CN114528895A - Fault detection method and device for oil well pump, computer equipment and storage medium - Google Patents

Fault detection method and device for oil well pump, computer equipment and storage medium Download PDF

Info

Publication number
CN114528895A
CN114528895A CN202011313334.6A CN202011313334A CN114528895A CN 114528895 A CN114528895 A CN 114528895A CN 202011313334 A CN202011313334 A CN 202011313334A CN 114528895 A CN114528895 A CN 114528895A
Authority
CN
China
Prior art keywords
fault detection
target
well pump
oil
sample
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
Application number
CN202011313334.6A
Other languages
Chinese (zh)
Inventor
陈哲
王洪雨
曲岩
蒋义伟
范德军
李石
谢庚易
刘艳秋
续瑾成
伏坤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Petrochina Co Ltd
Original Assignee
Petrochina Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Petrochina Co Ltd filed Critical Petrochina Co Ltd
Priority to CN202011313334.6A priority Critical patent/CN114528895A/en
Publication of CN114528895A publication Critical patent/CN114528895A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • 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
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Evolutionary Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

The application discloses a fault detection method and device of an oil well pump, computer equipment and a storage medium, and relates to the technical field of oil well pump detection. The method comprises the following steps: acquiring target characteristic information corresponding to a target oil well pump, determining a target fault detection model from at least two fault detection models according to the target characteristic information, wherein different fault detection models correspond to oil well pumps with different characteristics, the fault detection models are deep learning models, inputting a target indicator diagram of the target oil well pump into the target fault detection model, and obtaining a fault detection result output by the target fault detection model. Compare in the correlation technique according to general standard to the oil-well pump carry out fault detection, adopt the scheme that this application embodiment provided to carry out the pertinence based on the characteristic of oil-well pump and detect, help improving the detection accuracy of oil-well pump trouble.

Description

Fault detection method and device for oil well pump, computer equipment and storage medium
Technical Field
The application relates to the technical field of oil well pump detection, in particular to a fault detection method and device of an oil well pump, computer equipment and a storage medium.
Background
The oil well pump of the oil pumping unit is subjected to uninterrupted motion under complex conditions of a shaft and underground for a long time, and various faults can occur under the influence of structural parts of the oil well pump and environmental media in the shaft. In order to better maintain and repair the oil well pump aiming at different faults, the faults of the oil well pump need to be diagnosed, and the fault affecting the normal operation of the oil well pump is determined.
In the related technology, the fault of the oil well pump is diagnosed through the indicator diagram gridding model of the neural network, and whether different oil well pumps have faults or not and the type of the faults are analyzed based on the indicator diagram of the oil well pump by a set of universal standards.
However, in actual production applications, the faults corresponding to the same type of indicator diagram may not be the same for different wells, and therefore, the fault detection of the oil well pump based on the indicator diagram of the oil well pump cannot be performed according to a common standard.
Disclosure of Invention
In order to solve the problems of the related art, the embodiment of the application provides a fault detection method and device for an oil well pump, computer equipment and a storage medium. The technical scheme is as follows:
in one aspect, a fault detection method for an oil well pump is provided, and the method includes:
acquiring target characteristic information corresponding to a target oil well pump, wherein the target characteristic information comprises at least one of equipment characteristic information, production characteristic information and working environment characteristic information;
determining a target fault detection model from at least two fault detection models according to the target characteristic information, wherein different fault detection models correspond to oil-well pumps with different characteristics, and the fault detection model is a deep learning model;
and inputting the target indicator diagram of the target oil well pump into the target fault detection model to obtain a fault detection result output by the target fault detection model.
In another aspect, a fault detection device for an oil well pump is provided, the device comprising:
the first acquisition module is used for acquiring target characteristic information corresponding to a target oil well pump, wherein the target characteristic information comprises at least one of equipment characteristic information, production characteristic information and working environment characteristic information;
the first determining module is used for determining a target fault detection model from at least two fault detection models according to the target characteristic information, wherein different fault detection models correspond to oil-well pumps with different characteristics, and the fault detection model is a deep learning model;
and the detection module is used for inputting a target indicator diagram of the target oil well pump into the target fault detection model to obtain a fault detection result output by the target fault detection model.
In another aspect, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by the processor to implement the fault detection method of an oil well pump according to the above aspect.
In another aspect, a computer readable storage medium is provided, in which at least one instruction, at least one program, a set of codes or a set of instructions is stored, and the at least one instruction, the at least one program, the set of codes or the set of instructions is loaded and executed by a processor to implement the fault detection method for an oil well pump according to the above aspect.
