CN108304941A - A kind of failure prediction method based on machine learning - Google Patents
A kind of failure prediction method based on machine learning Download PDFInfo
- Publication number
- CN108304941A CN108304941A CN201711362861.4A CN201711362861A CN108304941A CN 108304941 A CN108304941 A CN 108304941A CN 201711362861 A CN201711362861 A CN 201711362861A CN 108304941 A CN108304941 A CN 108304941A
- Authority
- CN
- China
- Prior art keywords
- data
- feature
- failure
- character subset
- predicted
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Abstract
The invention discloses a kind of failure prediction methods based on machine learning.This method is：1) the setting operating index data for acquiring object to be predicted obtain the time series data of each setting operating index；Acquire the historical failure data of the object to be predicted；2) feature extraction is carried out respectively to the data of step 1) acquisition, the feature of extraction is input in machine learning system and is trained, obtain a basic failure predication model；3) real time data for collecting the setting operating index when object operation to be predicted, carries out feature extraction to it and inputs the basis failure predication model, predicts that the object to be predicted currently whether there is failure.The present invention improves equipment safety operation efficiency, shortens maintenance time, reduces maintenance cost, extends service life of equipment, the influence generated due to certain device fails is reduced or avoided.
Description
Technical field
The invention belongs to artificial intelligence machine learning areas, are related to a kind of maintaining method, are specially related to a kind of based on machine
The failure prediction method of device study.
Background technology
Currently, in people's actual life, for system and machine dependence out of the imagination of people.Go off daily is wanted
It drives, take elevator, taking high ferro or aircraft etc., also in enterprise's manufacture production, machine has liberated labourer, but these
Machine or system can break down, some failures are only made troubles, and some failures are then of vital importance.
When risk is very high, need routinely to safeguard system.Because the cost of failure will be far above surface
On cost.For example, high ferro customary detection daily, automobile is primary every maintenance some months, and then maintenance is primary daily for aircraft, so side
Rule is to lead to the serious waste of resource, is formed excessively, or even superfluous maintenance.
Predictive maintenance can predict failure, take action in advance, or even when precognition will appear failure, can greatly save
Expense brings high predictability and enhances the availability of system.Predictive maintenance avoids two kinds extremely simultaneously, maximumlly
Utilize resource.It will detect exception and fault mode, early provide warning information, avoid or minimize the downtime,
The attended operation of optimization cycle, to greatly improve maintenance efficiency and benefit.
Invention content
In order to improve equipment safety operation efficiency, shortening maintenance time reduces maintenance cost, extends service life of equipment,
The influence generated due to certain device fails is reduced or avoided, in a certain range the plan of reasonable arrangement maintenance time,
Loss reaches bottom line caused by reduce shutdown, and the present invention provides a kind of failure prediction method based on machine learning.
The technical scheme is that：
A kind of failure prediction method based on machine learning, step include：
1) the setting operating index data for acquiring object to be predicted obtain the time series number of each setting operating index
According to；Acquire the historical failure data of the object to be predicted；
2) feature extraction is carried out respectively to the data of step 1) acquisition, the feature of extraction is input in machine learning system
It is trained, obtains a basic failure predication model；
3) real time data for collecting setting operating index when object to be predicted operation carries out it feature extraction and defeated
Enter the basis failure predication model, predicts that the object to be predicted currently whether there is failure.
Further, machine learning system carries out denoising, Feature Engineering successively to input feature vector, and training obtains a basis event
Hinder prediction model and hyperparameter optimization is carried out to the basis failure predication model.
Further, the processing method of the Feature Engineering is：For each time series data, the time series is calculated
The sliding window variance of data, using multiple sliding window variances of the time series data as a character subset；Then right
Each character subset carries out k- mean clusters, is most there is the character subset of predictive ability；Calculate the sliding window of historical failure data
Mouth variance, obtains the corresponding character subset of historical failure data.
Further, the method for calculating the sliding window variance：For a time series data { x (t) }, setting one is wide
Degree is the diagnostic window of h, i.e., includes the h data by acquisition order arrangement in the diagnostic window, number when diagnostic window moment k
It is according to sequence:{xk}={ x (k-j) } (j=h-1, h-2 ..., 1,0), corresponding sliding window variance It is sequence { xkSample average, nqFor the diagnosis at k moment
Singular point number in window.
