CN109635873A - A kind of UPS failure prediction method - Google Patents
A kind of UPS failure prediction method Download PDFInfo
- Publication number
- CN109635873A CN109635873A CN201811551808.3A CN201811551808A CN109635873A CN 109635873 A CN109635873 A CN 109635873A CN 201811551808 A CN201811551808 A CN 201811551808A CN 109635873 A CN109635873 A CN 109635873A
- Authority
- CN
- China
- Prior art keywords
- ups
- random forest
- forest model
- decision tree
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000007637 random forest analysis Methods 0.000 claims abstract description 31
- 238000003066 decision tree Methods 0.000 claims abstract description 29
- 239000012535 impurity Substances 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 3
- 230000002441 reversible effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Abstract
The invention discloses a kind of UPS failure prediction methods, comprising the following steps: building tranining database, the tranining database includes multiple training samples;Random Forest model is constructed and initializes, the Random Forest model includes multiple decision trees;Multiple training samples are input in Random Forest model, the training operation of decision-tree model is completed;The real-time status parameter of UPS is acquired, sample to be tested is formed;The sample to be tested is input in Random Forest model, the failure predication result of the Random Forest model output UPS.The technical program completes the training operation of Random Forest model first, by the real-time working parameter for acquiring UPS, it is handled using real-time working parameter of the Random Forest model to UPS to realize the function of being predicted UPS incipient fault, intervene convenient for operation conditions of the relevant staff to UPS, the probability that UPS breaks down is effectively reduced.
Description
Technical field
The present invention relates to equipment fault prediction technique technical fields, more specifically to a kind of UPS (uninterruptible power supply)
Failure prediction method.
Background technique
Be equipped with UPS (uninterruptible power supply) in numerous machinery equipment at present, to prevent since alternating current is unstable or
The reasons such as commercial power interruption cause machinery equipment out of service, influence related work progress.
The working principle of existing on-line blackbody cavity is as follows, the reversible transducer work when alternating current is normal, in UPS
It in rectification state, charges to battery, alternating current is directly powered to the load by the intelligent voltage regulator of UPS, double when city's electrical anomaly
It works to converter in inverter mode, battery is powered by reversible transducer to load.
It can be seen that existing UPS from the working principle of UPS above and be each equipped with the corresponding corresponding electricity of sensor detection
Current voltage signal, then signal transmission is carried out by network communication equipment, although energy real-time monitoring and control, but can not be to UPS
Potential failure predicted, UPS in the process of running once break down, by for electric loading operation cause it is serious
Adverse effect.
Summary of the invention
The technical problem to be solved by the present invention is providing a kind of UPS failure prediction method based on random forest.
The solution that the present invention solves its technical problem is:
A kind of UPS failure prediction method, comprising the following steps:
Step 100, tranining database is constructed, the tranining database includes multiple training samples;
Step 200, Random Forest model is constructed and initializes, the Random Forest model includes multiple decision trees;
Step 300, multiple training samples are input in Random Forest model, complete the training behaviour of decision-tree model
Make;
Step 400, the real-time status parameter of UPS is acquired, sample to be tested is formed;
Step 500, the sample to be tested is input in Random Forest model, the Random Forest model output UPS's
Failure predication result.
As a further improvement of the above technical scheme, the training sample includes state parameter and faulty tag, institute
State state parameter and real-time status parameter include line voltage, mains frequency, reversible transducer state, UPS output voltage,
UPS exports electric current, UPS humidity, UPS temperature, UPS noise and accumulator electric-quantity.
As a further improvement of the above technical scheme, step 300 the following steps are included:
Step 310, by the training sample state parameter and faulty tag standardize;
Step 320, m characteristic variable is extracted in a random way from a training sample;
Step 330, it at the type node of decision tree, is selected from m characteristic variable according to Geordie impurity level minimum principle
The feature x for taking a classifying quality besti, which is divided into Liang Ge branch, the Geordie impurity level principle isWherein P (i) indicates the ratio of the total class number of every one kind Zhan;
Step 340, it repeats the above steps operation shown in 330 to each type node of decision tree, until the decision
Tree the Geordie impurity level of each type node can reach minimum in Accurate classification training sample or decision tree;
Step 350, next training sample is chosen, repeats step 320 to step 340, until all extraction training samples
Corresponding decision tree building finishes;
Step 360, cut operator is carried out to all decision trees;
Step 370, the constructed decision tree come out of all training samples collectively constitutes Random Forest model, described random gloomy
Woods model construction finishes.
