CN111008203A - Method, device and terminal for diagnosing misalignment positioning of oil well metering instrument - Google Patents
Method, device and terminal for diagnosing misalignment positioning of oil well metering instrument Download PDFInfo
- Publication number
- CN111008203A CN111008203A CN201811381243.9A CN201811381243A CN111008203A CN 111008203 A CN111008203 A CN 111008203A CN 201811381243 A CN201811381243 A CN 201811381243A CN 111008203 A CN111008203 A CN 111008203A
- Authority
- CN
- China
- Prior art keywords
- oil well
- sequence
- loss function
- misalignment
- displacement
- 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.)
- Pending
Links
- 239000003129 oil well Substances 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000006073 displacement reaction Methods 0.000 claims abstract description 61
- 230000008859 change Effects 0.000 claims abstract description 56
- 238000003745 diagnosis Methods 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 230000000737 periodic effect Effects 0.000 claims description 48
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 abstract description 19
- 238000013528 artificial neural network Methods 0.000 abstract description 3
- 238000007619 statistical method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 62
- 230000015654 memory Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 5
- 238000005086 pumping Methods 0.000 description 5
- 230000004913 activation Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
Abstract
The invention provides a method, a device and a terminal for diagnosing misalignment positioning of an oil well metering instrument, wherein the method comprises the following steps: acquiring a load sequence, a displacement sequence, an electric power sequence and an oil well stroke frequency, and generating a characteristic sequence set; training a neural network diagnosis model according to the characteristic sequence set, and extracting the characteristics of the characteristic sequence changing along with time; performing loss function calculation according to the characteristic sequence set and the characteristics of the characteristic sequence changing along with time to obtain a sample loss function proportional value; and diagnosing the misalignment of the metering device according to the loss function proportional value. And after acquiring historical data of oil well monitoring and drawing a curve, performing statistical analysis on the historical data of oil well monitoring by using a neural network model, and extracting characteristics, thereby diagnosing misalignment of the oil well metering instrument and diagnosing whether misalignment occurs in the current load sensor, the displacement sensor and the intelligent electric meter. And give out warning in the control interface, help to arrange personnel to take emergency treatment measure and calibrate or change in time.
Description
Technical Field
The invention relates to the technical field of fault diagnosis of a digital automatic control device, in particular to a method, a device and a terminal for diagnosing misalignment positioning of an oil well metering instrument.
Background
In order to monitor the output, oil pumping efficiency and oil pumping working condition change of an oil well and improve the informatization level, each oil well at present adopts a large number of intelligent instruments to remotely monitor the indicator diagram, the oil temperature, the oil pressure, the working voltage, the current and the like of the oil pumping unit. However, as the number of wells related to remote monitoring is hundreds, the types and the number of related monitoring instruments are various, monitoring data often deviate from a normal range, monitoring personnel cannot judge what is the reason, professional personnel are often required to be sent to check, diagnose and remove faults on site, and if the diagnosis instrument is out of alignment, various spot inspection devices are required to be carried, various standby replacement products are required to be carried, so that special vehicles and the professional personnel are required to run on-site diagnosis and maintenance, and a lot of manpower and material resources are wasted.
Disclosure of Invention
The embodiment of the invention provides a method, a device and a terminal for diagnosing misalignment positioning of an oil well metering instrument, which are used for at least solving the technical problems in the prior art.
In a first aspect, an embodiment of the present invention provides a method for diagnosing misalignment positioning of an oil well measuring instrument, including:
acquiring a load sequence, a displacement sequence, an electric power sequence and an oil well stroke frequency, and generating a characteristic sequence set;
training a neural network model according to the characteristic sequence set, and extracting the characteristics of the characteristic sequence changing along with time;
performing loss function calculation according to the characteristic sequence set and the characteristics of the characteristic sequence changing along with time to obtain a sample loss function proportional value;
and diagnosing the misalignment of the metering device according to the loss function proportional value.