Further, k- mean clusters are carried out to each character subset, is most there is the method for the character subset of predictive ability
For：For each character subset, 1) k object is chosen from this feature subset data space as initial cluster center；2) it counts
The Euclidean distance of the data object and each cluster centre in this feature subset is calculated, pressing will be in this feature subset apart from nearest criterion
Data object assign to the class corresponding to the cluster centre away from nearest neighbours；3) cluster centre is updated：To own in each classification
Cluster centre of the mean value as the category corresponding to object, the value of calculating target function；4) judge cluster centre and target letter
Whether several values changes, if constant, if output is as a result, 2) change, returns；Repeatedly until obtaining this feature
Collect the corresponding character subset for most having predictive ability.
Further, using most there is the character subset of predictive ability to train to obtain the basic failure predication model, and it is right
It carries out hyperparameter optimization processing；The basic failure predication model row is commented using the corresponding character subset of historical failure data
Estimate verification, if the conclusion obtained is matched with known fault, confirms the availability of the basic failure predication model, it is otherwise right
The basis failure predication model is modified.
Further, the hyper parameter of optimization includes：Iterations, distribution, activation primitive and hidden layer number.
Further, denoising is carried out successively to the feature of extraction using neural network Auto-Encoder.
Further, the feature of extraction includes the mean value of data, sliding window variance, root mean square, peak factor, kurtosis system
Number and shape factor.
Further, the setting operating index includes device temperature, heat, rotary speed, displacement, procedure parameter and vibration
Amount.
The beneficial effects of the invention are as follows：
Present invention is primarily intended to the times that pre- measurement equipment may break down, and then take relevant action to prevent these
Failure has preferable economic and social benefit for monitoring following failure and schedule ahead maintenance time.It can not only reduce
Cost, moreover it is possible to reach following effect：
1. reducing frequency of maintenance.
2. the time in the equipment that some is maintained is spent in reduction, efficiency is improved.
3. reducing maintenance cost.
Description of the drawings
Fig. 1 is flow chart of the method for the present invention.
Specific implementation mode
For the ease of those skilled in the art understand that the present invention technology contents, below in conjunction with the accompanying drawings to the content of present invention into
One step is illustrated.
It is basic that data are that machine learning solves the problems, such as, data selection is not right, then problem can not possibly be solved.First, number
According to being divided into two parts, a part is mainly the basic fundamental parameter of equipment, operating index data and passing breaks down
Primary data, design parameter are related to device temperature, heat, rotary speed, displacement, procedure parameter and vibratory output etc..Another part is to set
The time series data of the above-mentioned parameter of received shipment row, this kind of data are installed additional in required prediction object (such as equipment or system)
Above-mentioned two parts data are carried out feature extraction (mean value, side by sensor successively to collect the real time data of prediction object operation
Difference, root mean square, peak factor, kurtosis coefficient and shape factor), data cleansing and standardized pretreatment, later by formation
Data set is input in machine learning system, is passed through denoising, Feature Engineering successively and the step of hyperparameter optimization, is pushed away by intelligence
Adjustment method builds basic failure predication model first using supervision and unsupervised algorithm, further excellent using nitrification enhancement
Change model.Again by existing fault sample, assessment verification is carried out to prediction model, if the conclusion obtained and known fault
Match, then confirm the availability of model, if the conclusion obtained has deviation, prediction model is modified, if prediction conclusion goes out
It is exactly so-called poor fitting when existing high deviation, by increasing the number of input feature vector, turning down training pace, increase decision tree
The parameters such as number and depth, at this moment by increasing input data amount, besides pass through regularization if instead then there is over-fitting
Method makes Partial Feature weight become smaller or weight is 0, reduction model complexity.
Fig. 1 is the system frame structure figure of the present invention.It below will be with reference to the accompanying drawings and in conjunction with actual conditions, this is described in detail
Invention.The training of predictive maintenance data as shown in Figure 1 and appraisal framework figure.
First, initial data is subjected to denoising, feature work successively by being input in machine learning system after pretreatment
The processing of journey and hyperparameter optimization.Noise is removed with simple neural network Auto-Encoder, it is with the same data set
Carry out training pattern as outputting and inputting for network, the number of parameters of network is less than the dimension of data set.This and principal component analysis
Very similar, in principal component analysis, data are represented as its several principal dimensions.Since the dimension of noise will be far above often
Data are advised, which can reduce noise, then by the way that there are three the Auto-encoder of hidden layer optimizations to improve removal noise effects.
