CN114386519A - Drilling motor composite fault diagnosis method - Google Patents
Drilling motor composite fault diagnosis method Download PDFInfo
- Publication number
- CN114386519A CN114386519A CN202210040179.8A CN202210040179A CN114386519A CN 114386519 A CN114386519 A CN 114386519A CN 202210040179 A CN202210040179 A CN 202210040179A CN 114386519 A CN114386519 A CN 114386519A
- Authority
- CN
- China
- Prior art keywords
- fault
- bayesian network
- layer
- fault diagnosis
- drilling motor
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 104
- 238000005553 drilling Methods 0.000 title claims abstract description 51
- 239000002131 composite material Substances 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000004927 fusion Effects 0.000 claims abstract description 27
- 230000000694 effects Effects 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims abstract description 4
- 230000005347 demagnetization Effects 0.000 claims description 3
- 230000001364 causal effect Effects 0.000 claims description 2
- 230000009191 jumping Effects 0.000 claims 1
- 150000001875 compounds Chemical class 0.000 description 4
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000007500 overflow downdraw method Methods 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Control Of Electric Motors In General (AREA)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
Abstract
The invention discloses a composite fault diagnosis method for a drilling motor in the field of fault diagnosis of drilling equipment. The method specifically comprises the following steps: (1) defining a Bayesian network for fault diagnosis based on the operation data; (2) defining a Bayesian network for fault diagnosis based on working condition data; (3) defining a Bayesian network for fault diagnosis based on data fusion by combining two methods; (4) establishing a Bayesian network structure model and a parameter model for fault diagnosis based on data fusion; (5) and defining a fault diagnosis rule, updating the posterior probability of the fault node, and judging the fault type and the fault state. The invention integrates all available fault information in the drilling process for fault diagnosis, and places the drilling motor operation data in the specific working condition information for diagnosis, thereby increasing the fault characteristic discrimination and improving the identification effect of the composite fault. The fault type can be judged to be single fault or composite fault, and the fault state can be judged to be fault early warning or fault report. The embodiment shows that the information fusion model improves the accuracy and robustness of the fault diagnosis result and corrects missed diagnosis and misdiagnosis results in the composite fault diagnosis.
Description
Technical Field
The invention relates to the field of fault diagnosis of drilling equipment, in particular to a drilling motor composite fault diagnosis method.
Background
The drilling motor is suitable for downhole multi-working-condition operation, functions are continuously integrated, and the structure is more complex. The components of the drilling motor have high coupling and correlation, other faults can be induced by the fault which occurs firstly, and the faults can be mutually excited, so that a composite fault is formed. Different faults in a composite fault may have similar fault signatures, and in addition the downhole fault signature cannot be directly observed, making diagnosis of the composite fault more difficult. The traditional diagnosis method aiming at single fault has difficulty in meeting the requirement of compound fault diagnosis in complex equipment. At present, various intelligent diagnosis methods are being used to identify faults, and an information fusion method is a more effective method. The single data source has better single fault diagnosis effect, but when the method is applied to compound fault diagnosis, misdiagnosis and missed diagnosis are possible, and more accurate diagnosis effect can be obtained only by fusing all available fault information. With the progress of the information acquisition technology, the advantages of the information fusion technology in intelligent fault diagnosis can be more effectively exerted. Aiming at the problems, the invention provides a drilling motor composite fault diagnosis method which can improve the accuracy and robustness of single fault and composite fault diagnosis results and can correct missed diagnosis and misdiagnosis results of composite fault diagnosis.
Disclosure of Invention
The invention discloses a drilling motor composite fault diagnosis method. And respectively defining a Bayesian network based on operation data and a Bayesian network based on working condition data, then defining a fault diagnosis Bayesian network based on information fusion by combining the two networks, and establishing a Bayesian network fault diagnosis model based on information fusion. And collecting fault characteristic signals and working condition signals, and inputting the fault characteristic signals and the working condition signals into a diagnosis model to update the posterior probability of the fault node. And judging fault early warning or fault generation according to a corresponding threshold value of a diagnosis rule where the maximum difference value of the posterior probability and the prior probability of the fault node is located. The invention uses the information fusion model to improve the accuracy and robustness of the fault diagnosis result and correct missed diagnosis and misdiagnosis results in the composite fault diagnosis.