In one embodiment, the step of obtaining the load sequence, the displacement sequence and the electrical power sequence comprises:
acquiring historical load data, historical displacement data and historical power data;
drawing a periodic load change curve of an oil well according to the historical load data, drawing a periodic displacement change curve according to the historical displacement data, and drawing a periodic power change curve of an oil well motor according to the historical power data;
and obtaining the load sequence, the displacement sequence and the electric power sequence according to the oil well periodic load change curve, the periodic displacement change curve and the oil well motor periodic power change curve.
In one embodiment, diagnosing misalignment of a meter based on the loss function proportional value comprises:
when the loss function proportion value is less than or equal to 10%, the oil well metering instrument is normal according to the diagnosis result;
when the loss function proportion value is larger than 10% and smaller than or equal to 20%, the oil well metering instrument is to be monitored according to the diagnosis result;
when the loss function proportional value is greater than 20%, the diagnostic result is misalignment of the oil well metering instrument.
In a second aspect, the present invention also provides a well logging instrument misalignment positioning diagnostic apparatus, comprising:
the characteristic sequence acquisition module is used for acquiring a load sequence, a displacement sequence, an electric power sequence and an oil well stroke frequency to generate a characteristic sequence set;
the sequence change feature extraction module is used for training a neural network model according to the feature sequence set and extracting the feature of the feature sequence changing along with time;
the loss function calculation module is used for calculating a loss function according to the characteristic sequence set and the characteristics of the characteristic sequence changing along with time to obtain a sample loss function proportional value;
and the misalignment diagnosis module is used for diagnosing the misalignment of the metering device according to the loss function proportional value.
In one embodiment, the feature sequence acquisition module comprises:
the historical data acquisition unit is used for acquiring historical load data, historical displacement data and historical power data;
the change curve drawing unit is used for drawing an oil well periodic load change curve according to the historical load data, drawing a periodic displacement change curve according to the historical displacement data, and drawing an oil well motor periodic power change curve according to the historical power data;
and the sequence acquisition unit is used for obtaining the load sequence, the displacement sequence and the electric power sequence according to the oil well periodic load change curve, the periodic displacement change curve and the oil well motor periodic power change curve.
In one embodiment, the misalignment diagnostic module includes:
the normal diagnosis unit is used for judging that the oil well metering instrument is normal according to the diagnosis result when the loss function proportional value is less than or equal to 10%;
the to-be-monitored diagnosis unit is used for obtaining a diagnosis result that the oil well metering instrument is to be monitored when the loss function proportion value is larger than 10% and smaller than or equal to 20%;
and the misalignment diagnosis unit is used for diagnosing that the oil well metering instrument is misaligned when the loss function proportional value is greater than 20%.
In a third aspect, the invention also provides a terminal for diagnosing misalignment positioning of an oil well measuring instrument, which is characterized by comprising the device as described in any one of the above;
a display for displaying a diagnostic result of an oil well meter, the diagnostic result including that the oil well meter is normal, that the oil well meter is to be monitored, and that the oil well meter is misaligned;
and the alarm is used for sending an alarm signal when the diagnosis result is that the oil well metering instrument is out of order.
The functions can be realized by hardware, and the functions can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above-described functions.
In one possible design, the structure of the misalignment location diagnosis terminal for the oil well measuring instrument comprises a processor and a memory, the memory is used for storing a program for supporting the misalignment location diagnosis device for the oil well measuring instrument to execute the misalignment location diagnosis method for the oil well measuring instrument in the first aspect, and the processor is configured to execute the program stored in the memory. The misalignment positioning diagnosis terminal of the oil well measuring instrument can further comprise a communication interface, and the communication interface is used for communicating the misalignment positioning diagnosis terminal of the oil well measuring instrument with other equipment or a communication network.
One of the above technical solutions has the following advantages or beneficial effects: the method comprises the steps of obtaining historical data of oil well monitoring, drawing a curve, then carrying out statistical analysis on the historical data of oil well monitoring by using a neural network model, and extracting features, so that the misalignment of an oil well metering instrument is diagnosed, and whether the current load sensor, the displacement sensor and the intelligent electric meter are misaligned or not is diagnosed. And give out warning in the control interface, help to arrange personnel to take emergency treatment measure and calibrate or change in time.