As a further improvement of the above technical scheme, the UPS temperature includes transformer temperature value, transformer temperature value
Change rate, switching tube temperature value and switching tube temperature value change rate.
The beneficial effects of the present invention are: the present invention completes the training operation of Random Forest model first, pass through acquisition UPS's
Real-time working parameter, using real-time working parameter of the Random Forest model to UPS handled with realize to UPS incipient fault into
Row prediction function, intervene convenient for operation conditions of the relevant staff to UPS, be effectively reduced UPS break down it is general
Rate.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described.Obviously, described attached drawing is a part of the embodiments of the present invention, rather than is all implemented
Example, those skilled in the art without creative efforts, can also be obtained according to these attached drawings other designs
Scheme and attached drawing.
Fig. 1 is flow chart of the method for the present invention.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to design of the invention, specific structure and generation clear
Chu, complete description, to be completely understood by the purpose of the present invention, feature and effect.Obviously, described embodiment is this Shen
A part of the embodiment please, rather than whole embodiments, are based on embodiments herein, and those skilled in the art is not paying
Other embodiments obtained under the premise of creative work belong to the range of the application protection.
Referring to Fig.1, the technical program discloses a kind of UPS failure prediction method, comprising the following steps:
Step 100, tranining database is constructed, the tranining database includes multiple training samples;
Step 200, Random Forest model is constructed and initializes, the Random Forest model includes multiple decision trees;
Step 300, multiple training samples are input in Random Forest model, complete the training behaviour of decision-tree model
Make;
Step 400, the real-time status parameter of UPS is acquired, sample to be tested is formed;
Step 500, the sample to be tested is input in Random Forest model, the Random Forest model output UPS's
Failure predication result.
Specifically, the technical program completes the training operation of Random Forest model first, by the real-time working for acquiring UPS
Parameter is handled using real-time working parameter of the Random Forest model to UPS to realize and be predicted UPS incipient fault
Function is intervened convenient for operation conditions of the relevant staff to UPS, and the probability that UPS breaks down is effectively reduced.
It is further used as preferred embodiment, in the application specific embodiment, the training sample includes state ginseng
Several and faulty tag, the state parameter and real-time status parameter include line voltage, mains frequency, reversible transducer
State, UPS output voltage, UPS output electric current, UPS humidity, UPS temperature, UPS noise and accumulator electric-quantity.
Be further used as preferred embodiment, in the application specific embodiment, step 300 the following steps are included:
Step 310, by the training sample state parameter and faulty tag standardize;
Step 320, m characteristic variable is extracted in a random way from a training sample;
Step 330, it at the type node of decision tree, is selected from m characteristic variable according to Geordie impurity level minimum principle
The feature x for taking a classifying quality besti, which is divided into Liang Ge branch, the Geordie impurity level principle isWherein P (i) indicates the ratio of the total class number of every one kind Zhan;
Step 340, it repeats the above steps operation shown in 330 to each type node of decision tree, until the decision
Tree the Geordie impurity level of each type node can reach minimum in Accurate classification training sample or decision tree;
Step 350, next training sample is chosen, repeats step 320 to step 340, until all extraction training samples
Corresponding decision tree building finishes;
Step 360, cut operator is carried out to all decision trees;
Step 370, the constructed decision tree come out of all training samples collectively constitutes Random Forest model, described random gloomy
Woods model construction finishes.
It is further used as preferred embodiment, in the application specific embodiment, the UPS temperature includes transformer temperature
Angle value, transformer temperature value change rate, switching tube temperature value and switching tube temperature value change rate.It is random gloomy to further increase
Accuracy of the woods model to UPS failure predication needs to detect transformer temperature value, transformer temperature value simultaneously in the technical program
Change rate, switching tube temperature value and switching tube temperature value change rate.Specifically, in practical application, staff can draw UPS
Operating status, draw out transformer temperature and time homologous thread and switching tube temperature and time it is corresponding bent
Line can calculate transformer temperature value change rate and switching tube temperature value change rate by this two curves.