Data by denoising obtain character subset using the processing of Feature Engineering, first choose feature as much as possible, advanced
Row dimensionality reduction, that is, useful information is extracted from primary data, by dimensionality reduction, the data set in higher dimensional space is mapped to low
Dimension space data, while information is lost as few as possible, and the feature retained after dimensionality reduction is selected, finally preserve these spies
Levy subset.The processing step of Feature Engineering is as follows, sliding window variance：Data sampling time sequence is { x (t) }, and setting one is wide
Degree is the diagnostic window of h, i.e., includes the h data by acquisition order arrangement in window, then claim x variables the k moment diagnostic window
Mouthful time series is:{xk}={ x (k-j) } (j=h-1, h-2 ..., 1,0), sample standard deviation X variables are in the estimated value of the standard deviation at k moment:σkCharacterize x variables the k moment significant condition.Wherein,It is sequence { xkSample
Mean value, it is assumed that have n in the diagnostic window at k momentqA singular point.
K- mean values：1) it is directed to the character subset obtained after features described above project treatment, chooses each character subset data
For k object in space as initial cluster center, each object represents a cluster centre；2) for the data pair in sample
As nearest apart from them by them are assigned to apart from nearest criterion according to the Euclidean distance of they and these cluster centres
Class corresponding to cluster centre (most like)；3) cluster centre is updated：Mean value corresponding to all objects in each classification is made
For the cluster centre of the category, the value of calculating target function；4) judge whether the value of cluster centre and object function changes,
If constant, if output is as a result, 2) change, returns.Repeatedly until obtaining the character subset of optimum prediction ability.
With intelligent inference and deep neural network algorithm, fundamentals of forecasting mould is built based on the above-mentioned character subset obtained
Type, and hyperparameter optimization processing is carried out to it, optimize following hyper parameter：Iterations, normal distribution, activation primitive and hidden
Hide the number of layer.It in our daily carry out hyperparameter optimization work, can go to try manually, random search can also be used
The parameter that method has been transferred to.One initial hyper parameter value is set first, basic model training is then carried out, by the index of model
It feeds back in hyper parameter tuning mechanism, adjusts hyper parameter, continue training pattern, train repeatedly, obtain one afterwards several times
Hyper parameter value optimal at present.
Finally forecasting system is verified using the optimal hyper parameter, and assists existing fault sample, to pre-
Examining system carries out further assessment correction, if the conclusion obtained is matched with known fault, confirms the available of forecasting system
Property, if the conclusion obtained has deviation, forecasting system is corrected.Wherein in data set, if same class is by mistake
When point indicating, just will appear the distribution of unbalanced class, in order to avoid this problem, the present invention also using the character subset of generation come
Machine learning model is assessed, and using precision ratio and recall ratio as measurement standard.And for accuracy rate, recall ratio and precision ratio,
Preferably it is worth close to 1, trained model just has good performance.
The present invention is based on the failure prediction systems of machine learning, and input is by pretreated data to machine learning system
In, the processing of denoising, Feature Engineering and hyperparameter optimization is passed sequentially through, failure predication model is obtained by intelligent inference algorithm,
Model is assessed by typical fault sample and character subset, to improve the prediction model accuracy of model, to build
Failure prediction system is finally input to collected equipment real-time running data in failure prediction system, realizes to equipment event
The prediction of barrier.
The explanation of the preferred embodiment of the present invention contained above, this be for the technical characteristic that the present invention will be described in detail, and
Be not intended to invention content being limited in concrete form described in embodiment, according to the present invention content purport carry out other
Modifications and variations are also protected by this patent.The purport of the content of present invention is to be defined by the claims, rather than have embodiment
Specific descriptions are defined.
Claims (10)
1. a kind of failure prediction method based on machine learning, step include：
1) the setting operating index data for acquiring object to be predicted obtain the time series data of each setting operating index；It adopts
Collect the historical failure data of the object to be predicted；
2) feature extraction is carried out respectively to the data of step 1) acquisition, the feature of extraction is input in machine learning system and is carried out
Training obtains a basic failure predication model；
3) real time data for collecting the setting operating index when object operation to be predicted carries out it feature extraction and inputs to be somebody's turn to do
Basic failure predication model predicts that the object to be predicted currently whether there is failure.