The foregoing summary is provided for the purpose of description only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will be readily apparent by reference to the drawings and following detailed description.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.
FIG. 1 is a schematic flow chart of a method for diagnosing an oil well meter according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a method for diagnosing an oil well gauge provided in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an oil well metering instrument diagnostic device provided by an embodiment of the invention.
Detailed Description
In the following, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.
Example one
In one embodiment, a method for diagnosing misalignment positioning of a well logging instrument is provided, as shown in FIG. 1, comprising:
step S10: acquiring a load sequence, a displacement sequence, an electric power sequence and an oil well stroke frequency, and generating a characteristic sequence set;
step S20: training a neural network diagnosis model according to the characteristic sequence set, and extracting the characteristics of the characteristic sequence changing along with time;
step S30: performing loss function calculation according to the characteristic sequence set and the characteristics of the characteristic sequence changing along with time to obtain a sample loss function proportional value;
step S40: and diagnosing the misalignment of the metering device according to the loss function proportional value.
In this embodiment, the wellhead sensor of the oil well should be in a relatively balanced periodic state. According to the energy conservation model, E0 ═ E1+ E2-E3, E0: motor power, E1: suspension point load power, E2: friction (pumping unit loss) power, E3: the power of the balance weight. Wherein, the balance weight power theoretically combines with the displacement to form a sine curve, and the work done in one period is 0. The friction work is theoretically a straight line parallel to the displacement. Three standard parameters of suspension point load, displacement and electrical parameters are acquired on site.
In one example, under normal conditions, a load curve is drawn according to the load change of one stroke of the pumping unit, a two-dimensional curve formed by the load and the displacement is called a diagram curve, and a two-dimensional curve formed by the electric power and the displacement is called an electric power curve. The above curves are plotted over a short time series. In one implementation, the load sequence, displacement sequence, and electrical power sequence may be formed for a time sequence of a large span greater than three months.
As shown in fig. 2, first, the database is queried to obtain the periodic load variation curve, the periodic displacement variation curve and the electric power curve of the oil well in the latest period of time (such as the previous day and the current day) one by one. And obtaining the load sequence, the displacement sequence and the electric power sequence in a large-span time sequence according to the oil well periodic load change curve, the periodic displacement change curve and the oil well motor periodic power change curve. And acquiring a load sequence, a displacement sequence, an electric power sequence and the oil well stroke frequency to generate a characteristic sequence set.
Secondly, training a neural network model according to the characteristic sequence set. The characteristics of the data changing with time are found through a neural network model. And (3) realizing data feature extraction by using a depth self-encoder. In the table, LSTM (Long Short-Term Memory) is a Long Short-Term Memory network, as shown in the diagram data tables 1 and 2. The number of input parameters of the whole neural network model is 400 through calculation, 400 is input load and displacement vectors, dimensionality is continuously reduced in the encoding process, and main characteristic values are extracted, so that the network parameter configuration of each layer established by a self-encoder in the application deep learning of the following table is obtained. And entering model training and analyzing a model training result.
TABLE 1
| Network layer | Inputting parameters | Output parameter | Network type |
| Encoder 0 | 400 | 100 | LSTM |
| Encoder 1 | 100 | 80 | LSTM |
| Encoder 2 | 80 | 5 | LSTM |
| Decoder 1 | 5 | 80 | LSTM |
| Decoder 2 | 80 | 100 | LSTM |
| Output of | 100 | 400 | Data output |
TABLE 2
| Name (R) | Value of |
| Weight initialization function | |
| Weight update function | Learning rate of 0.05 |
| Activating a function | |
| Preventing overfitting functions | Regularization coefficient 0.0005 |
| Output layer loss function | |
| Output layer activation function |
Thirdly, calculating a loss function according to the acquired oil well data of 2-5 days in succession in the current time period to obtain a sample loss function proportion value. In a deep-learning self-encoder, the output data is considered as a prediction of the input data, the proximity of the two is characterized by a reconstructed error function, the sum of which is called a loss function throughout the sample set, and is used to diagnose misalignment of the meter in the meter misalignment discrimination.