The better embodiment of the application is illustrated above, but the application is not limited to the specific embodiments,
Those skilled in the art can also make various equivalent modifications or replacement on the premise of without prejudice to spirit of the invention, this
Equivalent variation or replacement are all included in the scope defined by the claims of the present application a bit.
Claims (4)
1. a kind of UPS failure prediction method, which comprises the following steps:
Step 100, tranining database is constructed, the tranining database includes multiple training samples;
Step 200, Random Forest model is constructed and initializes, the Random Forest model includes multiple decision trees;
Step 300, multiple training samples are input in Random Forest model, complete the training operation of decision-tree model;
Step 400, the real-time status parameter of UPS is acquired, sample to be tested is formed;
Step 500, the sample to be tested is input in Random Forest model, the failure of the Random Forest model output UPS
Prediction result.
2. a kind of UPS failure prediction method according to claim 1, it is characterised in that: the training sample includes state
Parameter and faulty tag, the state parameter and real-time status parameter include line voltage, mains frequency, two-way changing
Device state, UPS output voltage, UPS output electric current, UPS humidity, UPS temperature, UPS noise and accumulator electric-quantity.
3. a kind of UPS failure prediction method according to claim 2, it is characterised in that: step 300 the following steps are included:
Step 310, by the training sample state parameter and faulty tag standardize;
Step 320, m characteristic variable is extracted in a random way from a training sample;
Step 330, at the type node of decision tree, one is chosen from m characteristic variable according to Geordie impurity level minimum principle
The best feature x of a classifying qualityi, which is divided into Liang Ge branch, the Geordie impurity level principle isWherein P (i) indicates the ratio of the total class number of every one kind Zhan;
Step 340, it repeats the above steps operation shown in 330 to each type node of decision tree, until the decision tree energy
The Geordie impurity level of each type node reaches minimum in enough Accurate classification training samples or decision tree;
Step 350, next training sample is chosen, repeats step 320 to step 340, until all extraction training sample institutes are right
The decision tree building answered finishes;
Step 360, cut operator is carried out to all decision trees;
Step 370, the constructed decision tree come out of all training samples collectively constitutes Random Forest model, the random forest mould
Type building finishes.
4. a kind of UPS failure prediction method according to claim 3, it is characterised in that: the UPS temperature includes transformer
Temperature value, transformer temperature value change rate, switching tube temperature value and switching tube temperature value change rate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811551808.3A CN109635873A (en) | 2018-12-19 | 2018-12-19 | A kind of UPS failure prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811551808.3A CN109635873A (en) | 2018-12-19 | 2018-12-19 | A kind of UPS failure prediction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109635873A true CN109635873A (en) | 2019-04-16 |
Family
ID=66075300
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811551808.3A Pending CN109635873A (en) | 2018-12-19 | 2018-12-19 | A kind of UPS failure prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109635873A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110345463A (en) * | 2019-06-24 | 2019-10-18 | 佛山科学技术学院 | A kind of boiler incipient fault recognition methods and device |
CN110988563A (en) * | 2019-12-23 | 2020-04-10 | 厦门理工学院 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
CN111506093A (en) * | 2020-04-09 | 2020-08-07 | 陕西省地方电力(集团)有限公司延安供电分公司 | Unmanned aerial vehicle-based power inspection system and method |
CN112995155A (en) * | 2021-02-09 | 2021-06-18 | 中国工商银行股份有限公司 | Financial abnormal message identification method and device |
CN113495607A (en) * | 2020-03-18 | 2021-10-12 | 台达电子企业管理(上海)有限公司 | Fault diagnosis method and system for high-voltage generator |
CN113809786A (en) * | 2020-07-23 | 2021-12-17 | 广东毓秀科技有限公司 | Method for predicting faults of UPS rectification and inversion module through big data |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103257921A (en) * | 2013-04-16 | 2013-08-21 | 西安电子科技大学 | Improved random forest algorithm based system and method for software fault prediction |
CN107977626A (en) * | 2017-11-30 | 2018-05-01 | 厦门理工学院 | The group technology of a kind of electronic equipment operational data |