In another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the fault detection method for the oil well pump provided in the above aspect or in various optional implementations of the above aspect.
The technical scheme provided by the embodiment of the application has the beneficial effects that at least:
because the working states of the oil well pumps with different equipment characteristics, production characteristics and working environment characteristics are different, in the embodiment of the application, when the fault detection is carried out on the target oil well pump, firstly, a target fault detection model matched with the characteristics of the target oil well pump is determined according to the target characteristic information of the target oil well pump, so that the fault detection is carried out on the basis of a target indicator diagram of the target oil well pump by utilizing the target fault detection model to obtain a fault detection result; compare in the correlation technique according to general standard to the oil-well pump carry out fault detection, adopt the scheme that this application embodiment provided to carry out the pertinence based on the characteristic of oil-well pump and detect, help improving the detection accuracy of oil-well pump trouble.
Drawings
FIG. 1 is a flow chart of a method of fault detection for an oil well pump according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of a method of fault detection for a pump according to another exemplary embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a process for clustering a sample pump based on a sample feature vector according to an exemplary embodiment of the present application;
FIG. 4 is an indicator diagram provided by an exemplary embodiment of the present application;
fig. 5 is a schematic structural diagram of a fault detection device of an oil well pump according to an exemplary embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
In the description of the present application, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. "plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, and means that there can be three relationships, for example, a and/or B, and means that there are three cases of a alone, a and B simultaneously, and B alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Referring to fig. 1, a flowchart of a fault detection method for an oil well pump according to an exemplary embodiment of the present application is shown, where the method is used in a computer device for example, the fault detection method for an oil well pump includes:
step 101, acquiring target characteristic information corresponding to a target oil well pump, wherein the target characteristic information comprises at least one of equipment characteristic information, production characteristic information and working environment characteristic information.
The target oil well pump is an oil well pump for detecting which fault exists, the target characteristic information is used for representing the characteristics of the target oil well pump, the purpose of obtaining the target characteristic information corresponding to the target oil well pump is to determine the type of the target oil well pump based on the characteristics of the target oil well pump, the type is obtained by comprehensively analyzing various characteristics of the oil well pump and then classifying, and the fault of the target oil well pump can be accurately determined based on the type of the target oil well pump.
In some embodiments, the equipment characteristic information includes a model and a service life of the pumping unit, the production characteristic information includes quality and physical properties of the extracted oil, and the working environment characteristic information is geological conditions of an area where the target oil well pump is located.
And 102, determining a target fault detection model from at least two fault detection models according to the target characteristic information, wherein different fault detection models correspond to oil-well pumps with different characteristics, and the fault detection model is a deep learning model.
In a possible implementation manner, the computer device clusters the sample oil-well pumps in advance according to the characteristic information of the sample oil-well pumps, and trains the fault detection models corresponding to the sample oil-well pumps based on the historical working data (including the historical indicator diagram and the historical fault detection records) of each type of sample oil-well pumps, so as to obtain a plurality of fault detection models corresponding to the oil-well pumps with different characteristics.
Because different fault detection models correspond to oil-well pumps with different characteristics, if relevant data of a target oil-well pump is input into a fault detection model which does not correspond to the fault detection model, a subsequently obtained fault detection result is inconsistent with a fact, and therefore computer equipment needs to determine a target fault detection model from at least two fault detection models according to target characteristic information.
Deep learning is a new field in machine learning research, and the motivation is to establish and simulate a neural network for human brain to analyze and learn, which simulates the mechanism of human brain to interpret data, and a deep learning model is a deep learning carrier. The fault detection model in the embodiment of the application is a deep learning model obtained based on training of training samples.
The deep learning model includes at least one of a Visual Geometry Group Network (VGGNet), a google Network model (google net), a Residual Neural Network (ResNet), and an arix Network model (AlexNet), and the specific type of the fault detection model is not limited in this embodiment.
And 103, inputting a target indicator diagram of the target oil well pump into the target fault detection model to obtain a fault detection result output by the target fault detection model.
The indicator diagram is a closed curve measured by the indicator in a pumping cycle of the pumping unit, and in order to show the pattern of the change rule of the load of the suspension point of the pumping unit along with the displacement of the suspension point, the area enclosed by the closed curve represents the work done by the oil well pump in one reciprocating motion, and can indirectly reflect the fault conditions of the oil well pump, such as the type of the fault and the severity of the fault.
The target indicator diagram is the indicator diagram of the target oil well pump measured by the indicator in a certain period, and can reflect the fault condition of the target oil well pump in a certain period.