The depth self-encoder includes an input layer, a hidden layer, and an output layer. Let the latitude of the input layer and the output layer be n, the latitude of the hidden layer be m, and the sample data set
i is an intermediate variable, x (i) is the ith vector, i ═ 1 to N, indicating a total of N vectors, which constitute a sample data set.
Let f be the coding function, g be the decoding function from the input layer to the hidden layer and g be the decoding function from the hidden layer to the output layer.
The coding part of the automatic encoder maps input data to a hidden layer unit by using a nonlinear mapping function, and if h represents the activation of a neural unit of a hidden layer, the mathematical expression is as follows:
h＝f(x)＝sf(wx+p)
where p is the transformed offset matrix, w represents the weight matrix connecting the input layer and the hidden layer, SfIndicating the activation function of the encoder, usually a Sigmoid function, i.e. f (x) 1/(1+ e)-x)。
The decoding calculation principle is similar to the encoding, and the original input data is reconstructed by using the hidden layer obtained by encoding.
Where q is the transformed offset matrix, y denotes the reconstruction of the input data by the decoder, Sg denotes the decoder activation function, usually Sigmoid function or identity function, w denotes the weight matrix between the hidden layer and the output layer, and the parameter θ from the encoder is { w, p, q }.
The output data may be considered a prediction of the input data, with a reconstruction error function L (x, y) characterizing how close y is to x.
When Sg is an identity function: l (x, y) | | | x-y | | | non-phosphor2
When Sg is Sigmoid function:
when the training sample set is
The overall loss function of the self-encoder is:
and finally, iteratively calculating the minimum value of JAE (theta) by repeatedly using a gradient descent algorithm, so that the parameters of the self-encoding network can be solved, and the training of the automatic encoder is completed.
And fourthly, diagnosing the misalignment risk probability of the misalignment metering instrument according to the loss function proportion value, and giving an alarm on a monitoring screen according to the misalignment risk probability.
The method comprises the steps that historical data of a time sequence uploaded by an oil well monitoring instrument through a monitoring network are analyzed through an oil well neural network based on monitoring software installed on a monitoring center server, specifically, high-level feature extraction of the data is achieved through a long-short-term memory network and a deep self-coding structure, abnormal data detection is achieved through a support vector data description method, meanwhile, misalignment of the oil well metering instrument is diagnosed, and whether misalignment occurs in a current load sensor, a displacement sensor and an intelligent electric meter or not is diagnosed. And give out warning in the control interface, help to arrange personnel to take emergency treatment measure and calibrate or change in time.
In one embodiment, the step of obtaining the load sequence, the displacement sequence and the electrical power sequence comprises:
acquiring historical load data, historical displacement data and historical power data;
drawing a periodic load change curve of an oil well according to the historical load data, drawing a periodic displacement change curve according to the historical displacement data, and drawing a periodic power change curve of an oil well motor according to the historical power data;
and obtaining the load sequence, the displacement sequence and the electric power sequence according to the oil well periodic load change curve, the periodic displacement change curve and the oil well motor periodic power change curve.
In one example, the oil well monitoring physical model comprises a load sensor, a displacement sensor, a remote terminal unit of a smart meter and serial port networking equipment, wherein the load sensor is used for monitoring and acquiring oil well load data, the displacement sensor is used for monitoring and acquiring displacement data and stroke frequency, the smart meter is used for monitoring and acquiring oil well electric power data, and uploading load data, historical displacement data and historical power data of historical time periods and recent time periods through the remote terminal unit on site. And drawing a periodic load change curve of the oil well according to the historical load data, drawing a periodic displacement change curve according to the historical displacement data, and drawing a periodic power change curve of the oil well motor according to the historical power data. And uploading data such as a periodic load change curve, a periodic displacement change curve, an oil well motor periodic power change curve and the like to a water injection well site or a monitoring center server of the united station through a monitoring network. The monitoring network is based on the digital oil field automatic system monitoring network, and only the necessary hardware and software upgrading is needed to implement the scheme, so that the monitoring network becomes a higher-level comprehensive information network.
