CN115236453A - Fault early warning method based on oil field grid power equipment - Google Patents
Fault early warning method based on oil field grid power equipment Download PDFInfo
- Publication number
- CN115236453A CN115236453A CN202210811681.4A CN202210811681A CN115236453A CN 115236453 A CN115236453 A CN 115236453A CN 202210811681 A CN202210811681 A CN 202210811681A CN 115236453 A CN115236453 A CN 115236453A
- Authority
- CN
- China
- Prior art keywords
- fault
- early warning
- data
- oil field
- grid power
- 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
Images
Classifications
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a fault early warning method based on oil field grid power equipment, which comprises the steps of firstly, building a probability type data training algorithm suitable for oil field grid power based on the fault early warning requirement of the oil field grid power equipment; then importing historical fault data of the oil field grid power equipment into a probabilistic data training algorithm to generate a probabilistic fault prediction model; and finally, importing the real-time data of the oil field grid power equipment into a probability type fault prediction model, comparing, and predicting and early warning the fault. The invention provides a new idea for building a historical fault model on the basis of judging the original fault threshold, provides a more effective early warning mechanism aiming at the possibility of equipment fault occurrence, is superior to the existing method, and has the advantages of strong universality, convenient building and the like.
Description
Technical Field
The invention relates to the field of computer fault early warning methods, in particular to a fault early warning method for oil field grid power equipment.
Background
The equipment fault early warning technology has a gain effect on prolonging the service life of equipment in the use of the oil field grid power equipment, and can give an early warning to the bad state of the equipment before the fault occurs. The oil drilling site is usually in an outdoor rare place, at the present stage, the oil drilling usually adopts a grid power driving motor as main power driving equipment to extract oil, the grid power working condition of the site often faces the problems of long line stringing distance, unstable grid voltage, large load, large harmonic wave and the like, and the long-term operation under the working condition causes large load, easy failure and loss of the grid power equipment, so that the design of an efficient failure early warning method based on the oil field grid power equipment is very necessary and urgent.
The past prediction method only aiming at the data failure threshold value generally only aims at two types of data: firstly, protection and fault flag bits in the instrument are collected and judged in a switching value mode; second, the threshold value to the parameter such as the current, voltage, harmonic wave; the two methods have defects respectively, and aiming at the modes of protection and fault marking value, the method can only detect the occurrence of the fault generally and cannot predict the fault in advance; and the early warning mode aiming at the parameter threshold value, the early warning basis is usually calculated from the rated parameters of the equipment, but the working condition of the oil field grid power equipment is very complicated, the equipment loss is large, many equipment can not normally work in the designed rated interval after working for a period of time, and the mode of early warning through the parameter threshold value has certain limitation in the oil field grid power equipment.
Disclosure of Invention
The invention aims to provide a fault early warning method based on oil field grid power equipment aiming at the defects of the prior art.
The purpose of the invention is realized by the following technical scheme: a fault early warning method based on oil field grid power equipment comprises the following steps:
(1) Establishing a fault data training algorithm: establishing a probability type data training algorithm suitable for the oil field power grid based on the fault early warning requirement of the oil field power grid equipment;
(2) Training a fault early warning model: importing historical fault data of the oil field grid power equipment into the probabilistic data training algorithm built in the step (1) to generate a probabilistic fault prediction model;
(3) Fault early warning: and (3) importing the real-time data of the oil field grid power equipment into the probability type fault prediction model generated in the step (2), comparing, and predicting and early warning faults.
Further, the step (1) includes the sub-steps of:
(1.1) defining parameters: extracting a core data set G of fault prediction according to the fault early warning requirement of the oil field grid power equipment e Core data set G when failure occurs e The value of each element in (1) is defined as G en Defining the real-time data of each element as G rn Defining the safety interval of each element in the core data as G sn Defining the occurrence frequency of faults as N, and defining the value G of each element in core data in the N faults en Out of safety interval G s The number of n is defined as G bn Defining the early warning precision as um and defining the fault early warning triggering interval as G umn Defining the probability of each element in the model triggering the fault as G tn N is a sequence of 1, 2, 3, 4.. Times;
(1.2) obtaining the following algorithm of historical fault data through the parameters defined in the step (1.1): g bn Initial value of 0, when G en Over G sn When, G bn +1；G umn In the interval of G sn Upper and lower limits of (D) by um, G umn ＝G sn *um；G tn ＝G bn /N。
Further, the step (2) specifically comprises: counting the number of historical faults into N, wherein N is the number of element values G in core data en Out of safety range G sn Number of times G bn Zero clearing, as the historical data G of the core data en Out of safety interval G sn Time, number of times G bn +1; fault early warning trigger interval G umn Has a value of the safety interval G sn The upper and lower limits are obtained by multiplying the early warning precision um, and the fault occurrence probability G of each element tn Is given a value of G bn And dividing the number of times of the historical faults to obtain a fault early warning model generated according to the actually occurring historical faults.