2. the method as described in claim 1, which is characterized in that machine learning system carries out denoising, spy successively to input feature vector
Engineering is levied, training obtains a basic failure predication model and carries out hyperparameter optimization to the basis failure predication model.
3. method as claimed in claim 2, which is characterized in that the processing method of the Feature Engineering is：For each time
Sequence data calculates the sliding window variance of the time series data, by multiple sliding window variances of the time series data
As a character subset；Then k- mean clusters are carried out to each character subset, is most there is the character subset of predictive ability；Meter
The sliding window variance for calculating historical failure data, obtains the corresponding character subset of historical failure data.
4. method as claimed in claim 3, which is characterized in that the method for calculating the sliding window variance：For the time
Sequence data { x (t) }, the diagnostic window that one width of setting is h, i.e., comprising h by acquisition order arrangement in the diagnostic window
Data, data sequence when diagnostic window moment k are:{xk}={ x (k-j) } (j=h-1, h-2 ..., 1,0), corresponding cunning
Dynamic window variancene=h-nq- 1,It is sequence { xkSample average, nqFor k
Singular point number in the diagnostic window at moment.
5. method as claimed in claim 3, which is characterized in that carry out k- mean clusters to each character subset, most had pre-
The method of the character subset of survey ability is：For each character subset, 1) k object is chosen from this feature subset data space
As initial cluster center；2) Euclidean distance of the data object and each cluster centre in this feature subset is calculated, most by distance
Data object in this feature subset is assigned to the class corresponding to the cluster centre away from nearest neighbours by close criterion；3) update cluster
Center：Using the mean value corresponding to all objects in each classification as the cluster centre of the category, the value of calculating target function；4)
Judge whether the value of cluster centre and object function changes, if constant, if output is as a result, 2) change, returns；So
Repeatedly until obtaining the corresponding character subset for most having predictive ability of this feature subset.
6. method as claimed in claim 3, which is characterized in that using most have the character subset of predictive ability train to obtain it is described
Basic failure predication model, and hyperparameter optimization processing is carried out to it；Using the corresponding character subset of historical failure data to institute
Basic failure predication model row assessment verification is stated, if the conclusion obtained is matched with known fault, confirms the basic failure
Otherwise the availability of prediction model is modified the basic failure predication model.
7. method as claimed in claim 6, which is characterized in that the hyper parameter of optimization includes：Iterations, distribution, activation letter
The number of number and hidden layer.
8. method as claimed in claim 2, which is characterized in that using neural network Auto-Encoder to the feature of extraction according to
Secondary carry out denoising.
9. the method as described in claim 1, which is characterized in that the feature of extraction include the mean value of data, sliding window variance,
Root mean square, peak factor, kurtosis coefficient and shape factor.
10. the method as described in claim 1, which is characterized in that the setting operating index includes device temperature, heat, turns
Speed, displacement, procedure parameter and vibratory output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711362861.4A CN108304941A (en) | 2017-12-18 | 2017-12-18 | A kind of failure prediction method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711362861.4A CN108304941A (en) | 2017-12-18 | 2017-12-18 | A kind of failure prediction method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108304941A true CN108304941A (en) | 2018-07-20 |
Family