In order to achieve the above purpose, the invention discloses a drilling motor composite fault diagnosis method, which comprises the following basic steps:
step 1: defining a Bayesian network for fault diagnosis based on operation data, and dividing the network into two layers: fault layer and fault signature layer.
Step 2: defining a Bayesian network for fault diagnosis based on working condition data, and dividing the network into two layers: failure layer and failure cause layer.
And step 3: and fusing the Bayesian networks defined in the step 1 and the step 2 to define a Bayesian network for fault diagnosis based on data fusion, and dividing the network into three layers: fault cause layer, fault signature layer.
And 4, step 4: and 3, establishing a Bayesian network structure model and a parameter model for fault diagnosis based on data fusion according to the definition in the step 3.
And 5: and defining a fault diagnosis rule, updating the posterior probability of the fault node according to the states of the fault characteristic node and the reason node, and judging the fault type and the fault state.
Further, in step 1, the bayesian network for performing fault diagnosis based on the operation data is divided into a fault layer and a fault feature layer. Each fault level node represents a potential fault of the drilling motor; each failure signature layer node represents a signature of a failure of the drilling motor. The two layers of nodes are connected through directed edges to form a topological structure, and the causal relationship between the fault and the characteristic is shown.
Further, in step 1, the bayesian network fault layer node performing fault diagnosis based on the operation data is: rotor eccentricity, bearing faults, turn-to-turn short circuit and uniform demagnetization represent four typical potential faults of a drilling motor; the node states for each fault are divided into two categories: presence and absence.
Further, in the step 1, the nodes of the bayesian network fault feature layer for fault diagnosis based on the operation data are vibration signals, rotation speed signals, torque signals and current signals, and represent large data of a drilling motor operation well site obtained through a sensor; the node states of each feature are divided into three types: normal, high, low.
Further, in step 2, the bayesian network for fault diagnosis based on the operating condition data is divided into a fault layer and a fault cause layer. Each fault level node represents a potential fault of the drilling motor; each failure cause level node represents one extreme condition that may cause a drilling motor failure. The two layers of nodes are connected through directed edges to form a topological structure, and the cause and effect relationship between the fault reason and the fault is shown.
Further, in the step 2, the node and the node state of the bayesian network fault layer for fault diagnosis based on the working condition data are the same as the node and the node state of the bayesian network fault layer for fault diagnosis based on the operation data; the Bayesian network fault cause layer nodes for fault diagnosis based on the working condition data are drill tripping, stick slip and high temperature, and represent extreme working conditions possibly causing the fault of a drilling motor in the drilling process; the node states for each reason are divided into two types: presence and absence.
Further, in step 3, the bayesian network for fault diagnosis based on data fusion is divided into: fault cause layer, fault signature layer. And the nodes and node states of each layer are determined by the nodes and node states of each layer of the Bayesian network defined in the step 1 and the step 2.
Further, in the step 4, the operation data is counted and calculated to obtain a conditional probability relationship between the fault layer and the fault characteristic layer node, and the working condition data is counted and calculated to obtain a conditional probability relationship between the fault cause layer and the fault layer; and filling a Netica software conditional probability table, and uniformly setting the prior probability of the fault reason node.
Further, in the step 5, the actual operation data and the working condition data of the drilling motor are obtained, the state information is extracted, and the posterior probability of the fault node is updated according to the state information of the characteristic node and the reason node.
Further, in the step 5, a diagnosis rule is defined, whether the fault type is a single fault or a composite fault is determined according to a corresponding threshold value of the diagnosis rule where the maximum difference value between the posterior probability and the prior probability of the fault node is located, and whether the fault state is a fault early warning or a fault report is determined.
The technical scheme of the embodiment of the invention has the following advantages:
the components of the drilling motor have high coupling and correlation, and complex faults are easily caused. Different faults in the composite fault have similar fault characteristics, and the underground fault characteristics of the drilling motor are difficult to directly observe, so that the composite fault diagnosis is very difficult. A single data source has a good effect on single fault diagnosis, but misdiagnosis and missed diagnosis may occur when the method is applied to compound fault diagnosis. According to the invention, all available fault information in the drilling process is fused for fault diagnosis, and the drilling motor operation data is placed in specific working condition information for diagnosis, so that the fault characteristic discrimination is increased, and the identification effect of the composite fault is improved. The fault type can be judged to be single fault or composite fault, and the fault state can be judged to be fault early warning or fault report. The embodiment shows that the information fusion model improves the accuracy and robustness of the fault diagnosis result and corrects missed diagnosis and misdiagnosis results in the composite fault diagnosis.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart of a drilling motor composite fault diagnosis method according to an embodiment of the method of the present invention.