In one embodiment, diagnosing misalignment of a meter based on the loss function proportional value comprises:
when the loss function proportion value is less than or equal to 10%, the oil well metering instrument is normal according to the diagnosis result;
when the loss function proportion value is larger than 10% and smaller than or equal to 20%, the oil well metering instrument is to be monitored according to the diagnosis result;
when the loss function proportional value is greater than 20%, the diagnostic result is misalignment of the oil well metering instrument.
In one example, well metering is normal when the loss function is no higher than 10% of the overall sample data, overall data sample, well metering is to be monitored when the loss function is no higher than 20% and higher than 10% of the overall sample data, and well metering is abnormal when the loss function is higher than 20% of the overall sample data.
Example two
The invention also provides a misalignment positioning diagnostic device for an oil well measuring instrument, as shown in fig. 3, comprising:
the characteristic sequence acquisition module 10 is used for acquiring a load sequence, a displacement sequence, an electric power sequence and an oil well stroke frequency to generate a characteristic sequence set;
a sequence change feature extraction module 20, configured to train a neural network model according to the feature sequence set, and extract features of the feature sequence changing with time;
the loss function calculation module 30 is configured to perform loss function calculation according to the feature sequence set and the feature of the feature sequence changing with time to obtain a sample loss function ratio value;
and the misalignment diagnosis module 40 is used for diagnosing the misalignment of the metering device according to the loss function proportional value.
In one embodiment, the feature sequence acquisition module 10 includes:
the historical data acquisition unit is used for acquiring historical load data, historical displacement data and historical power data;
the change curve drawing unit is used for drawing an oil well periodic load change curve according to the historical load data, drawing a periodic displacement change curve according to the historical displacement data, and drawing an oil well motor periodic power change curve according to the historical power data;
and the sequence acquisition unit is used for obtaining the load sequence, the displacement sequence and the electric power sequence according to the oil well periodic load change curve, the periodic displacement change curve and the oil well motor periodic power change curve.
In one embodiment, the misalignment diagnostic module 40 includes:
the normal diagnosis unit is used for judging that the oil well metering instrument is normal according to the diagnosis result when the loss function proportional value is less than or equal to 10%;
the to-be-monitored diagnosis unit is used for obtaining a diagnosis result that the oil well metering instrument is to be monitored when the loss function proportion value is larger than 10% and smaller than or equal to 20%;
and the misalignment diagnosis unit is used for diagnosing that the oil well metering instrument is misaligned when the loss function proportional value is greater than 20%.
EXAMPLE III
The invention also provides an oil well metering instrument misalignment positioning diagnosis terminal which is characterized by comprising the device as described in any one of the above items;
a display for displaying a diagnostic result of an oil well meter, the diagnostic result including that the oil well meter is normal, that the oil well meter is to be monitored, and that the oil well meter is misaligned;
and the alarm is used for sending an alarm signal when the diagnosis result is that the oil well metering instrument is out of order.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (7)
1. A method of diagnosing misalignment of an oil well logging instrument, comprising:
acquiring a load sequence, a displacement sequence, an electric power sequence and an oil well stroke frequency, and generating a characteristic sequence set;
training a neural network model according to the characteristic sequence set, and extracting the characteristics of the characteristic sequence changing along with time;
performing loss function calculation according to the characteristic sequence set and the characteristics of the characteristic sequence changing along with time to obtain a sample loss function proportional value;
and diagnosing the misalignment of the metering device according to the loss function proportional value.
2. The method of claim 1, wherein the step of obtaining a load sequence, a displacement sequence, and an electrical power sequence comprises:
acquiring historical load data, historical displacement data and historical power data;
drawing a periodic load change curve of an oil well according to the historical load data, drawing a periodic displacement change curve according to the historical displacement data, and drawing a periodic power change curve of an oil well motor according to the historical power data;
and obtaining the load sequence, the displacement sequence and the electric power sequence according to the oil well periodic load change curve, the periodic displacement change curve and the oil well motor periodic power change curve.