ID=62870169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711362861.4A Pending CN108304941A (en) | 2017-12-18 | 2017-12-18 | A kind of failure prediction method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108304941A (en) |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109412892A (en) * | 2018-10-23 | 2019-03-01 | 株洲中车时代电气股份有限公司 | A kind of network communication quality assessment system and method |
| CN109472285A (en) * | 2018-09-29 | 2019-03-15 | 北京中油瑞飞信息技术有限责任公司 | Leakage recognition methods, device and computer equipment |
| CN109492752A (en) * | 2018-11-05 | 2019-03-19 | 常熟理工学院 | Using intelligent learning system and method for the data-signal in conjunction with knowledge elicitation |
| CN109547251A (en) * | 2018-11-27 | 2019-03-29 | 广东电网有限责任公司 | A kind of operation system failure and performance prediction method based on monitoring data |
| CN109583751A (en) * | 2018-11-27 | 2019-04-05 | 中国科学院空间应用工程与技术中心 | The failure decision-making technique of payload |
| CN109582724A (en) * | 2018-12-07 | 2019-04-05 | 厦门铅笔头信息科技有限公司 | Distributed automated characterization engineering system framework |
| CN109670551A (en) * | 2018-12-20 | 2019-04-23 | 树根互联技术有限公司 | The failure prediction method and device of engineering mechanical device |
| CN109685331A (en) * | 2018-12-06 | 2019-04-26 | 中国软件与技术服务股份有限公司 | A kind of high-speed rail bogie sensor fault diagnosis method based on machine learning |
| CN109737045A (en) * | 2019-01-11 | 2019-05-10 | 南方电网科学研究院有限责任公司 | Air compressor machine fault early warning method, system and relevant apparatus applied to chip production |
| CN110033135A (en) * | 2019-04-15 | 2019-07-19 | 北京交通大学 | The train braking system failure prediction method that Multivariate Time Series feature is reinforced |
| CN110175701A (en) * | 2019-04-29 | 2019-08-27 | 北京六捷科技有限公司 | A kind of railway service Call failure prediction technique and device |
| CN110349289A (en) * | 2019-06-21 | 2019-10-18 | 东软集团股份有限公司 | Failure prediction method, device, storage medium and electronic equipment |
| CN110428109A (en) * | 2019-08-07 | 2019-11-08 | 佳都新太科技股份有限公司 | Subway shield door time between failures prediction model is established and prediction technique |
| CN110750784A (en) * | 2019-09-24 | 2020-02-04 | 深圳市智莱科技股份有限公司 | Safety prevention and control method and system for automatic vending equipment |
| CN110794227A (en) * | 2018-08-02 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Fault detection method, system, device and storage medium |
| CN110995384A (en) * | 2019-11-27 | 2020-04-10 | 杭州联汇科技股份有限公司 | Broadcast master control fault trend prejudging method based on machine learning |
| CN111105063A (en) * | 2018-10-26 | 2020-05-05 | 北京国双科技有限公司 | Fault prediction method, fault prediction device, model construction method, fault prediction device, processor and readable storage medium |
| CN111219942A (en) * | 2018-11-26 | 2020-06-02 | 珠海格力电器股份有限公司 | Refrigerator fault prediction method and device |
| CN111459692A (en) * | 2019-01-18 | 2020-07-28 | 伊姆西Ip控股有限责任公司 | Method, apparatus and computer program product for predicting drive failure |
| CN111724048A (en) * | 2020-06-03 | 2020-09-29 | 浙江中烟工业有限责任公司 | Characteristic extraction method for finished product library scheduling system performance data based on characteristic engineering |
| CN111829425A (en) * | 2020-08-06 | 2020-10-27 | 厦门航空有限公司 | Health monitoring method and system for civil aircraft leading edge position sensor |
| CN111860943A (en) * | 2020-06-08 | 2020-10-30 | 清华大学 | Power grid fault prediction method and system based on numerical meteorological data and machine learning |
| CN111985651A (en) * | 2019-05-22 | 2020-11-24 | 中国移动通信集团福建有限公司 | Operation and maintenance method and device for business system |
| CN112241511A (en) * | 2019-07-19 | 2021-01-19 | 上海杰之能软件科技有限公司 | Performance detection method and device of auxiliary electrical system of vehicle and terminal |
| CN112506687A (en) * | 2020-11-24 | 2021-03-16 | 四川长虹电器股份有限公司 | Fault diagnosis method based on multi-period segmented sliding window standard deviation |
| CN112534370A (en) * | 2018-08-12 | 2021-03-19 | 斯凯孚人工智能有限公司 | System and method for predicting industrial machine failure |
| CN112541597A (en) * | 2019-09-04 | 2021-03-23 | 上海杰之能软件科技有限公司 | Multi-equipment maintenance method and device, storage medium and terminal |