The fault detection result comprises the probability that the target oil well pump is in different types of faults, whether the target oil well pump has faults or not and the fault type when the target oil well pump has faults.
Optionally, the computer device takes the fault type with the highest probability as the fault type of the target oil well pump.
Optionally, the computer device uses the first n fault types with the highest probability as the fault types of the target oil well pump, and n is an integer greater than or equal to 1.
In an illustrative example, the computer device takes the fault type with the highest probability as the fault type of the target pump. If the three faults with the highest probability in the fault detection results output by the target fault detection model are fault type 1, fault type 2 and fault type 3, the probability of the fault type 1 is 80%, the probability of the fault type 2 is 10% and the probability of the fault type 3 is 5%, the computer device determines the fault type of the target oil well pump as fault type 1.
In other possible implementations, the computer device takes the fault type with the probability higher than the probability threshold as the fault type of the target oil well pump.
In summary, in this embodiment, because the working states of the oil well pumps with different device characteristics, production characteristics, and working environment characteristics are different, in the embodiment of the present application, when performing fault detection on a target oil well pump, firstly, a target fault detection model matching the characteristics of the target oil well pump is determined according to target characteristic information of the target oil well pump, so that fault detection is performed based on a target indicator diagram of the target oil well pump by using the target fault detection model to obtain a fault detection result; compare and carry out fault detection to the oil-well pump according to general standard among the correlation technique, adopt the scheme that this application embodiment provided to carry out the pertinence detection based on the characteristic of oil-well pump, help improving the detection accuracy of oil-well pump trouble.
Referring to fig. 2, a flowchart of a fault detection method for an oil well pump according to another exemplary embodiment of the present application is shown, where the method is used in a computer device for example, the fault detection method for an oil well pump includes:
step 201, obtaining a sample characteristic vector corresponding to the sample oil well pump, wherein the sample characteristic vector is obtained by converting sample characteristic information corresponding to the sample oil well pump.
The sample oil-well pump is an oil-well pump obtained by sampling a large number of samples, and the characteristic information of each type of the oil-well pump is not completely the same, so that more differences generally exist.
It is not easy to classify similar sample oil-well pumps only according to the characteristic information, because the characteristic information has many kinds, the similarity of a certain characteristic can only be obtained by singly comparing the same type of sample information, and the overall similarity of all the compared characteristics can not be obtained. Therefore, the sample characteristic information is converted into the sample characteristic vectors, and the computer equipment can obtain the overall similarity of all sample information of the sample oil well pump by calculating the similarity of each sample characteristic vector, so that the subsequent process of clustering the sample oil well pump is simplified.
Optionally, the computer device generates feature vectors of the sample oil well pump in different dimensions according to the sample feature information of each dimension of the sample oil well pump. The feature vector is set based on the similarity of the same type of sample information and the weight of different types of sample information.
Optionally, the computer device obtains sample characteristic information corresponding to the sample oil well pump, where the sample characteristic information includes information of k dimensions, and k is an integer greater than or equal to 2; and training a vector transformation model based on the sample characteristic information, wherein the vector transformation model is used for transforming the input characteristic information into a k-dimensional characteristic vector. Wherein the sample characteristic information may include at least one of equipment characteristic information, production characteristic information, and operating environment characteristic information.
In one possible implementation, the vector transformation model is a word to vector (w 2v) model, and the purpose of training the vector transformation model is to improve the speed and accuracy of transforming the sample feature information into the feature vector.
Optionally, for the ith dimension of the k dimensions, the computer device trains a vector transformation submodel corresponding to the ith dimension according to information corresponding to the ith dimension in the sample feature information, where i is a positive integer less than or equal to k; and generating a vector conversion model according to the k vector conversion submodels.
Because the sample feature information has multiple dimensions, that is, multiple types of sample feature information exist, the multiple types of sample feature information correspond to multiple dimensions of feature vectors, and the multiple dimensions of vectors are composed of single dimensions of vectors, a vector conversion sub-model corresponding to the single-dimensional sample feature information is needed, so that the single-dimensional sample feature information is firstly converted into the single-dimensional feature vectors through the vector conversion sub-model, and then the k single-dimensional feature vectors are combined to generate the k-dimensional feature vectors.
Step 202, clustering the sample oil well pumps based on the sample characteristic vectors to obtain at least one oil well pump cluster.