Fig. 2 is a bayesian network based on data fusion defined in an embodiment of the method of the present invention.
Fig. 3 is a bayesian network fault diagnosis model of the drilling motor in the method embodiment of the invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In describing the present invention, it is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and/or "comprising," when used in this specification, are intended to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," and the like are used in the orientation or positional relationship indicated in the drawings for convenience in describing the invention and for simplicity in description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be construed as limiting the invention. The terms "mounted," "connected," and "coupled" are to be construed broadly and may, for example, be fixedly coupled, detachably coupled, or integrally coupled; can be mechanically or electrically connected; the two elements can be directly connected, indirectly connected through an intermediate medium, or communicated with each other inside; either a wireless or a wired connection. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
According to the drilling motor composite fault diagnosis method provided by the invention, a Bayesian network based on operation data and a Bayesian network based on working condition data are combined, and a Bayesian network fault diagnosis model based on information fusion is established. The method places the operation data of the drilling motor in specific working conditions, increases the fault characteristic discrimination and improves the identification effect of the composite fault. The inventive concept is as follows:
and respectively defining a Bayesian network based on operation data and a Bayesian network based on working condition data, then defining a fault diagnosis Bayesian network based on information fusion by combining the two networks, and establishing a Bayesian network fault diagnosis model based on information fusion. And collecting fault characteristic signals and working condition signals, and inputting the fault characteristic signals and the working condition signals into a diagnosis model to update the posterior probability of the fault node. And judging fault early warning or fault generation according to a corresponding threshold value of a diagnosis rule where the maximum difference value of the posterior probability and the prior probability of the fault node is located. The invention uses the information fusion model to improve the accuracy and robustness of the fault diagnosis result and correct missed diagnosis and misdiagnosis results in the composite fault diagnosis.
The drilling motor composite fault diagnosis method provided by the embodiment is characterized by comprising the following steps as shown in fig. 1:
step 1: defining a Bayesian network for fault diagnosis based on operation data, and dividing the network into two layers: and the fault layer and the fault characteristic layer determine fault nodes and fault states of each layer.
Step 2: defining a Bayesian network for fault diagnosis based on working condition data, and dividing the network into two layers: and the fault layer and the fault reason layer determine fault nodes and fault states of each layer.
And step 3: and fusing the Bayesian networks defined in the step 1 and the step 2 to define a Bayesian network for fault diagnosis based on data fusion, wherein the nodes and node states of each layer are determined by the nodes and node states of each layer of the Bayesian network defined in the step 1 and the step 2.
And 4, step 4: and counting and calculating the operation data and the working condition data to obtain a conditional probability relation among the fault reason layer, the fault layer and the fault characteristic layer nodes, filling a conditional probability table and uniformly setting the prior probability of the fault reason nodes. And 3, establishing a Bayesian network model for fault diagnosis based on data fusion according to the definition in the step 3.
And 5: and acquiring actual operation data and working condition data of the drilling motor, extracting state information from the actual operation data and the working condition data, and updating the posterior probability of the fault node according to the node state. Judging whether the fault state is fault early warning or fault generation according to a corresponding threshold value of a diagnosis rule where the maximum difference value of the posterior probability and the prior probability of the fault node is located, if the maximum difference value is larger than 60%, generating a fault report, and if the maximum difference value is between 30% and 60%, making fault early warning; and judging whether the fault type is a single fault or a composite fault according to the number of the faults in the corresponding threshold value.
According to the method, the Bayesian network fault diagnosis model based on information fusion is established by using the operation data and the working condition data acquired from the well field data, and the drilling motor operation data is placed in specific working conditions, so that the fault characteristic discrimination is increased, and the identification effect of the compound fault is improved. The engineering example shows that the information fusion model improves the accuracy and robustness of the fault diagnosis result and corrects the missed diagnosis and misdiagnosis results in the composite fault diagnosis.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (6)
1. A drilling motor composite fault diagnosis method is characterized by comprising the following steps:
step 1: defining a Bayesian network for fault diagnosis based on the operation data;
step 2: defining a Bayesian network for fault diagnosis based on working condition data;
and step 3: defining a Bayesian network for fault diagnosis based on data fusion;
and 4, step 4: establishing a Bayesian network model for fault diagnosis based on data fusion;
and 5: and defining a fault diagnosis rule and judging the fault type and the fault state.
2. The drilling motor composite fault diagnosis method according to claim 1, wherein the step 1 of defining the bayesian network for fault diagnosis based on the operation data comprises the following specific steps:
the Bayesian network for fault diagnosis based on the operation data is divided into a fault layer and a fault characteristic layer. Each fault level node represents a potential fault of the drilling motor; each failure signature layer node represents a signature of a failure of the drilling motor. The two layers of nodes are connected through directed edges to form a topological structure, and the causal relationship between the fault and the characteristic is shown. Specifically, the fault layer node is: rotor eccentricity, bearing faults, turn-to-turn short circuit and uniform demagnetization represent four typical potential faults of a drilling motor; the node states for each fault are divided into two categories: presence and absence. The fault characteristic layer nodes are vibration signals, rotating speed signals, torque signals and current signals and represent well site big data of the operation of the drilling motor obtained through the sensor; the node states of each feature are divided into three types: normal, high, low.
3. The drilling motor composite fault diagnosis method according to claim 1, wherein the step 2 of defining the Bayesian network for fault diagnosis based on the working condition data comprises the following specific steps:
the Bayesian network for fault diagnosis based on the working condition data is divided into a fault layer and a fault cause layer. Each fault level node represents a potential fault of the drilling motor; each failure cause level node represents one extreme condition that may cause a drilling motor failure. The two layers of nodes are connected through directed edges to form a topological structure, and the cause and effect relationship between the fault reason and the fault is shown. The fault layer nodes and the node states are the same as those of the Bayesian network fault layer nodes and the node states in the step 1; the Bayesian network fault cause layer nodes for fault diagnosis based on the working condition data are drill tripping, stick slip and high temperature, and represent extreme working conditions possibly causing the fault of a drilling motor in the drilling process; the node states for each reason are divided into two types: presence and absence.
4. The drilling motor composite fault diagnosis method according to claim 1, wherein the step 3 of defining the bayesian network for fault diagnosis based on data fusion comprises the following specific steps:
and fusing the Bayesian networks defined in the step 1 and the step 2 to define a Bayesian network based on data fusion. The Bayesian network based on data fusion is divided into three layers, namely a fault reason layer, a fault layer and a fault characteristic layer. The fault cause layer node is an extreme factor which easily causes the fault of a drilling motor in the drilling working condition: jumping, stick-slip, high temperature; the node states of the fault cause layer are two types: presence, absence. The fault layer node is a common fault type of a drilling motor: rotor eccentricity, bearing failure, turn-to-turn short circuit and uniform demagnetization; the fault layer node states are two types: presence, absence. The fault characteristic layer nodes are vibration signals, rotating speed signals, torque signals and current signals which can be acquired by well site big data; the node states of the fault characteristic layer are three types: normal, high, low.
5. The drilling motor composite fault diagnosis method according to claim 1, wherein the step 4 of establishing the bayesian network model for fault diagnosis based on data fusion comprises the following specific steps:
and counting and calculating the operation data and the working condition data to obtain a conditional probability relation among the fault reason layer, the fault layer and the fault characteristic layer nodes, filling a conditional probability table and uniformly setting the prior probability of the fault reason nodes. And 3, establishing a Bayesian network model for fault diagnosis based on data fusion according to the definition in the step 3.