CN108009582A (en) * | 2017-11-30 | 2018-05-08 | 厦门理工学院 | The method that a kind of electronic equipment standard working index is set |
CN108303632A (en) * | 2017-12-14 | 2018-07-20 | 佛山科学技术学院 | Circuit failure diagnosis method based on random forests algorithm |
-
2018
- 2018-12-19 CN CN201811551808.3A patent/CN109635873A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103257921A (en) * | 2013-04-16 | 2013-08-21 | 西安电子科技大学 | Improved random forest algorithm based system and method for software fault prediction |
CN107977626A (en) * | 2017-11-30 | 2018-05-01 | 厦门理工学院 | The group technology of a kind of electronic equipment operational data |
CN108009582A (en) * | 2017-11-30 | 2018-05-08 | 厦门理工学院 | The method that a kind of electronic equipment standard working index is set |
CN108303632A (en) * | 2017-12-14 | 2018-07-20 | 佛山科学技术学院 | Circuit failure diagnosis method based on random forests algorithm |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110345463A (en) * | 2019-06-24 | 2019-10-18 | 佛山科学技术学院 | A kind of boiler incipient fault recognition methods and device |
CN110988563A (en) * | 2019-12-23 | 2020-04-10 | 厦门理工学院 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
CN110988563B (en) * | 2019-12-23 | 2022-04-01 | 厦门理工学院 | UPS (uninterrupted Power supply) fault detection method, device, equipment and storage medium |
CN113495607A (en) * | 2020-03-18 | 2021-10-12 | 台达电子企业管理(上海)有限公司 | Fault diagnosis method and system for high-voltage generator |
US11852686B2 (en) | 2020-03-18 | 2023-12-26 | Delta Electronics (Shanghai) Co., Ltd. | Fault diagnosis method and system for high-voltage generator |
CN111506093A (en) * | 2020-04-09 | 2020-08-07 | 陕西省地方电力(集团)有限公司延安供电分公司 | Unmanned aerial vehicle-based power inspection system and method |
CN113809786A (en) * | 2020-07-23 | 2021-12-17 | 广东毓秀科技有限公司 | Method for predicting faults of UPS rectification and inversion module through big data |
CN112995155A (en) * | 2021-02-09 | 2021-06-18 | 中国工商银行股份有限公司 | Financial abnormal message identification method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109635873A (en) | A kind of UPS failure prediction method | |
CN104617330B (en) | Recognition method of micro-short circuiting of batteries | |
CN105548949B (en) | The fault remote determination methods of a kind of intelligent electric energy meter and system thereof | |
CN104020754A (en) | Method for enabling state monitoring information of transformer station primary main equipment to access to regulation and control system | |
US11953870B2 (en) | System and method for controlling solar photovoltaic power generation on basis of machine learning | |
CN108764684A (en) | Intelligent box substation health state evaluation method based on Fuzzy AHP | |
CN105093047B (en) | Power circuit load monitoring early warning system | |
US11870264B2 (en) | System and method for controlling photovoltaic balancing | |
US20160061881A1 (en) | Smart Junction Box for Photovoltaic Systems | |
CN110727257A (en) | Equipment operation diagnosis method and device based on K-means clustering algorithm | |
CN116080456A (en) | Portable electric pile that fills based on thing networking control and energy storage charge supervisory systems thereof | |
CN108005893A (en) | A kind of energy-saving air compressor machine analysis and diagnosis system and its control method | |
CN115201616A (en) | Charger operation online monitoring method based on big data | |
CN104779913B (en) | Method and system for monitoring working state of solar photovoltaic power station | |
CN104834305A (en) | Distribution network automated terminal telemetering abnormity analyzing system and method based on DMS system | |
CN108446202B (en) | Method for judging safety condition of machine room equipment | |
CN113379005A (en) | Intelligent energy management system and method for power grid power equipment | |
CN109948738A (en) | Energy consumption method for detecting abnormality, the apparatus and system of coating drying room | |
CN110108983B (en) | Intelligent cable state online measurement and control management method | |
CN115825756B (en) | Multi-stage fault diagnosis method and system for distributed energy storage power station | |
CN108802565B (en) | Medium-voltage power distribution network disconnection ungrounded fault detection method based on machine learning | |
CN208334607U (en) | A kind of street lamp fault diagnostic circuit | |
CN106251002A (en) | Association analysis method for the meteorological big data of overhead transmission line load-bearing capacity assessment | |
CN116151099A (en) | Low-voltage distribution network load state estimation terminal | |
CN108828469A (en) | A kind of street lamp fault diagnostic circuit and its diagnostic method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |