CN106516923A - Elevator running failure prediction method based on technology of Internet of Things - Google Patents
Elevator running failure prediction method based on technology of Internet of Things Download PDFInfo
- Publication number
- CN106516923A CN106516923A CN201610787698.5A CN201610787698A CN106516923A CN 106516923 A CN106516923 A CN 106516923A CN 201610787698 A CN201610787698 A CN 201610787698A CN 106516923 A CN106516923 A CN 106516923A
- Authority
- CN
- China
- Prior art keywords
- elevator
- internet
- things
- technology
- data
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0018—Devices monitoring the operating condition of the elevator system
- B66B5/0031—Devices monitoring the operating condition of the elevator system for safety reasons
Landscapes
- Indicating And Signalling Devices For Elevators (AREA)
- Maintenance And Inspection Apparatuses For Elevators (AREA)
Abstract
The invention discloses an elevator running failure prediction method based on the technology of Internet of Things. The method comprises the following steps of 1, mounting sensing equipment at the top and the bottom of a lift car of an elevator and on the lift car, and achieving transmission of monitoring data through a DTU and a data card in the DTU; 2, establishing elevator failure maintenance prediction models, and predicting future determined values such as failure maintenance through the elevator failure maintenance prediction models; and 3, evaluating a model result. By means of the elevator running failure prediction method based on the technology of Internet of Things, potential failure hazards of the elevator can be found as early as possible, sufficient time is reserved for repair work, and heavy losses are avoided. The elevator running failure prediction method is applied to the field of elevator Internet of Things, and elevator running safety and reliability within the local scope can be greatly enhanced.
Description
Technical field
The present invention relates to a kind of failure prediction method, and in particular to a kind of elevator operation troubles based on technology of Internet of things is pre-
Survey method.The present invention relates to Internet of Things/Sensor Network field.
Background technology
The country solves the problems, such as that elevator safety mainly passes through two approach:One is the fault diagnosis after failure occurs, and two is dimension
Repair personnel's regularly maintaining.And the fault diagnosis technology being widely used at present mainly has expert system, fuzzy reasoning, nerve
Network etc..But these technologies depend critically upon expertise, acquirement of expert knowledge difficulty becomes the bottleneck of fault diagnosis enforcement.Separately
Outward, most of method for diagnosing faults can not all provide failure predication function, and passive-type diagnosis cannot prevent the generation of failure, can only
It is fixed against elevator periodic maintenance maintenance.Not only high cost, efficiency are low for the indefinite periodic maintenance of purpose, and by artificial
Inspection also is difficult to find the potential safety hazard of elevator.
Patent No. ' CN201210064642.9 ', entitled ' elevator running performance in-line analyzer and on-line analysis side
Method ' patent, elevator running performance in-line analyzer and on-line analysis belong to elevator technology field, it is characterised in that on
Position machine is used for realizing the statistics and analysis of signal, but the cost of equipment is too high, and technology is immature, there is the high mistake of comparison
Rate, causes easily to break down when in use.
Patent No. ' CN201210176351.9 ', entitled ' Elevator Fault Diagnosis based on data-driven and the pre- police
Method ' patent, the invention adopts the technical scheme that, the Elevator Fault Diagnosis and method for early warning based on data-driven, by means of
Remote service center, fault diagnosis and fault prediction terminal and electric life controller are realized, but do not provide concrete implementation mode,
Function is not concrete enough.
The content of the invention
For solving the deficiencies in the prior art, it is an object of the invention to provide a kind of elevator based on technology of Internet of things runs
Failure prediction method.
In order to realize above-mentioned target, the present invention is adopted the following technical scheme that:
A kind of elevator operation troubles Forecasting Methodology based on technology of Internet of things, it is characterised in that comprise the steps:
Step one:In the car top of elevator, car, car floor install sensing equipment, by the data card in DTU and DTU, realize prison
The transmission of control data;
Step 2:The model that elevator faults safeguard prediction is set up, and the following determination value of Breakdown Maintenance etc. is predicted using them;
Step 3:Model result is estimated.
A kind of aforesaid elevator operation troubles Forecasting Methodology based on technology of Internet of things, it is characterised in that the step 2
Including:Data of the method for moving average using history, carry out smooth movement, in time series while calculating to existing entry
To sequential mean value, translate because the method for moving average is simply simple, the weights of each element are the same, so as to eliminate season well
The impact that section sexual factor and random fluctuation bring;According to sample number n, if weights sequence is w1, w2 ... wn, and w1+ w2 are met
+ ...+wn=1, then there are f (t)=w1Zt-1+ w2Zt-2+ ...+wnZt-n;Each weight is adjusted, is close to predicted value actual
Value.
A kind of aforesaid elevator operation troubles Forecasting Methodology based on technology of Internet of things, it is characterised in that the step 3
Including:The historical data of prediction object is arranged by certain time interval, a time dependent statistics sequence is constituted
Row, set up the time dependent model of corresponding data, and the model is extrapolated to future is predicted;According to the history that oneself knows
Data are fitted a curve so that this curve can reflect the time dependent trend of prediction object;According to change trend curve,
For following a certain moment, the predicted value at the moment is estimated from curve.