Clustering is the process of dividing a collection of physical or abstract objects into classes composed of similar objects. The clusters generated by clustering are a collection of a set of data objects that are similar to objects in the same cluster and distinct from objects in other clusters. In order to determine the oil-well pumps with similar characteristics, the computer device clusters the sample oil-well pumps based on the sample characteristic vectors through a clustering algorithm, so as to obtain at least one oil-well pump cluster, wherein the similarity of the sample characteristic vectors corresponding to the sample oil-well pumps in the same oil-well pump cluster is higher than the similarity of the sample characteristic vectors corresponding to the sample oil-well pumps in different oil-well pump clusters.
The clustering method includes k-means clustering, mean shift clustering, and density-based clustering, and the specific clustering algorithm used in this embodiment is not limited.
As shown in fig. 3, assuming that the sample feature vector is a two-dimensional vector, the sample feature vector may be represented by a point 304 on a planar coordinate system, and according to a distance between the points 304, the point may be clustered to obtain a first cluster 301, a second cluster 302, and a third cluster 303, where each cluster represents an oil pump cluster.
Step 203, for any oil pump cluster, training a fault detection model corresponding to the oil pump cluster according to a sample indicator diagram corresponding to a sample oil pump in the oil pump cluster and a fault label corresponding to the sample indicator diagram.
After the fault type of the sample oil well pump is determined, the fault label indicates the fault type corresponding to the sample indicator diagram.
Because the characteristic similarity of the sample oil-well pumps in the same oil-well pump cluster is higher, and the fault types corresponding to the same sample indicator diagram are basically the same, the fault label can be accurately made for the sample indicator diagram, and then the fault detection model corresponding to the oil-well pump cluster is trained according to the sample indicator diagram corresponding to the sample oil-well pump in the oil-well pump cluster and the fault label corresponding to the sample indicator diagram, and the fault detection model is used for detecting the fault of the oil-well pump with the higher characteristic similarity with the sample oil-well pump in the oil-well pump cluster.
Optionally, the computer device selects a part of the sample indicator diagram as a training set, and the remaining part of the sample indicator diagram as a test set, inputs the training set into the deep learning network for training to obtain a fault detection model corresponding to the oil-well pump cluster, inputs the test set into the fault detection model to obtain a detection result, and adjusts a weight coefficient and a bias term in the fault detection model according to the detection result.
And 204, determining candidate characteristic vectors corresponding to the fault detection model according to the sample characteristic vectors corresponding to the sample oil-well pumps in the oil-well pump cluster.
In a possible implementation manner, in order to facilitate subsequent determination of the oil-well pump cluster to which the oil-well pump to be detected belongs, and thus to select a fault detection model corresponding to the cluster for fault detection, the computer device needs to further determine a candidate feature vector representing the feature of the oil-well pump cluster according to a sample feature vector corresponding to a sample oil-well pump in the oil-well pump cluster.
In a possible implementation manner, the computer device determines a vector average value of a sample feature vector corresponding to a sample oil-well pump in the oil-well pump cluster as a candidate feature vector of the oil-well pump cluster. In an illustrative example, the oil well pump cluster includes 100 sample oil well pumps, and the computer device determines an average value of feature vectors of the samples corresponding to the 100 sample oil well pumps as a candidate feature vector.
Through the steps 201 to 204, the computer equipment completes the training of the fault detection models corresponding to the oil-well pumps of different types, and the subsequent computer equipment can perform fault detection on the oil-well pumps by using the fault detection models obtained through the training.
And step 205, acquiring target characteristic information corresponding to the target oil well pump.
The step 101 may be referred to in the implementation manner of this step, and this embodiment is not described herein again.
Step 206, converting the target characteristic information into a target characteristic vector.
The target characteristic information needs to be compared with the sample characteristic information to determine the similarity between the characteristics of the target oil well pump and the characteristics of which sample oil well pumps, so that a target fault detection model is determined, but the sample characteristic information is converted into a sample characteristic vector, candidate characteristic vectors for representing the characteristics of various oil well pumps are determined according to the sample characteristic vector, the information cannot be compared with the vectors, and therefore the target characteristic information needs to be converted into the target characteristic vector.
In a possible implementation manner, the computer device inputs the target feature information into a vector transformation model obtained by training in the model training process to obtain the target feature vector.
And step 207, determining a target fault detection model from at least two fault detection models according to the target characteristic vector and the candidate characteristic vectors corresponding to the fault detection models respectively.
Optionally, the computer device calculates a vector distance between the target feature vector and each candidate feature vector, and determines the fault detection model corresponding to the minimum vector distance as the target fault detection model.