Further, the step (3) is specifically: when G is tn When greater than um, G rn Exceeding G umn Namely triggering fault early warning; when G is tn < um or G tn When = umLet the cumulative parameter n =0, G rn Over G umn Time-of-flight accumulation, dividing the accumulated value n by G tn And obtaining m for the data times less than or equal to um, and triggering fault early warning if (m + 1)/2 is greater than 0.5.
The invention has the advantages that the fault early warning algorithm and the model of the oil field grid electric equipment are constructed, so that the oil field grid electric equipment can be effectively protected, the dangerous behavior of the equipment can be predicted in advance, and the service life of the equipment is prolonged. The method has the advantages of being superior to the existing method for predicting based on the fault threshold, and has the characteristics of strong universality, convenience in construction and the like.
Drawings
Fig. 1 is an algorithm block diagram of the fault early warning method based on the oilfield grid power equipment.
Detailed Description
The method analyzes the historical fault data of the oil field grid power equipment, builds a reasonable fault early warning model through a fault early warning algorithm, compares the real-time data of the oil field grid power equipment with the model, and gives fault early warning to the data which is not in compliance with the model.
The invention provides a fault early warning method based on oil field grid power equipment, which comprises the following steps:
1. establishing a fault data training algorithm: establishing a probability type data training algorithm suitable for oil field grid power based on the fault early warning requirement of the oil field grid power equipment; the method specifically comprises the following substeps:
1.1. extracting a core data set G of fault prediction according to the fault early warning requirement of the oil field grid power equipment e Core data set G when failure occurs e The value of each element in (1) is defined as G en (n is a sequence of 1.2.3.4.. Times.) the real-time data for each element is defined as G rn (n is the sequence of 1.2.3.4.. And G. en Corresponding to the sequence of (c) and defining the security interval of each element in the core data as G sn (n is the sequence of 1.2.3.4.. And G. en Corresponding to the sequence of (c) defining the number of times of occurrence of the fault as N, and defining the value of each element in the core data in N faults as G en Out of safety range G sn Is defined as G bn (n is a sequence of 1.2.3.4.. DegreeColumn, and G en Sequence of (c) defining early warning accuracy as um, defining interval triggered by fault early warning as G umn (n is the sequence of 1.2.3.4.. And G. en Corresponding to the sequence of (c), the probability of each element in the model triggering a failure is defined as G tn (n is the sequence of 1.2.3.4.. And G.) en Corresponds to (ii).
1.2. The following algorithm for obtaining historical fault data is obtained through the parameters defined in step 1.1): g bn Initial value is 0, when G en Exceeding G sn Time G bn +1；G umn In the interval of G sn Upper and lower limits of (D) multiplied by um, G umn ＝G sn *um；G tn ＝G bn /N。
2. Training a fault early warning model: and (3) importing historical fault data of the oilfield grid power equipment into the fault data training algorithm in the step 1 to generate a probability type fault prediction model.
Counting the number of historical faults into N, wherein N is the value G of each element in core data in the faults en Out of safety range G sn Number of times G bn Zero clearing, as the historical data G of the core data en Out of safety range G sn Time, number of times G bn +1; fault early warning trigger interval G umn Is a safety interval G sn The upper limit and the lower limit are obtained by multiplying the early warning precision um, and the fault occurrence probability G of each element tn Is given a value of G bn And dividing the number of times of the historical faults by the number of times of the historical faults to obtain a fault early warning model generated according to the actually occurring historical faults.
3. Fault early warning: the fault early warning is verified by implementing data, and the real-time data of the oil field grid power equipment is imported into the step 2 and is subjected to historical fault data G en In the generated fault model, comparison is carried out, and prediction and early warning are carried out on the fault: when real-time data G rn Out of safety range G sn Triggering fault early warning; when G is tn When greater than um, if G rn Exceeding G umn Triggering fault early warning; when G is tn And accumulating when the sum is less than um, dividing the accumulated value by the accumulated times to obtain m, and triggering fault early warning if (m + 1)/2 is more than 0.5.