The invention has benefit that:The present invention can have found the potential faults of elevator early, reserve to maintenance abundant
Time, it is to avoid the generation of heavy losses.The present invention is applied to electricity in elevator Internet of Things field meeting significant increase regional extent
The safety and reliability of ladder operation.
Description of the drawings
Fig. 1 is the structural representation being preferable to carry out of the present invention.
Specific embodiment
Make specific introduction to the present invention below in conjunction with the drawings and specific embodiments.
With reference to shown in Fig. 1, the present invention
Failure prediction method is comprised the following steps:
(1)In the car top of elevator, car, car floor install sensing equipment, by the data card in DTU and DTU, realize monitoring number
According to transmission.
(2)With the research of elevator remote monitoring system, with the mathematical methods such as mathematical statistics, trend analysis and road force
Empirical method is guiding theory, on the basis of the accumulation data of analysis of history failure, sets up the mould that elevator faults safeguard prediction
Type, and the following determination value of Breakdown Maintenance etc. is predicted using them, its result is unique.The method of moving average is using history
Data, carry out smooth movement in time series, while existing entry is carried out being calculated sequential mean value, because of the method for moving average
Simply simple to translate, the weights of each element are the same, so as to good deseasonalization and random fluctuation bring
Affect.According to sample number n, if weights sequence is w1, w2... wn, and meet w1+ w2+…+ wn =1, then there is f (t)=w1Zt-1+
w2Zt-2+…+ wnZt-n。
Rule of thumb adjusting each weight, predicted value is made to be close to actual value, in the case where seasonal effect is relevant, can
Adjust with according to Seasonal Data, effect can be more preferable.
(3)Model result is assessed.
The present invention is arranged the historical data of prediction object by certain time interval, is constituted one and is changed over
Statistical series, set up the time dependent model of corresponding data, and the model be extrapolated to into future and be predicted.According to oneself
The historical data known is fitted a curve so that this curve can reflect the time dependent trend of prediction object.According to change
Trend curve, for following a certain moment, from curve it is estimated that the predicted value at the moment.Effectively premise of the invention
It is that past development model can be extended to future, thus the present invention is relatively good to short-term forecast effect.
In the car top of elevator, car, car floor install sensing equipment, by the data card in DTU and DTU, realize monitoring
The transmission of data.
With the research of elevator remote monitoring system, with the mathematical methods such as mathematical statistics, trend analysis and road surface mechanics
Empirical method is guiding theory, on the basis of the accumulation data of analysis of history failure, sets up the model that elevator faults safeguard prediction,
And the following determination value of Breakdown Maintenance etc. is predicted using them, its result is unique.Number of the method for moving average using history
According to, smooth movement is carried out in time series, while existing entry is carried out being calculated sequential mean value, because of the method for moving average only
It is simple translation, the weights of each element are the same, so as to the shadow that good deseasonalization and random fluctuation bring
Ring.
Rule of thumb adjusting each weight, predicted value is made to be close to actual value, in the case where seasonal effect is relevant, can
Adjust with according to Seasonal Data, effect can be more preferable.
Model result is assessed.
The sensing equipment includes that the traction machine sensor being arranged on traction machine and the car being arranged on car are passed
Sensor, the traction machine sensor and car sensor are connected with Surveillance center respectively, are just having elevator in the Surveillance center
When often operating traction machine each operation phase spectrogram and car each operation phase spectrogram, and Surveillance center
Process contrast can be carried out to the data of traction machine sensor and car sensor.Traction machine sensor and car sensor are
3-axis acceleration sensor.The sensor noise being connected with Surveillance center, Surveillance center's internal memory is provided with outside lift car
Spectrogram of the car external noise in each operation phase when having elevator normal operation, and Surveillance center can be to sensor noise
Data carry out process contrast.
The implementation method of early warning includes having the following steps:
When step one, elevator operation, sensed by the traction machine sensor being arranged on traction machine, the car being arranged on car
Device and be arranged on car external noise sensor collection elevator under the different motion stage traction machine, car vibration data with
And the noise data outside car, and transmit to Surveillance center;
Step 2, Surveillance center carry out fast Flourier to the noise data outside traction machine, the vibration data of car and car
Conversion, draws the rumble spectrum figure of traction machine, cabin elevator under the different motion stage, and the outer elevator of car in different motion
Noise pattern under stage;
Step 3, Surveillance center collection rumble spectrum figure, noise pattern and Surveillance center's internal memory elevator normal operation
Rumble spectrum figure, noise pattern contrast, if the traction machine rumble spectrum figure of collection, car vibrations spectrogram, making an uproar outside car
In audio frequency spectrogram, any one or multiple spectrograms are more than or equal to the frequency in the amplitude of certain frequency range or multiple frequency ranges
1.5~3 times of the lower normal amplitude of section, then assert that elevator occurs or will break down, and carries out early warning, and carries out
Maintenance, if full frequency band amplitude without departing from 1.5~3 times of normal amplitude, then it is assumed that elevator is in normal operation.