6. The drilling motor composite fault diagnosis method according to claim 1, wherein the step 5 defines a fault diagnosis rule, and the specific steps of distinguishing the fault type and the fault state are as follows:
and acquiring actual operation data and working condition data of the drilling motor, extracting state information from the actual operation data and the working condition data, and updating the posterior probability of the fault node according to the node state. Judging whether the fault state is fault early warning or fault generation according to a corresponding threshold value of a diagnosis rule where the maximum difference value of the posterior probability and the prior probability of the fault node is located, if the maximum difference value is larger than 60%, generating a fault report, and if the maximum difference value is between 30% and 60%, making fault early warning; and judging whether the fault type is a single fault or a composite fault according to the number of the faults in the corresponding threshold value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210040179.8A CN114386519A (en) | 2022-01-14 | 2022-01-14 | Drilling motor composite fault diagnosis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210040179.8A CN114386519A (en) | 2022-01-14 | 2022-01-14 | Drilling motor composite fault diagnosis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114386519A true CN114386519A (en) | 2022-04-22 |
Family
ID=81201564
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210040179.8A Pending CN114386519A (en) | 2022-01-14 | 2022-01-14 | Drilling motor composite fault diagnosis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114386519A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112145375A (en) * | 2020-09-28 | 2020-12-29 | 湘潭大学 | Fan variable pitch system fault diagnosis method based on Neo4j and Bayes |
CN113310171A (en) * | 2021-05-24 | 2021-08-27 | 浙江大学 | Central air-conditioning system fault detection and diagnosis method based on Bayesian network unit |
CN113761728A (en) * | 2021-08-24 | 2021-12-07 | 威海广泰空港设备股份有限公司 | Airport electric special vehicle fault early warning method based on Internet of vehicles platform |
-
2022
- 2022-01-14 CN CN202210040179.8A patent/CN114386519A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112145375A (en) * | 2020-09-28 | 2020-12-29 | 湘潭大学 | Fan variable pitch system fault diagnosis method based on Neo4j and Bayes |
CN113310171A (en) * | 2021-05-24 | 2021-08-27 | 浙江大学 | Central air-conditioning system fault detection and diagnosis method based on Bayesian network unit |
CN113761728A (en) * | 2021-08-24 | 2021-12-07 | 威海广泰空港设备股份有限公司 | Airport electric special vehicle fault early warning method based on Internet of vehicles platform |
Non-Patent Citations (3)
Title |
---|
XIAO WS等: "A Novel Support Vector Machine Based on Hybrid Bat Algorithm and Its Application to Identification of Low Velocity Impact Areas", 《IEEE ACCESS》, 28 April 2020 (2020-04-28) * |
张振海等: "基于关联规则的铁路信号设备故障诊断方法", 《铁道标准设计》, 22 July 2021 (2021-07-22) * |
李子恒: "高铁牵引系统复合故障智能诊断方法研究", 《中国知网硕士电子期刊》, 15 July 2021 (2021-07-15) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210226919A1 (en) | Information processing method, information processing system, and non-transitory computer-readable recording medium storing a program | |
CN105721230B (en) | Modbus protocol-oriented fuzz testing method | |
CN106130761A (en) | The recognition methods of the failed network device of data center and device | |
CN109733238B (en) | Fault detection method, device, storage medium and processor | |
WO2023138337A1 (en) | Motor fault detection method and apparatus | |
CN106249835A (en) | The method being applicable to power management, system, user terminal and device | |
CN108572308A (en) | fault diagnosis method and system | |
CN115278741A (en) | Fault diagnosis method and device based on multi-mode data dependency relationship | |
CN113361136B (en) | Diagnostic verification method for automatic manufacturing system based on Petri network | |
CN108228379A (en) | Log statistic method collects server, distributed server and summarizes server | |
CN114386519A (en) | Drilling motor composite fault diagnosis method | |
CN107222497A (en) | Network traffic anomaly monitor method and electronic equipment | |
CN113890567A (en) | HPLC networking program fault diagnosis method based on network maintenance iterative algorithm | |
US20220147034A1 (en) | Automated refinement of a labeled window of time series data | |
CN109946542B (en) | Inverter direct-current loop capacitance fault detection method based on long-time and short-time information fusion | |
CN116930750A (en) | Motor monitoring and diagnosing method and system based on decision tree model and electronic equipment | |
CN112578694A (en) | Monitoring system, method, apparatus and computer readable medium for an industrial controller | |
JP3711879B2 (en) | Network failure analysis apparatus and network failure analysis method | |
CN113487141B (en) | Bearing state evaluation method based on multisource information clustering fusion | |
CN111639141B (en) | Data testing method and device and computer terminal | |
CN112347317B (en) | Equipment fault diagnosis method based on particle swarm optimization improved negative selection algorithm | |
CN103063251B (en) | Failure recognition method based on engineering machinery | |
CN106706028B (en) | Method and system for detecting motor state | |
CN116708514B (en) | Electric energy meter data acquisition method and system based on Internet of things | |
CN108920356B (en) | Sensing node abnormity detection method based on task execution trajectory model |
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 |