3. The method of claim 1, wherein diagnosing misalignment of a meter based on the loss function proportional value comprises:
when the loss function proportion value is less than or equal to 10%, the oil well metering instrument is normal according to the diagnosis result;
when the loss function proportion value is larger than 10% and smaller than or equal to 20%, the oil well metering instrument is to be monitored according to the diagnosis result;
when the loss function proportional value is greater than 20%, the diagnostic result is misalignment of the oil well metering instrument.
4. An oil well instrumentation misalignment positioning diagnostic apparatus comprising:
the characteristic sequence acquisition module is used for acquiring a load sequence, a displacement sequence, an electric power sequence and an oil well stroke frequency to generate a characteristic sequence set;
the sequence change feature extraction module is used for training a neural network model according to the feature sequence set and extracting the feature of the feature sequence changing along with time;
the loss function calculation module is used for calculating a loss function according to the characteristic sequence set and the characteristics of the characteristic sequence changing along with time to obtain a sample loss function proportional value;
and the misalignment diagnosis module is used for diagnosing the misalignment of the metering device according to the loss function proportional value.
5. The apparatus of claim 4, wherein the signature sequence acquisition module comprises:
the historical data acquisition unit is used for acquiring historical load data, historical displacement data and historical power data;
the change curve drawing unit is used for drawing an oil well periodic load change curve according to the historical load data, drawing a periodic displacement change curve according to the historical displacement data, and drawing an oil well motor periodic power change curve according to the historical power data;
and the sequence acquisition unit is used for obtaining the load sequence, the displacement sequence and the electric power sequence according to the oil well periodic load change curve, the periodic displacement change curve and the oil well motor periodic power change curve.
6. The apparatus of claim 4, wherein the misalignment diagnostic module comprises:
the normal diagnosis unit is used for judging that the oil well metering instrument is normal according to the diagnosis result when the loss function proportional value is less than or equal to 10%;
the to-be-monitored diagnosis unit is used for obtaining a diagnosis result that the oil well metering instrument is to be monitored when the loss function proportion value is larger than 10% and smaller than or equal to 20%;
and the misalignment diagnosis unit is used for diagnosing that the oil well metering instrument is misaligned when the loss function proportional value is greater than 20%.
7. An oil well metrology instrument misalignment location diagnostic terminal comprising the apparatus of any one of claims 4 to 6;
a display for displaying a diagnostic result of an oil well meter, the diagnostic result including that the oil well meter is normal, that the oil well meter is to be monitored, and that the oil well meter is misaligned;
and the alarm is used for sending an alarm signal when the diagnosis result is that the oil well metering instrument is out of order.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811381243.9A CN111008203A (en) | 2018-11-20 | 2018-11-20 | Method, device and terminal for diagnosing misalignment positioning of oil well metering instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811381243.9A CN111008203A (en) | 2018-11-20 | 2018-11-20 | Method, device and terminal for diagnosing misalignment positioning of oil well metering instrument |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111008203A true CN111008203A (en) | 2020-04-14 |
Family
ID=70110715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811381243.9A Pending CN111008203A (en) | 2018-11-20 | 2018-11-20 | Method, device and terminal for diagnosing misalignment positioning of oil well metering instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008203A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202596709U (en) * | 2012-06-07 | 2012-12-12 | 东北石油大学 | Oil well fault intelligent diagnosing device |
| CN104234695A (en) * | 2014-08-27 | 2014-12-24 | 陕西延长石油(集团)有限责任公司研究院 | Oil well fault diagnosis method based on neural network |