The vector distance reflects the magnitude of the similarity degree between vectors, the larger the vector distance is, the smaller the similarity degree between vectors is, and conversely, the smaller the vector distance is, the larger the similarity degree between vectors is.
When the vector distance between the target characteristic vector and a certain candidate characteristic vector is minimum, the characteristics of the target oil well pump and the sample oil well pump corresponding to the candidate characteristic vector are most similar, and therefore the fault detection model corresponding to the minimum vector distance is determined as the target fault detection model.
The vector distance calculation method includes an euclidean distance algorithm, a manhattan distance algorithm, and an angle cosine algorithm, which is not limited in this embodiment.
In one illustrative example, the computer device calculates a vector distance between a target feature vector and a candidate feature vector using the euclidean distance algorithm, where the target feature vector a is (x)1，x2，...xn) Some candidate feature vector b ═ y1，y2,...yn) The Euclidean distance between the target feature vector and the candidate feature vectorThe formula for the calculation is:
Figure BDA0002790524600000091
and 208, acquiring at least two candidate indicator diagrams corresponding to the target oil well pump, wherein the at least two candidate indicator diagrams are continuously generated indicator diagrams.
The indicator diagram is a graph representing the work done by the oil well pump in one reciprocating motion, so that the continuously generated indicator diagram can represent the work done by the oil well pump in several continuous reciprocating motions, and the time when the oil well pump breaks down can be determined based on the work done by the oil well pump in several continuous reciprocating motions represented by the indicator diagram.
In one possible implementation, the computer device acquires at least two candidate indicator diagrams generated continuously, so as to determine a target indicator diagram for fault detection from the candidate indicator diagrams.
Step 209, if the indicator diagram similarity between the first candidate indicator diagram and the second candidate indicator diagram is smaller than the similarity threshold, determining the second candidate indicator diagram as the target indicator diagram, where the first candidate indicator diagram and the second candidate indicator diagram are adjacent indicator diagrams.
Because the indicator diagram generated by the indicator does not have too much difference in shape under the condition that the oil well pump is in normal operation, namely the similarity of the indicator diagram is higher, and once the oil well pump has a fault, the indicator diagram generated under the fault is obviously different from the shape of the oil well pump in normal operation, namely the similarity of the indicator diagram is lower, the computer equipment can select the candidate indicator diagram with lower similarity for subsequent fault detection by comparing the indicator diagram similarity of the candidate indicator diagram.
Optionally, if the area difference between the first candidate indicator diagram and the second candidate indicator diagram is greater than the area difference threshold, and/or the difference between the tangent slope extreme value at the target position on the second candidate indicator diagram and the target slope is greater than the tangent slope difference threshold, the computer device determines the second candidate indicator diagram as the target indicator diagram.
As shown in fig. 4, a first candidate indicator diagram 401 is an indicator diagram of an oil well pump in a normal operation state, and is shaped like a parallelogram, and a second candidate indicator diagram 402 is an indicator diagram of an oil well pump in a fault state, and is shaped like an irregular figure. The first candidate indicator diagram 401 and the second candidate indicator diagram 402 have a difference in area, and the slope of each side of the first candidate indicator diagram 401 is fixed, but the slope of the tangent line of a point on the corresponding side of the second candidate indicator diagram 402 is not the same.
And step 210, inputting the target indicator diagram into the target fault detection model to obtain a fault detection result output by the target fault detection model.
The step 103 may be referred to in the implementation manner of this step, and this embodiment is not described herein again.
In summary, in the embodiment, the efficiency of determining the target fault detection model is improved by converting the feature information into the feature vector and determining the target fault detection model according to the feature vector; and the sample oil-well pumps are clustered based on the sample characteristic vectors to obtain at least one oil-well pump cluster, so that model training is performed based on a sample indicator diagram and a fault label of the sample oil-well pumps in the same oil-well pump cluster, the pertinence and the training quality of the model training are improved, and the accuracy of subsequent fault detection is further improved.
In addition, in this embodiment, the computer device screens out the target indicator diagram for fault detection according to the similarity between the indicator diagrams generated continuously, so as to avoid processing resource waste caused by fault detection on each indicator diagram.
Please refer to fig. 5, which illustrates a schematic structural diagram of a fault detection apparatus of an oil well pump according to an embodiment of the present application. The device includes: a first obtaining module 501, a first determining module 502 and a detecting module 503.