| CN112613619A (en) * | 2020-11-30 | 2021-04-06 | 重庆电子工程职业学院 | Safety operation management system for gas area in workshop |
| CN112947356A (en) * | 2019-12-10 | 2021-06-11 | 佳能株式会社 | Control method, control device, mechanical equipment and recording medium |
| CN112989501A (en) * | 2021-05-10 | 2021-06-18 | 中国标准化研究院 | Balance car safety evaluation method and device and terminal equipment |
| CN113383282A (en) * | 2019-01-31 | 2021-09-10 | 应用材料公司 | Correcting component failure in an ion implanted semiconductor manufacturing tool |
| CN113609187A (en) * | 2021-07-23 | 2021-11-05 | 四川虹美智能科技有限公司 | Fault diagnosis method and system based on big data |
| CN113656287A (en) * | 2021-07-28 | 2021-11-16 | 北京宝兰德软件股份有限公司 | Method and device for predicting software instance fault, electronic equipment and storage medium |
| CN114251295A (en) * | 2020-09-23 | 2022-03-29 | 株式会社岛津制作所 | Pump monitoring device, vacuum pump, pump monitoring method, and storage medium |
| CN114492517A (en) * | 2022-01-10 | 2022-05-13 | 南方科技大学 | Elevator detection method, elevator detection device, electronic device and storage medium |
| CN114781762A (en) * | 2022-06-21 | 2022-07-22 | 四川观想科技股份有限公司 | Equipment fault prediction method based on life consumption |
| CN114987773A (en) * | 2022-05-20 | 2022-09-02 | 成都飞机工业（集团）有限责任公司 | Method, device, equipment and medium for identifying performance abnormity of aircraft hydraulic system |
| US11520564B2 (en) | 2021-01-20 | 2022-12-06 | International Business Machines Corporation | Intelligent recommendations for program code |
| CN116579762A (en) * | 2023-04-14 | 2023-08-11 | 广州林旺空调工程有限公司 | Intelligent operation and maintenance platform for cooling tower |
Citations (3)
| 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 |
| CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
| US20170249234A1 (en) * | 2016-02-29 | 2017-08-31 | B. G. Negev Technologies And Applications Ltd., At Ben-Gurion University | Data-augmented software diagnosis method and a diagnoser therefor |
-
2017
- 2017-12-18 CN CN201711362861.4A patent/CN108304941A/en active Pending
Patent Citations (3)
| 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 |
| CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
| US20170249234A1 (en) * | 2016-02-29 | 2017-08-31 | B. G. Negev Technologies And Applications Ltd., At Ben-Gurion University | Data-augmented software diagnosis method and a diagnoser therefor |
Non-Patent Citations (1)
| Title |
|---|
| 白小琴 等: ""流程工业仪表故障快速检测方法"", 《化工自动化及仪表》 * |
Cited By (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110794227A (en) * | 2018-08-02 | 2020-02-14 | 阿里巴巴集团控股有限公司 | Fault detection method, system, device and storage medium |
| CN112534370A (en) * | 2018-08-12 | 2021-03-19 | 斯凯孚人工智能有限公司 | System and method for predicting industrial machine failure |
| CN109472285A (en) * | 2018-09-29 | 2019-03-15 | 北京中油瑞飞信息技术有限责任公司 | Leakage recognition methods, device and computer equipment |
| CN109412892B (en) * | 2018-10-23 | 2022-03-01 | 株洲中车时代电气股份有限公司 | Network communication quality evaluation system and method |
| CN109412892A (en) * | 2018-10-23 | 2019-03-01 | 株洲中车时代电气股份有限公司 | A kind of network communication quality assessment system and method |
| CN111105063A (en) * | 2018-10-26 | 2020-05-05 | 北京国双科技有限公司 | Fault prediction method, fault prediction device, model construction method, fault prediction device, processor and readable storage medium |
| CN109492752A (en) * | 2018-11-05 | 2019-03-19 | 常熟理工学院 | Using intelligent learning system and method for the data-signal in conjunction with knowledge elicitation |
| CN111219942A (en) * | 2018-11-26 | 2020-06-02 | 珠海格力电器股份有限公司 | Refrigerator fault prediction method and device |
| CN109547251A (en) * | 2018-11-27 | 2019-03-29 | 广东电网有限责任公司 | A kind of operation system failure and performance prediction method based on monitoring data |
| CN109583751A (en) * | 2018-11-27 | 2019-04-05 | 中国科学院空间应用工程与技术中心 | The failure decision-making technique of payload |
| CN109547251B (en) * | 2018-11-27 | 2022-05-10 | 广东电网有限责任公司 | Service system fault and performance prediction method based on monitoring data |
| CN109685331A (en) * | 2018-12-06 | 2019-04-26 | 中国软件与技术服务股份有限公司 | A kind of high-speed rail bogie sensor fault diagnosis method based on machine learning |
