detection data of the oilfield moving equipment as training samples and training by using a machine learning method and is used for detecting the health degree of the oilfield moving equipment. Therefore, the health degree of the oil field power equipment is detected through the health degree detection model, the accuracy of the health degree detection of the oil field power equipment can be improved, and powerful technical support is provided for predictive maintenance.
With further reference to fig. 2, a flow 200 of yet another embodiment of a detection method is shown. The process 200 of the detection method comprises the following steps:
In this embodiment, the oilfield equipment may be equipped with a plurality of sensors. The execution main body can periodically or real-timely acquire the operation data to be detected of the oilfield equipment during production or self-inspection through the plurality of sensors. The operation data may include, but is not limited to: frequency spectrum, audio, current, voltage, flow, temperature, picture.
In this embodiment, the execution main body inputs the to-be-detected operation data into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield operation equipment. The health degree detection model can be obtained by training through the following steps:
the method comprises the following steps of firstly, obtaining historical operation data and historical detection data of the oilfield equipment.
And secondly, setting the historical health degree of the oil field power equipment based on the historical detection data. Here, the historical health degree may be a numerical value located in a preset numerical interval (e.g., [0,10 ]). The larger the value of the health degree is, the better the running condition of the oil field power plant is.
Here, the historical health degree corresponding to each historical detection data may be calculated using various preset rules. As an example, historical health may be determined in conjunction with fault identification, fault type, and alarm amount in the historical detection data. See in particular the following table:
as shown in the table, if the fault mark is 1, it indicates that the oilfield equipment has a fault; and if the fault mark is 0, the oil field power equipment is not in fault. Taking the second column in the table as an example, when the oilfield equipment has a fault, the fault type is a fault with fracture, and the alarm amount is in the third gear, the historical health degree may be set to 0.
The rule for setting the historical health degree corresponding to each piece of historical test data may be set as needed, and is not limited herein.
And thirdly, establishing a corresponding relation between each historical operation data and the historical health degree. As an example, if the device is inspected once every inspection period (for example, 24 hours), the historical health degree corresponding to the historical inspection data recorded after each inspection can be obtained. Furthermore, a corresponding relation can be established between the historical operation data acquired in each routing inspection period and the historical health degree corresponding to the historical period.
And fourthly, taking each historical operating data as the input of a pre-established initial model, taking the historical health degree corresponding to the input historical operating data as the output of the initial model, and training by using a machine learning method to obtain a health degree detection model for detecting the health degree of the oilfield mobile equipment.
In this embodiment, when the oilfield equipment fails, the execution main body may acquire operation data of the oilfield equipment during the failure, and acquire detection data of the oilfield equipment after the failure. In practice, the execution main body may further store the operation data in a database, so as to provide data support for subsequent fault analysis.
And 204, taking the operation data and the detection data as training samples, and training the health degree detection model by using a machine learning method so as to update the health degree detection model.
In this embodiment, the executing entity may train the health degree detection model by using a machine learning method using the operation data and the detection data as training samples to update the health degree detection model.
In some optional implementations of this embodiment, the model may be updated as follows:
first, a target health degree of the oilfield equipment during the fault period is set based on the detection data, and a correspondence relationship between the operation data and the target health degree is established. Here, the setting manner of the target health degree may refer to the setting manner of the historical health degree in step 202, and is not described herein again.
Then, the operating data is used as the input of the health degree detection model, the target health degree is used as the output of the health degree detection model, and the health degree detection model is trained by a machine learning method so as to update the parameters of the health degree detection model.
As can be seen from fig. 2, compared with the embodiment corresponding to fig. 1, the flow 200 of the detection method in this embodiment relates to the step of retraining the model by using the operation data when the oilfield equipment fails. Therefore, the scheme described in the embodiment can optimize the model in real time, and the accuracy of the model is improved.
With further reference to fig. 3, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of a detection apparatus, which corresponds to the embodiment of the method shown in fig. 1, and which is particularly applicable to various electronic devices.
As shown in fig. 3, the detecting device 300 of the present embodiment includes: the first acquisition unit 301 is configured to acquire operation data to be detected of the oilfield equipment during production or self-inspection; the detection unit 302 is configured to input the operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield mobile equipment, wherein the health degree detection model is a health degree detection model for detecting the health degree of the oilfield mobile equipment, which is obtained by training historical operation data and historical detection data of the oilfield mobile equipment as training samples by using a machine learning method.
In some optional implementations of this embodiment, the oilfield equipment is equipped with a plurality of sensors; and the first obtaining unit is further configured to: through the sensors, the operation data to be detected of the oilfield equipment during production or self-inspection is periodically or real-timely acquired.
In some optional implementations of this embodiment, the health detection model is obtained by training through the following steps: acquiring historical operation data and historical detection data of the oilfield dynamic equipment; setting the historical health degree of the oil field power equipment based on the historical detection data; establishing a corresponding relation between each historical operation data and the historical health degree; and taking each historical operation data as the input of a pre-established initial model, taking the historical health degree corresponding to the input historical operation data as the output of the initial model, and training by using a machine learning method to obtain a health degree detection model for detecting the health degree of the oilfield mobile equipment.
In some optional implementations of this embodiment, the apparatus further includes: the device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is configured to acquire operation data of the oilfield dynamic equipment during the fault when the oilfield dynamic equipment fails and acquire detection data of the oilfield dynamic equipment after the fault occurs; and the updating unit is configured to train the health degree detection model by using a machine learning method by taking the operation data and the detection data as training samples so as to update the health degree detection model.
In some optional implementations of this embodiment, the update unit is further configured to: setting a target health degree of the oilfield equipment in the fault period based on the detection data, and establishing a corresponding relation between the operation data and the target health degree; and training the health degree detection model by using a machine learning method to update parameters of the health degree detection model by using the operation data as the input of the health degree detection model and the target health degree as the output of the health degree detection model.
In some optional implementations of this embodiment, the apparatus further includes: a first searching unit configured to search a preset first corresponding relation table for representing a corresponding relation between the health level and the health degree range, for a target health level corresponding to the current health degree indicated by the health degree detection result; the second searching unit is configured to search a target maintenance mode corresponding to the target health level from a preset second corresponding relation table, wherein the second corresponding relation table is used for representing the corresponding relation between the health level and the maintenance mode; and a maintenance unit configured to perform maintenance on the oilfield equipment using the target maintenance method.
In some optional implementation manners of this embodiment, the operation data to be detected includes at least one of the following: frequency spectrum, audio, current, voltage, flow, temperature, picture.
The detection device comprises a processor and a memory, the first acquisition unit, the detection unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize 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, the accuracy of the health degree detection of the oilfield dynamic equipment is improved by adjusting kernel parameters, and powerful technical support is provided for predictive maintenance.
An embodiment of the present invention provides a computer-readable medium on which a program is stored, which, when executed by a processor, implements the detection method.
The embodiment of the invention provides a processor, which is used for running a program, wherein the detection method is executed when the program runs.
The embodiment of the invention provides equipment, which comprises at least one processor, at least one memory and a bus, wherein the memory and the bus are connected with the processor; the processor and the memory complete mutual communication through a bus; the processor is used for calling the program instructions in the memory to execute the detection method. 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: acquiring operation data to be detected of the oilfield mobile equipment during production or self-inspection; and inputting the operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield mobile equipment, wherein the health degree detection model is a health degree detection model for detecting the health degree of the oilfield mobile equipment, which is obtained by training the historical operation data and the historical detection data of the oilfield mobile equipment as training samples by using a machine learning method.
Optionally, the oilfield power plant is provided with a plurality of sensors; the above-mentioned operation data to be detected that obtains the oil field and move equipment when production or self-checking includes: through the sensors, the operation data to be detected of the oilfield equipment during production or self-inspection is periodically or real-timely acquired.
Optionally, the health degree detection model is obtained by training through the following steps: acquiring historical operation data and historical detection data of the oilfield dynamic equipment; setting the historical health degree of the oil field power equipment based on the historical detection data; establishing a corresponding relation between each historical operation data and the historical health degree; and taking each historical operation data as the input of a pre-established initial model, taking the historical health degree corresponding to the input historical operation data as the output of the initial model, and training by using a machine learning method to obtain a health degree detection model for detecting the health degree of the oilfield mobile equipment.
Optionally, the program, when executed on a data processing device, may be adapted to further perform a procedure for initializing the following method steps: when the oil field power equipment fails, acquiring operation data of the oil field power equipment during the failure, and acquiring detection data of the oil field power equipment after the failure; and taking the operation data and the detection data as training samples, and training the health degree detection model by using a machine learning method so as to update the health degree detection model.
Optionally, the training the health degree detection model by using the operating data and the detection data as training samples and using a machine learning method to update the health degree detection model includes: setting a target health degree of the oilfield equipment in the fault period based on the detection data, and establishing a corresponding relation between the operation data and the target health degree; and training the health degree detection model by using a machine learning method to update parameters of the health degree detection model by using the operation data as the input of the health degree detection model and the target health degree as the output of the health degree detection model.
Optionally, after the health degree detection result of the oilfield equipment is obtained, the method may be further adapted to further execute a program initializing the following method steps: searching a target health level corresponding to the current health level indicated by the health level detection result from a preset first corresponding relation table, wherein the first corresponding relation table is used for representing the corresponding relation between the health level and the health level range; searching a target maintenance mode corresponding to the target health grade from a preset second corresponding relation table, wherein the second corresponding relation table is used for representing the corresponding relation between the health grade and the maintenance mode; and maintaining the oil field power equipment by using the target maintenance mode.
Optionally, the operation data to be detected includes at least one of the following items: frequency spectrum, audio, current, voltage, flow, temperature, picture.
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 (8)
1. A method of detection, the method comprising:
acquiring operation data to be detected of the oilfield mobile equipment during production or self-inspection;
inputting the operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield mobile equipment, wherein the health degree detection model is a health degree detection model for detecting the health degree of the oilfield mobile equipment, which is obtained by training the historical operation data and the historical detection data of the oilfield mobile equipment as training samples by using a machine learning method;
the historical operating data comprises frequency spectrum, audio frequency, current, voltage, flow and temperature;
the historical detection data comprises fault identification, fault types and alarm amount;
the health degree detection model is obtained by training through the following steps of:
acquiring historical operation data and historical detection data of the oilfield dynamic equipment;
setting the historical health degree of the oilfield equipment based on the historical detection data;
establishing a corresponding relation between each historical operation data and the historical health degree corresponding to the historical period;
and taking each historical operation data as the input of a pre-established initial model, taking the historical health degree corresponding to the input historical operation data as the output of the initial model, and training by using a machine learning method to obtain a health degree detection model for detecting the health degree of the oilfield mobile equipment.
2. The method of testing as defined in claim 1, wherein said oilfield equipment is equipped with a plurality of sensors; and
the method for acquiring the operation data to be detected of the oilfield dynamic equipment during production or self-inspection comprises the following steps:
and acquiring operation data to be detected of the oilfield equipment during production or self-inspection periodically or in real time through the plurality of sensors.
3. The detection method according to claim 1, further comprising:
when the oil field power equipment fails, acquiring operation data of the oil field power equipment during the failure, and acquiring detection data of the oil field power equipment after the failure;
and taking the operation data and the detection data as training samples, and training the health degree detection model by using a machine learning method so as to update the health degree detection model.
4. The detection method according to claim 3, wherein the training the health degree detection model by using the operation data and the detection data as training samples and using a machine learning method to update the health degree detection model comprises:
setting a target health degree of the oilfield equipment in the fault period based on the detection data, and establishing a corresponding relation between the operation data and the target health degree;
and taking the operating data as the input of the health degree detection model, taking the target health degree as the output of the health degree detection model, and training the health degree detection model by using a machine learning method so as to update the parameters of the health degree detection model.
5. The method of testing as defined in claim 1, wherein after said obtaining the health test results of the oilfield equipment, the method further comprises:
searching a target health level corresponding to the current health degree indicated by the health degree detection result from a preset first corresponding relation table, wherein the first corresponding relation table is used for representing the corresponding relation between the health level and the health degree range;
searching a target maintenance mode corresponding to the target health grade from a preset second corresponding relation table, wherein the second corresponding relation table is used for representing the corresponding relation between the health grade and the maintenance mode;
and maintaining the oil field power equipment by using the target maintenance mode.
6. A detection device, the device comprising:
the system comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is configured to acquire operation data to be detected of the oilfield equipment during production or self-inspection;
the detection unit is configured to input the operation data to be detected into a pre-constructed health degree detection model to obtain a health degree detection result of the oilfield mobile equipment, wherein the health degree detection model is a health degree detection model which is obtained by training historical operation data and historical detection data of the oilfield mobile equipment as training samples by using a machine learning method and is used for detecting the health degree of the oilfield mobile equipment;
the historical operating data comprises frequency spectrum, audio frequency, current, voltage, flow and temperature;
the historical detection data comprises fault identification, fault types and alarm amount;
the health degree detection model is obtained by training through the following steps of:
acquiring historical operation data and historical detection data of the oilfield dynamic equipment;
setting the historical health degree of the oilfield equipment based on the historical detection data;
establishing a corresponding relation between each historical operation data and the historical health degree corresponding to the historical period;
and taking each historical operation data as the input of a pre-established initial model, taking the historical health degree corresponding to the input historical operation data as the output of the initial model, and training by using a machine learning method to obtain a health degree detection model for detecting the health degree of the oilfield mobile equipment.
7. An apparatus, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
8. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910746127.0A CN112393931B (en) | 2019-08-13 | 2019-08-13 | Detection method, detection device, electronic equipment and computer readable medium |
| PCT/CN2019/126217 WO2021027213A1 (en) | 2019-08-13 | 2019-12-18 | Detection method and apparatus, electronic device and computer-readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910746127.0A CN112393931B (en) | 2019-08-13 | 2019-08-13 | Detection method, detection device, electronic equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112393931A CN112393931A (en) | 2021-02-23 |
| CN112393931B true CN112393931B (en) | 2022-04-19 |
Family
ID=74569681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910746127.0A Active CN112393931B (en) | 2019-08-13 | 2019-08-13 | Detection method, detection device, electronic equipment and computer readable medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112393931B (en) |
| WO (1) | WO2021027213A1 (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113221455A (en) * | 2021-05-10 | 2021-08-06 | 北京和利时系统工程有限公司 | Equipment health state detection method and device |
| CN113404742B (en) * | 2021-07-09 | 2024-01-26 | 中国人民解放军火箭军工程大学 | Electro-hydraulic servo mechanism health assessment method and system based on test data |
| CN113586961A (en) * | 2021-07-22 | 2021-11-02 | 北京山太公务机维修技术有限公司 | Aircraft maintenance oxygenation method, system, terminal and storage medium |
| CN113847305A (en) * | 2021-09-06 | 2021-12-28 | 盛景智能科技(嘉兴)有限公司 | Early warning method and early warning system for hydraulic system of operating machine and operating machine |
| CN113822577A (en) * | 2021-09-23 | 2021-12-21 | 烟台杰瑞石油装备技术有限公司 | Wellsite equipment health state evaluation method and device and storage medium |
| CN114664061A (en) * | 2022-02-24 | 2022-06-24 | 深圳有象智联科技有限公司 | Security monitoring method, device, terminal and computer readable storage medium |
| CN115186924A (en) * | 2022-07-28 | 2022-10-14 | 网思科技股份有限公司 | Equipment health state evaluation method and device based on artificial intelligence |
| CN115361254B (en) * | 2022-08-03 | 2024-01-19 | 杭州大杰智能传动科技有限公司 | Intelligent master station communication method and control system for three major mechanisms of tower crane |
| CN116699390A (en) * | 2023-04-20 | 2023-09-05 | 上海宇佑船舶科技有限公司 | Diesel engine set fault detection method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800139A (en) * | 2018-12-18 | 2019-05-24 | 东软集团股份有限公司 | Server health degree analysis method, device, storage medium and electronic equipment |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| MX347127B (en) * | 2011-07-08 | 2017-04-17 | Schlumberger Technology Bv | System and method for determining a health condition of wellsite equipment. |
| US11476781B2 (en) * | 2012-11-16 | 2022-10-18 | U.S. Well Services, LLC | Wireline power supply during electric powered fracturing operations |
| US9611705B2 (en) * | 2013-10-11 | 2017-04-04 | Antelope Oil Tool & Mfg. Co. | Centralizer preconditioning and testing apparatus and method |
| CN106022352A (en) * | 2016-05-05 | 2016-10-12 | 哈尔滨理工大学 | Submersible piston pump fault diagnosis method based on support vector machine |
| WO2019023255A1 (en) * | 2017-07-24 | 2019-01-31 | Bj Services, Llc | Developing oilfield models using cognitive computing |
| CN108460515A (en) * | 2018-01-16 | 2018-08-28 | 中国海洋石油集团有限公司 | A kind of electric immersible pump well unit failure risk prediction technique |
| CN109460561B (en) * | 2018-07-25 | 2021-08-17 | 北京国双科技有限公司 | Fault diagnosis method and device for oil extraction equipment |
| CN109632355B (en) * | 2018-12-20 | 2021-03-16 | 广州航天海特系统工程有限公司 | Fault prediction method and system based on electromechanical device state data drift |
| CN109657982B (en) * | 2018-12-20 | 2022-02-11 | 三一重能有限公司 | Fault early warning method and device |
| CN109854304A (en) * | 2019-03-11 | 2019-06-07 | 天地（常州）自动化股份有限公司 | Coal mine safety monitoring system Grading And Zoning alarm method and safety monitoring system |
-
2019
- 2019-08-13 CN CN201910746127.0A patent/CN112393931B/en active Active
- 2019-12-18 WO PCT/CN2019/126217 patent/WO2021027213A1/en active Application Filing
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800139A (en) * | 2018-12-18 | 2019-05-24 | 东软集团股份有限公司 | Server health degree analysis method, device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021027213A1 (en) | 2021-02-18 |
| CN112393931A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112393931B (en) | Detection method, detection device, electronic equipment and computer readable medium | |
| US20210011791A1 (en) | Abnormality detection system, abnormality detection method, abnormality detection program, and method for generating learned model | |
| JP2021064370A (en) | Method and system for semi-supervised deep abnormality detection for large-scale industrial monitoring system based on time-series data utilizing digital twin simulation data | |
| TWI385492B (en) | A system for maintaining and analyzing manufacturing equipment and method therefor | |
| WO2020019681A1 (en) | Fault diagnosis method and apparatus for oil production equipment | |
| CN112346941A (en) | Fault diagnosis method and device | |
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| EP3183622B1 (en) | Population-based learning with deep belief networks | |
| US20210042585A1 (en) | Abnormality detection device, abnormality detection method and computer readable medium | |
| CN110426634B (en) | Method and equipment for predicting abnormity of driving system | |
| CN105593864B (en) | Analytical device degradation for maintenance device | |
| CN111174370A (en) | Fault detection method and device, storage medium and electronic device | |
| CN107942956B (en) | Information processing device, information processing method, information processing program, and recording medium | |
| CN109213034B (en) | Equipment health degree monitoring method and device, computer equipment and readable storage medium | |
| US20220004163A1 (en) | Apparatus for predicting equipment damage | |
| CN113762344A (en) | Fault identification method of machine tool spindle and fault identification model training method and device | |
| Wang et al. | Tool wear monitoring based on cointegration modelling of multisensory information | |
| CN111199090A (en) | Fault identification method and related equipment | |
| CN112577664A (en) | Sensor fault detection method and device and related product | |
| CN110543869A (en) | Ball screw service life prediction method and device, computer equipment and storage medium | |
| CN112882898B (en) | Anomaly detection method, system, device and medium based on big data log analysis | |
| CN110780198B (en) | Waveform identification method and equipment for servo welding system motion | |
| CN110995461B (en) | Network fault diagnosis method | |
| CN110956308A (en) | Chemical equipment health state prediction method based on time sequence | |
| EP4174601A1 (en) | System, apparatus and method for monitoring condition of an asset in technical installation |
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 |