A first obtaining module 501, configured to obtain target characteristic information corresponding to a target oil well pump, where the target characteristic information includes at least one of equipment characteristic information, production characteristic information, and working environment characteristic information;
a first determining module 502, configured to determine a target fault detection model from at least two fault detection models according to the target feature information, where different fault detection models correspond to oil-well pumps with different features, and the fault detection model is a deep learning model;
and the detection module 503 is configured to input the target indicator diagram of the target oil well pump into the target fault detection model, and obtain a fault detection result output by the target fault detection model.
Optionally, the first determining module 502 includes:
the conversion unit is used for converting the target characteristic information into a target characteristic vector;
and the first determining unit is used for determining the target fault detection model from at least two fault detection models according to the target characteristic vector and the candidate characteristic vector corresponding to each fault detection model.
Optionally, the first determining unit is configured to:
calculating a vector distance between the target feature vector and each candidate feature vector;
and determining the fault detection model corresponding to the minimum vector distance as the target fault detection model.
Optionally, the apparatus further comprises:
the second acquisition module is used for acquiring a sample characteristic vector corresponding to the sample oil well pump, and the sample characteristic vector is obtained by converting sample characteristic information corresponding to the sample oil well pump;
the clustering module is used for clustering the sample oil well pump based on the sample characteristic vector to obtain at least one oil pump cluster;
the first training module is used for training the fault detection model corresponding to any oil pump cluster according to a sample indicator diagram corresponding to the sample oil-well pump in the oil pump cluster and a fault label corresponding to the sample indicator diagram;
and the second determination module is used for determining the candidate characteristic vector corresponding to the fault detection model according to the sample characteristic vector corresponding to the sample oil-well pump in the oil-well pump cluster.
Optionally, the apparatus further comprises:
the third acquisition module is used for acquiring sample characteristic information corresponding to the sample oil well pump, wherein the sample characteristic information contains information of k dimensions, and k is an integer greater than or equal to 2;
and the second training module is used for training a vector conversion model based on the sample characteristic information, and the vector conversion model is used for converting the input characteristic information into a k-dimensional characteristic vector.
Optionally, the second training module includes:
the training unit is used for training a vector conversion sub-model corresponding to the ith dimension according to information corresponding to the ith dimension in the sample characteristic information for the ith dimension in the k dimensions, wherein i is a positive integer less than or equal to k;
and the generating unit is used for generating the vector conversion model according to the k vector conversion sub-models.
Optionally, the detecting module 503 includes
The acquisition unit is used for acquiring at least two candidate indicator diagrams corresponding to the target oil well pump, wherein the at least two candidate indicator diagrams are continuously generated indicator diagrams;
a second determining unit, configured to determine a second candidate indicator diagram as the target indicator diagram if indicator diagram similarity between a first candidate indicator diagram and the second candidate indicator diagram is smaller than a similarity threshold, where the first candidate indicator diagram and the second candidate indicator diagram are adjacent to each other to generate indicator diagrams;
and the detection unit is used for inputting the target indicator diagram into the target fault detection model to obtain the fault detection result output by the target fault detection model.
In summary, in the embodiment of the present application, because the working states of the oil well pumps with different equipment characteristics, production characteristics, and working environment characteristics are different, in the embodiment of the present application, when performing fault detection on a target oil well pump, a target fault detection model matching with the characteristics of the target oil well pump is determined according to target characteristic information of the target oil well pump, so that fault detection is performed based on a target indicator diagram of the target oil well pump by using the target fault detection model to obtain a fault detection result; compare in the correlation technique according to general standard to the oil-well pump carry out fault detection, adopt the scheme that this application embodiment provided to carry out the pertinence based on the characteristic of oil-well pump and detect, help improving the detection accuracy of oil-well pump trouble.
In the embodiment, the efficiency of determining the target fault detection model is improved by converting the characteristic information into the characteristic vector and determining the target fault detection model according to the characteristic vector; and the sample oil-well pumps are clustered based on the sample characteristic vectors to obtain at least one oil-well pump cluster, so that model training is performed based on a sample indicator diagram and a fault label of the sample oil-well pumps in the same oil-well pump cluster, the pertinence and the training quality of the model training are improved, and the accuracy of subsequent fault detection is further improved.
In addition, in this embodiment, the computer device screens out the target indicator diagram for fault detection according to the similarity between the indicator diagrams generated continuously, so as to avoid processing resource waste caused by fault detection on each indicator diagram.
It should be noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.
Referring to fig. 6, a schematic structural diagram of a computer device according to an exemplary embodiment of the present application is shown. Specifically, the method comprises the following steps: the computer apparatus 600 includes a Central Processing Unit (CPU) 601, a system memory 604 including a random access memory 602 and a read only memory 603, and a system bus 605 connecting the system memory 604 and the CPU 601. The computer device 600 also includes a basic Input/Output system (I/O system) 606, which facilitates the transfer of information between various devices within the computer, and a mass storage device 607, which stores an operating system 613, application programs 614, and other program modules 615.