| CN109582724B (en) * | 2018-12-07 | 2022-04-08 | 厦门铅笔头信息科技有限公司 | Distributed automatic feature engineering system architecture |
| CN109582724A (en) * | 2018-12-07 | 2019-04-05 | 厦门铅笔头信息科技有限公司 | Distributed automated characterization engineering system framework |
| CN109670551A (en) * | 2018-12-20 | 2019-04-23 | 树根互联技术有限公司 | The failure prediction method and device of engineering mechanical device |
| CN109737045A (en) * | 2019-01-11 | 2019-05-10 | 南方电网科学研究院有限责任公司 | Air compressor machine fault early warning method, system and relevant apparatus applied to chip production |
| CN111459692B (en) * | 2019-01-18 | 2023-08-18 | 伊姆西Ip控股有限责任公司 | Method, apparatus and computer program product for predicting drive failure |
| CN111459692A (en) * | 2019-01-18 | 2020-07-28 | 伊姆西Ip控股有限责任公司 | Method, apparatus and computer program product for predicting drive failure |
| CN113383282A (en) * | 2019-01-31 | 2021-09-10 | 应用材料公司 | Correcting component failure in an ion implanted semiconductor manufacturing tool |
| CN110033135A (en) * | 2019-04-15 | 2019-07-19 | 北京交通大学 | The train braking system failure prediction method that Multivariate Time Series feature is reinforced |
| CN110175701A (en) * | 2019-04-29 | 2019-08-27 | 北京六捷科技有限公司 | A kind of railway service Call failure prediction technique and device |
| CN111985651A (en) * | 2019-05-22 | 2020-11-24 | 中国移动通信集团福建有限公司 | Operation and maintenance method and device for business system |
| CN110349289A (en) * | 2019-06-21 | 2019-10-18 | 东软集团股份有限公司 | Failure prediction method, device, storage medium and electronic equipment |
| CN112241511A (en) * | 2019-07-19 | 2021-01-19 | 上海杰之能软件科技有限公司 | Performance detection method and device of auxiliary electrical system of vehicle and terminal |
| CN110428109A (en) * | 2019-08-07 | 2019-11-08 | 佳都新太科技股份有限公司 | Subway shield door time between failures prediction model is established and prediction technique |
| CN110428109B (en) * | 2019-08-07 | 2020-11-03 | 佳都新太科技股份有限公司 | Subway shield door fault interval time prediction model establishing and predicting method |
| CN112541597A (en) * | 2019-09-04 | 2021-03-23 | 上海杰之能软件科技有限公司 | Multi-equipment maintenance method and device, storage medium and terminal |
| CN110750784B (en) * | 2019-09-24 | 2023-10-03 | 深圳市智莱科技股份有限公司 | Security prevention and control method and system for automatic vending equipment |
| CN110750784A (en) * | 2019-09-24 | 2020-02-04 | 深圳市智莱科技股份有限公司 | Safety prevention and control method and system for automatic vending equipment |
| CN110995384B (en) * | 2019-11-27 | 2021-08-10 | 杭州联汇科技股份有限公司 | Broadcast master control fault trend prejudging method based on machine learning |
| CN110995384A (en) * | 2019-11-27 | 2020-04-10 | 杭州联汇科技股份有限公司 | Broadcast master control fault trend prejudging method based on machine learning |
| CN112947356A (en) * | 2019-12-10 | 2021-06-11 | 佳能株式会社 | Control method, control device, mechanical equipment and recording medium |
| CN111724048A (en) * | 2020-06-03 | 2020-09-29 | 浙江中烟工业有限责任公司 | Characteristic extraction method for finished product library scheduling system performance data based on characteristic engineering |
| CN111860943A (en) * | 2020-06-08 | 2020-10-30 | 清华大学 | Power grid fault prediction method and system based on numerical meteorological data and machine learning |
| CN111829425A (en) * | 2020-08-06 | 2020-10-27 | 厦门航空有限公司 | Health monitoring method and system for civil aircraft leading edge position sensor |
| CN114251295A (en) * | 2020-09-23 | 2022-03-29 | 株式会社岛津制作所 | Pump monitoring device, vacuum pump, pump monitoring method, and storage medium |
| TWI826803B (en) * | 2020-09-23 | 2023-12-21 | 日商島津製作所股份有限公司 | Pump monitoring device, vacuum pump, pump monitoring method and pump monitoring program |
| CN112506687A (en) * | 2020-11-24 | 2021-03-16 | 四川长虹电器股份有限公司 | Fault diagnosis method based on multi-period segmented sliding window standard deviation |
| CN112613619A (en) * | 2020-11-30 | 2021-04-06 | 重庆电子工程职业学院 | Safety operation management system for gas area in workshop |
| CN112613619B (en) * | 2020-11-30 | 2024-04-09 | 重庆电子工程职业学院 | Safety operation management system for gas area in workshop |
| US11520564B2 (en) | 2021-01-20 | 2022-12-06 | International Business Machines Corporation | Intelligent recommendations for program code |
| CN112989501B (en) * | 2021-05-10 | 2022-02-01 | 中国标准化研究院 | Balance car safety evaluation method and device and terminal equipment |
| CN112989501A (en) * | 2021-05-10 | 2021-06-18 | 中国标准化研究院 | Balance car safety evaluation method and device and terminal equipment |
| CN113609187A (en) * | 2021-07-23 | 2021-11-05 | 四川虹美智能科技有限公司 | Fault diagnosis method and system based on big data |
| CN113656287A (en) * | 2021-07-28 | 2021-11-16 | 北京宝兰德软件股份有限公司 | Method and device for predicting software instance fault, electronic equipment and storage medium |
| CN114492517A (en) * | 2022-01-10 | 2022-05-13 | 南方科技大学 | Elevator detection method, elevator detection device, electronic device and storage medium |
| CN114492517B (en) * | 2022-01-10 | 2022-11-25 | 南方科技大学 | Elevator detection method, elevator detection device, electronic device and storage medium |
| CN114987773A (en) * | 2022-05-20 | 2022-09-02 | 成都飞机工业（集团）有限责任公司 | Method, device, equipment and medium for identifying performance abnormity of aircraft hydraulic system |
| CN114781762A (en) * | 2022-06-21 | 2022-07-22 | 四川观想科技股份有限公司 | Equipment fault prediction method based on life consumption |
| CN116579762B (en) * | 2023-04-14 | 2023-10-20 | 广州林旺空调工程有限公司 | Intelligent operation and maintenance platform for cooling tower |
| CN116579762A (en) * | 2023-04-14 | 2023-08-11 | 广州林旺空调工程有限公司 | Intelligent operation and maintenance platform for cooling tower |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108304941A (en) | A kind of failure prediction method based on machine learning | |
| CN108584592B (en) | A kind of shock of elevator car abnormity early warning method based on time series predicting model | |
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| CN112418277B (en) | Method, system, medium and equipment for predicting residual life of rotating machine parts | |
| CN104200396B (en) | A kind of wind turbine component fault early warning method | |
| CN111353482A (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| KR101948604B1 (en) | Method and device for equipment health monitoring based on sensor clustering | |
| CN106094744A (en) | The determination method of thermoelectricity factory owner's operational factor desired value based on association rule mining | |
| CN111275255A (en) | Construction method of concrete dam deformation monitoring and forecasting model | |
| CN110472800A (en) | A kind of machine tool method for predicting residual useful life based on LSTM+CNN | |
| CN107273924A (en) | The Fault Analysis of Power Plants method of multi-data fusion based on fuzzy cluster analysis | |
| CN104123678A (en) | Electricity relay protection status overhaul method based on status grade evaluation model | |
| CN108435819A (en) | A kind of aluminum section extruder energy consumption method for detecting abnormality | |
| CN109190184A (en) | A kind of heating system historical data preprocess method | |
| Barbieri et al. | Sensor-based degradation prediction and prognostics for remaining useful life estimation: Validation on experimental data of electric motors | |
| Tang et al. | Fault diagnosis of rolling bearing based on probability box theory and GA-SVM | |
| Addeh et al. | Control chart patterns detection using COA based trained MLP neural network and shape features | |
| CN105956708A (en) | Grey correlation time sequence based short-term wind speed forecasting method | |
| CN114757365A (en) | High-speed railway roadbed settlement prediction and early warning method based on deep learning | |
| CN113539382B (en) | Early warning positioning method and system for key technological parameters of dimethyl phosphite | |
| CN104978484B (en) | Fuzzy forecasting model based method for detecting pulp concentration in ore grinding process of dressing plant | |
| CN107067028A (en) | Network traffics Time Series Forecasting Methods based on Distributed Cluster | |
| CN109594967A (en) | A kind of lock of tool drilling detection method for early warning based on well logging big data | |
| CN109145773A (en) | A kind of failure prediction method of multi-source tendency information fusion | |
| CN111275136B (en) | Fault prediction system based on small sample and early warning method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180720 |
|
| RJ01 | Rejection of invention patent application after publication |