| CN106555788A (en) * | 2016-11-11 | 2017-04-05 | 河北工业大学 | Application of the deep learning based on Fuzzy Processing in hydraulic equipment fault diagnosis |
| CN106682815A (en) * | 2016-11-30 | 2017-05-17 | 西安石油大学 | Pumping well monitoring system and monitoring method |
| US20180087360A1 (en) * | 2016-09-26 | 2018-03-29 | International Business Machines Corporation | Controlling operation of a steam-assisted gravity drainage oil well system by adjusting controls based on forecast emulsion production |
| CN108197648A (en) * | 2017-12-28 | 2018-06-22 | 华中科技大学 | A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on LSTM deep learning models |
-
2018
- 2018-11-20 CN CN201811381243.9A patent/CN111008203A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202596709U (en) * | 2012-06-07 | 2012-12-12 | 东北石油大学 | Oil well fault intelligent diagnosing device |
| CN104234695A (en) * | 2014-08-27 | 2014-12-24 | 陕西延长石油(集团)有限责任公司研究院 | Oil well fault diagnosis method based on neural network |
| US20180087360A1 (en) * | 2016-09-26 | 2018-03-29 | International Business Machines Corporation | Controlling operation of a steam-assisted gravity drainage oil well system by adjusting controls based on forecast emulsion production |
| CN106555788A (en) * | 2016-11-11 | 2017-04-05 | 河北工业大学 | Application of the deep learning based on Fuzzy Processing in hydraulic equipment fault diagnosis |
| CN106682815A (en) * | 2016-11-30 | 2017-05-17 | 西安石油大学 | Pumping well monitoring system and monitoring method |
| CN108197648A (en) * | 2017-12-28 | 2018-06-22 | 华中科技大学 | A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on LSTM deep learning models |
Non-Patent Citations (2)
| Title |
|---|
| 严学丰, 上海财经大学出版社 * |
| 崔广新 等: "基于自编码算法的深度学习综述", 《计算机系统应用》, vol. 27, no. 9, pages 425 - 426 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11334407B2 (en) | Abnormality detection system, abnormality detection method, abnormality detection program, and method for generating learned model | |
| CN108363886A (en) | Deformation prediction method and system based on deep learning | |
| CN112416643A (en) | Unsupervised anomaly detection method and unsupervised anomaly detection device | |
| CN113486420B (en) | Reservoir dam bank slope stability monitoring method, device, equipment and medium | |
| Mosallam et al. | Component based data-driven prognostics for complex systems: Methodology and applications | |
| CN113359682B (en) | Equipment fault prediction method, device, equipment fault prediction platform and medium | |
| CN110580488B (en) | Multi-working-condition industrial monitoring method, device, equipment and medium based on dictionary learning | |
| CN112416662A (en) | Multi-time series data anomaly detection method and device | |
| CN112036042A (en) | Power equipment abnormality detection method and system based on variational modal decomposition | |
| Qin et al. | Remaining useful life prediction for rotating machinery based on optimal degradation indicator | |
| CN112668526A (en) | Bolt group loosening positioning monitoring method based on deep learning and piezoelectric active sensing | |
| CN113760670A (en) | Cable joint abnormity early warning method and device, electronic equipment and storage medium | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| RU2719467C1 (en) | Method for complex monitoring of state of a multiparameter object based on heterogeneous information | |
| CN111008203A (en) | Method, device and terminal for diagnosing misalignment positioning of oil well metering instrument | |
| CN114837902B (en) | Health degree evaluation method, system, equipment and medium for wind turbine generator | |
| JP2019191880A (en) | Equipment management support system | |
| US11669082B2 (en) | Online fault localization in industrial processes without utilizing a dynamic system model | |
| CN114623799A (en) | Structural health monitoring data abnormity early warning method, system, device and storage medium | |
| Smarsly et al. | Real-time monitoring of wind energy converters based on software agents | |
| CN115222164B (en) | Water pump fault prediction method and system based on empirical coupling function | |
| CN111006747B (en) | Misalignment positioning diagnosis method and device for water injection metering instrument and terminal | |
| Akpudo et al. | A CEEMDAN-Assisted Deep Learning Model for the RUL Estimation of Solenoid Pumps. Electronics 2021, 10, 2054 | |
| CN117451288A (en) | Fault diagnosis method and device for offshore flexible straight platform valve cold main circulating pump | |
| CN117705178A (en) | Wind power bolt information detection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200414 |