Compared with the conventional prediction method only aiming at the data fault threshold, the fault early warning algorithm based on the oilfield grid power equipment has higher prediction precision and can protect the oilfield grid power equipment more effectively. However, the prediction algorithm has the problem that the probability of triggering faults in the model is smaller than the element of prediction accuracy, and the actual prediction cannot be accurately measured, so that only a fuzzy algorithm can be adopted, the false triggering probability is reduced as much as possible, and the prediction accuracy is improved.
Examples of the embodiments
An embodiment of the invention is implemented on a machine equipped with an Intel Core i7-3770 central processing unit, an NVidia GTX760 graphics processor, and 32GB memory. According to the algorithm shown in fig. 1, a computer program is written, a fault prediction model is obtained by using historical fault data, real-time data of equipment is brought into the fault model for comparison, and a fault is triggered when the fault early warning precision is reached. Compared with the existing method, the method can more accurately predict the fault of the equipment, and can send out early warning when the fault occurs, thereby greatly reducing the fault rate of the equipment and prolonging the service life of the equipment.
Claims (4)
1. A fault early warning method based on oil field network electric equipment is characterized by comprising the following steps:
(1) Establishing a fault data training algorithm: establishing a probability type data training algorithm suitable for oil field grid power based on the fault early warning requirement of the oil field grid power equipment;
(2) Training a fault early warning model: importing historical fault data of the oil field grid power equipment into the probabilistic data training algorithm built in the step (1) to generate a probabilistic fault prediction model;
(3) Fault early warning: and (3) importing the real-time data of the oil field grid power equipment into the probability type fault prediction model generated in the step (2), comparing, and predicting and early warning faults.
2. The method according to claim 1, characterized in that said step (1) comprises the following sub-steps:
(1.1) defining parameters: according to oil field net electric installationThe fault early warning requirement of (2) is that a core data set G for fault prediction is extracted e Core data set G when failure occurs e The value of each element in (1) is defined as G en Defining the real-time data of each element as G rn Defining the safety interval of each element in the core data as G sn Defining the occurrence frequency of faults as N, and defining the value G of each element in core data in the N faults en Out of safety interval G sn Is defined as G bn Defining the early warning precision as um and defining the fault early warning triggering interval as G umn Defining the probability of each element in the model triggering the fault as G tn N is a sequence of 1, 2, 3, 4.. Times;
(1.2) obtaining the following algorithm of historical fault data through the parameters defined in the step (1.1): g bn Initial value is 0, when G en Over G sn When, G bn +1；G umn Interval of G sn Upper and lower limits of (D) by um, G umn ＝G sn *um；G tn ＝G bn /N。
3. The method according to claim 1, wherein the step (2) is specifically: counting the number of historical faults into N, wherein N is the number of element values G in core data en Out of safety interval G sn Number of times G bn Zero clearing, as the historical data G of the core data en Out of safety interval G sn Time, number of times G bn +1; fault early warning trigger interval G umn Has a value of the safety interval G sn The upper and lower limits are obtained by multiplying the early warning precision um, and the fault occurrence probability G of each element tn Is given a value of G bn And dividing the number of times of the historical faults to obtain a fault early warning model generated according to the actually occurring historical faults.
4. The method according to claim 1, wherein the step (3) is specifically: when G is tn When greater than um, G rn Over G umn Namely triggering fault early warning; when G is tn < um or G tn If = um, the accumulation parameter n =0 is set rn Over G umn Time-of-flight accumulation, dividing the accumulated value n by G tn And obtaining m for the data times less than um, and triggering fault early warning if (m + 1)/2 is greater than 0.5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210811681.4A CN115236453A (en) | 2022-07-11 | 2022-07-11 | Fault early warning method based on oil field grid power equipment |
| PCT/CN2022/118701 WO2024011745A1 (en) | 2022-07-11 | 2022-09-14 | Fault warning method based on oil field grid power device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210811681.4A CN115236453A (en) | 2022-07-11 | 2022-07-11 | Fault early warning method based on oil field grid power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115236453A true CN115236453A (en) | 2022-10-25 |
Family
ID=83670706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210811681.4A Pending CN115236453A (en) | 2022-07-11 | 2022-07-11 | Fault early warning method based on oil field grid power equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115236453A (en) |
| WO (1) | WO2024011745A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11955782B1 (en) | 2022-11-01 | 2024-04-09 | Typhon Technology Solutions (U.S.), Llc | System and method for fracturing of underground formations using electric grid power |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714401A (en) * | 2014-01-21 | 2014-04-09 | 国家电网公司 | Method for predicting distribution and transformation fault frequency of electric network |
| US11226856B2 (en) * | 2015-04-24 | 2022-01-18 | Senslytics Corporation | Methods and systems correlating hypotheses outcomes using relevance scoring for intuition based forewarning |
| CN112257988A (en) * | 2020-09-29 | 2021-01-22 | 中广核工程有限公司 | Complex accident feature identification and risk early warning system and method for nuclear power plant |
| CN112836436A (en) * | 2021-03-01 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Power distribution network line risk quantitative prediction method based on probability graph model |
| CN114444714A (en) * | 2021-12-31 | 2022-05-06 | 上海恕笃智能科技有限公司 | Power plant equipment real-time fault early warning method based on rapid autonomous learning |
-
2022
- 2022-07-11 CN CN202210811681.4A patent/CN115236453A/en active Pending
- 2022-09-14 WO PCT/CN2022/118701 patent/WO2024011745A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11955782B1 (en) | 2022-11-01 | 2024-04-09 | Typhon Technology Solutions (U.S.), Llc | System and method for fracturing of underground formations using electric grid power |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024011745A1 (en) | 2024-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110596486B (en) | Intelligent early warning operation and maintenance method and system for charging pile | |
| US8682612B2 (en) | Trend analysis methods and system for incipient fault prediction | |
| US20210278464A1 (en) | Condition assessment method and device for an outdoor post-mounted vacuum switch | |
| CN115236453A (en) | Fault early warning method based on oil field grid power equipment | |
| CN108680798B (en) | Lightning monitoring and early warning method and system | |
| CN102915515A (en) | Cascade outage recognition and risk evaluation method of power grid | |
| CN106199251B (en) | A kind of distribution network failure early warning system and method based on adaptive modeling analysis | |
| KR101099788B1 (en) | Apparatus and method of determinating lightening induced flashover in transmission lines | |
| CN117590148A (en) | Power grid line fault diagnosis method and system based on big data | |
| CN116070794B (en) | Current collecting line impact trip probability prediction and alarm method and system | |
| CN101988940A (en) | Three-dimensional evaluation method for lightning protection performance of power transmission lines based on lightning strike density statistics | |
| CN113589098A (en) | Power grid fault prediction and diagnosis method based on big data drive | |
| CN114465217B (en) | Lightning protection method and device based on high-frequency isolation | |
| CN107832943A (en) | A kind of power system mobile terminal safety intimidation estimating method | |
| CN115275946A (en) | Distribution line-oriented lightning trip probability analysis method and system | |
| US20220200281A1 (en) | Systems and methods for evaluating electrical phasors to identify, assess, and mitigate power quality issues | |
| CN113783174B (en) | Lightning protection and abnormal power transmission line protection method and system | |
| JP2007020341A (en) | Insulator damage determination device and program | |
| CN109742845B (en) | Rapid switching-on method of power supply rapid switching-off device based on optimal phase | |
| CN103852659A (en) | Novel SPD on-line detection device | |
| CN117878836B (en) | Active protection method and protection device for transformer based on pulse current signal characteristics | |
| CN110988453B (en) | Method for judging small current variable by apparent power | |
| CN111313355A (en) | Method for updating monitoring signal event rule under manual supervision | |
| CN105117865B (en) | A kind of power transmission line inspection strategy process based on lightning fault insulation recovery characteristic | |
| CN110988454B (en) | Method for monitoring small current by apparent power and real-time disposal |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230327 Address after: Room 2155, Building 3, Huayuan Village, No. 203 Zhenzhong Road, Xihu District, Hangzhou City, Zhejiang Province, 310000 Applicant after: Hangzhou Ruiwangyuan Technology Co.,Ltd. Address before: 214500 Suyuan Thermal Circuit, Jingjiang Development Zone, Taizhou City, Jiangsu Province (formerly Qianjin Village Industrial Park Phase I) Applicant before: JIANGSU CHENWU ENERGY-SAVING TECHNOLOGY CO.,LTD. |