The basic input/output system 606 includes a display 608 for displaying information and an input device 609 such as a mouse, keyboard, etc. for a user to input information. Wherein the display 608 and the input device 609 are connected to the central processing unit 601 through an input output controller 610 connected to the system bus 605. The basic input/output system 606 may also include an input/output controller 610 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 610 may also provide output to a display screen, a printer, or other type of output device.
The mass storage device 607 is connected to the central processing unit 601 through a mass storage controller (not shown) connected to the system bus 605. The mass storage device 607 and its associated computer-readable media provide non-volatile storage for the computer device 600. That is, the mass storage device 607 may include a computer-readable medium (not shown) such as a hard disk or drive.
Without loss of generality, the computer-readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes Random Access Memory (RAM), Read Only Memory (ROM), flash Memory or other solid state Memory technology, Compact disk Read-Only Memory (CD-ROM), Digital Versatile Disks (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media is not limited to the foregoing. The system memory 604 and mass storage device 607 described above may be collectively referred to as memory.
The memory stores one or more programs configured to be executed by the one or more central processing units 601, the one or more programs containing instructions for implementing the methods described above, and the central processing unit 601 executes the one or more programs to implement the methods provided by the various method embodiments described above.
According to various embodiments of the present application, the computer device 600 may also operate as a remote computer connected to a network via a network, such as the Internet. That is, the computer device 600 may be connected to the network 612 through the network interface unit 611 connected to the system bus 605, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 611.
The memory also includes one or more programs, stored in the memory, that include instructions for performing the steps performed by the computer device in the methods provided by the embodiments of the present application.
The embodiment of the present application further provides a computer-readable storage medium, where at least one instruction, at least one program, a code set, or an instruction set is stored in the computer-readable storage medium, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the fault detection method for an oil well pump provided in the foregoing embodiment.
Embodiments of the present application also provide a computer program product or a computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the fault detection method for the oil well pump provided in the above aspect or in various optional implementations of the above aspect.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps in the information processing method for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc. The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (10)

1. A method of fault detection for an oil well pump, the method comprising:
acquiring target characteristic information corresponding to a target oil well pump, wherein the target characteristic information comprises at least one of equipment characteristic information, production characteristic information and working environment characteristic information;
determining a target fault detection model from at least two fault detection models according to the target characteristic information, wherein different fault detection models correspond to oil-well pumps with different characteristics, and the fault detection model is a deep learning model;
and inputting the target indicator diagram of the target oil well pump into the target fault detection model to obtain a fault detection result output by the target fault detection model.
2. The method of claim 1, wherein determining a target fault detection model from at least two fault detection models based on the target characteristic information comprises:
converting the target characteristic information into a target characteristic vector;
and determining the target fault detection model from at least two fault detection models according to the target characteristic vector and the candidate characteristic vector corresponding to each fault detection model.
3. The method according to claim 2, wherein the determining the target fault detection model from at least two fault detection models according to the target feature vector and the candidate feature vector corresponding to each fault detection model comprises:
calculating a vector distance between the target feature vector and each candidate feature vector;
and determining the fault detection model corresponding to the minimum vector distance as the target fault detection model.
4. The method of claim 2, further comprising:
acquiring a sample characteristic vector corresponding to a sample oil well pump, wherein the sample characteristic vector is obtained by converting sample characteristic information corresponding to the sample oil well pump;
clustering the sample oil well pumps based on the sample characteristic vector to obtain at least one oil pump cluster;
for any oil pump cluster, training the fault detection model corresponding to the oil pump cluster according to a sample indicator diagram corresponding to the sample oil pump in the oil pump cluster and a fault label corresponding to the sample indicator diagram;
and determining the candidate characteristic vector corresponding to the fault detection model according to the sample characteristic vector corresponding to the sample oil-well pump in the oil-well pump cluster.
5. The method of any of claims 2 to 4, further comprising:
acquiring sample characteristic information corresponding to a sample oil well pump, wherein the sample characteristic information comprises information of k dimensions, and k is an integer greater than or equal to 2;
training a vector transformation model based on the sample feature information, wherein the vector transformation model is used for transforming the input feature information into a k-dimensional feature vector.
6. The method of claim 5, wherein training a vector transformation model based on the sample feature information comprises:
for the ith dimension in the k dimensions, training a vector conversion sub-model corresponding to the ith dimension according to information corresponding to the ith dimension in the sample characteristic information, wherein i is a positive integer less than or equal to k;
and generating the vector conversion model according to the k vector conversion sub-models.
7. The method according to any one of claims 1 to 4, wherein the step of inputting the target indicator diagram of the target oil well pump into the target fault detection model to obtain the fault detection result output by the target fault detection model comprises:
acquiring at least two candidate indicator diagrams corresponding to the target oil well pump, wherein the at least two candidate indicator diagrams are continuously generated indicator diagrams;
if the indicator diagram similarity between a first candidate indicator diagram and a second candidate indicator diagram is smaller than a similarity threshold value, determining the second candidate indicator diagram as the target indicator diagram, wherein the first candidate indicator diagram and the second candidate indicator diagram are adjacent indicator diagrams;
and inputting the target indicator diagram into the target fault detection model to obtain the fault detection result output by the target fault detection model.
8. A fault detection device for an oil well pump, the device comprising:
the first acquisition module is used for acquiring target characteristic information corresponding to a target oil well pump, wherein the target characteristic information comprises at least one of equipment characteristic information, production characteristic information and working environment characteristic information;
the first determining module is used for determining a target fault detection model from at least two fault detection models according to the target characteristic information, wherein different fault detection models correspond to oil-well pumps with different characteristics, and the fault detection model is a deep learning model;
and the detection module is used for inputting a target indicator diagram of the target oil well pump into the target fault detection model to obtain a fault detection result output by the target fault detection model.
9. A computer device comprising a processor and a memory, wherein the memory has stored therein at least one instruction, at least one program, set of codes or set of instructions, which is loaded and executed by the processor to implement the method of fault detection for an oil well pump according to any one of claims 1 to 7.
10. A computer readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the method of fault detection for an oil well pump according to any one of claims 1 to 7.
CN202011313334.6A 2020-11-20 2020-11-20 Fault detection method and device for oil well pump, computer equipment and storage medium Pending CN114528895A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011313334.6A CN114528895A (en) 2020-11-20 2020-11-20 Fault detection method and device for oil well pump, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011313334.6A CN114528895A (en) 2020-11-20 2020-11-20 Fault detection method and device for oil well pump, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114528895A true CN114528895A (en) 2022-05-24

Family

ID=81618664

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011313334.6A Pending CN114528895A (en) 2020-11-20 2020-11-20 Fault detection method and device for oil well pump, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114528895A (en)

Similar Documents

Publication Publication Date Title
Zhang et al. CADN: A weakly supervised learning-based category-aware object detection network for surface defect detection
JP6362808B1 (en) Information processing apparatus and information processing method
CN108985380B (en) Point switch fault identification method based on cluster integration
CN111222548A (en) Similar image detection method, device, equipment and storage medium
CN104038792A (en) Video content analysis method and device for IPTV (Internet Protocol Television) supervision
Du et al. Convolutional neural network-based data anomaly detection considering class imbalance with limited data
CN116861331A (en) Expert model decision-fused data identification method and system
Wen et al. A new method for identifying the ball screw degradation level based on the multiple classifier system
CN114897085A (en) Clustering method based on closed subgraph link prediction and computer equipment
CN113723558A (en) Remote sensing image small sample ship detection method based on attention mechanism
US11829442B2 (en) Methods and systems for efficient batch active learning of a deep neural network
CN117036732B (en) Electromechanical equipment detection system, method and equipment based on fusion model
CN111709475B (en) N-gram-based multi-label classification method and device
Boillet et al. Confidence estimation for object detection in document images
JP2021192155A (en) Program, method and system for supporting abnormality detection
CN111782805A (en) Text label classification method and system
CN116383747A (en) Anomaly detection method for generating countermeasure network based on multi-time scale depth convolution
CN114528895A (en) Fault detection method and device for oil well pump, computer equipment and storage medium
CN113591400B (en) Power dispatching monitoring data anomaly detection method based on characteristic correlation partition regression
CN116956089A (en) Training method and detection method for temperature anomaly detection model of electrical equipment
CN113920302A (en) Multi-head weak supervision target detection method based on cross attention mechanism
Laib et al. Unsupervised feature selection based on space filling concept
CN117290742B (en) Signal time sequence data fault diagnosis method and system based on dynamic clustering
CN117539920B (en) Data query method and system based on real estate transaction multidimensional data
US20230410477A1 (en) Method and device for segmenting objects in images using artificial intelligence

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