In described step three, if the traction machine rumble spectrum figure of collection, car vibrations spectrogram, car external noise frequency spectrum
In figure, the amplitude of any one or multiple spectrogram frequency ranges or multiple frequency ranges is more than or equal to normal width under the frequency range
2 times of value, then assert elevator occur or will break down, carry out early warning, if full frequency band amplitude without departing from just
2 times of normal amplitude, then it is assumed that elevator is in normal operation.
The basic principles, principal features and advantages of the present invention have been shown and described above.The technical staff of the industry should
Understand, the invention is not limited in any way for above-described embodiment, it is all to be obtained by the way of equivalent or equivalent transformation
Technical scheme, all falls within protection scope of the present invention.
Claims (3)
1. a kind of elevator operation troubles Forecasting Methodology based on technology of Internet of things, it is characterised in that comprise the steps:
Step one:In the car top of elevator, car, car floor install sensing equipment, by the data card in DTU and DTU, realize prison
The transmission of control data;
Step 2:The model that elevator faults safeguard prediction is set up, and the following determination value of Breakdown Maintenance etc. is predicted using them;
Step 3:Model result is estimated.
2. a kind of elevator operation troubles Forecasting Methodology based on technology of Internet of things according to claim 1, it is characterised in that
The step 2 includes:Data of the method for moving average using history, carry out smooth movement, in time series while to existing entry
Carry out being calculated sequential mean value, translate because the method for moving average is simply simple, the weights of each element are the same, so as to very
The impact that good deseasonalization and random fluctuation is brought;According to sample number n, if weights sequence is w1, w2... wn, and it is full
Sufficient w1+ w2+…+ wn=1, then there is f (t)=w1Zt-1+ w2Zt-2+…+ wnZt-n;Each weight is adjusted, is close to predicted value real
Actual value.
3. a kind of elevator operation troubles Forecasting Methodology based on technology of Internet of things according to claim 1, it is characterised in that
The step 3 includes:The historical data of prediction object is arranged by certain time interval, an anaplasia at any time is constituted
The statistical series of change, set up the time dependent model of corresponding data, and the model is extrapolated to future is predicted;According to
The historical data that oneself knows is fitted a curve so that this curve can reflect the time dependent trend of prediction object;According to change
Change trend curve, for following a certain moment, estimate the predicted value at the moment from curve.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610787698.5A CN106516923A (en) | 2016-08-31 | 2016-08-31 | Elevator running failure prediction method based on technology of Internet of Things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610787698.5A CN106516923A (en) | 2016-08-31 | 2016-08-31 | Elevator running failure prediction method based on technology of Internet of Things |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106516923A true CN106516923A (en) | 2017-03-22 |
Family
ID=58344871
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610787698.5A Pending CN106516923A (en) | 2016-08-31 | 2016-08-31 | Elevator running failure prediction method based on technology of Internet of Things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106516923A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109033450A (en) * | 2018-08-22 | 2018-12-18 | 太原理工大学 | Lift facility failure prediction method based on deep learning |
CN110817628A (en) * | 2018-08-08 | 2020-02-21 | 北京感瞰科技有限公司 | Intelligent fault diagnosis method, device and system for elevator |
CN111994749A (en) * | 2020-08-14 | 2020-11-27 | 揭阳市聆讯软件有限公司 | Elevator intelligent supervision and on-demand maintenance system and method based on PHM technology |
CN112978531A (en) * | 2021-02-07 | 2021-06-18 | 猫岐智能科技(上海)有限公司 | Elevator operation evaluation system |
CN113673558A (en) * | 2021-07-13 | 2021-11-19 | 华南理工大学 | Elevator fault diagnosis method based on machine learning |
CN114154667A (en) * | 2020-09-07 | 2022-03-08 | 思维实创(哈尔滨)科技有限公司 | Mixed time series elevator operation parameter prediction method based on big data |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005219929A (en) * | 2004-02-02 | 2005-08-18 | Inventio Ag | Method for designing regulator for damping vibration in elevator cage |
US20070016332A1 (en) * | 2004-01-23 | 2007-01-18 | Kone Corporation | Elevator arrangement |
CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
CN105731209A (en) * | 2016-03-17 | 2016-07-06 | 天津大学 | Intelligent prediction, diagnosis and maintenance method for elevator faults on basis of Internet of Things |
-
2016
- 2016-08-31 CN CN201610787698.5A patent/CN106516923A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070016332A1 (en) * | 2004-01-23 | 2007-01-18 | Kone Corporation | Elevator arrangement |
JP2005219929A (en) * | 2004-02-02 | 2005-08-18 | Inventio Ag | Method for designing regulator for damping vibration in elevator cage |
CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
CN105731209A (en) * | 2016-03-17 | 2016-07-06 | 天津大学 | Intelligent prediction, diagnosis and maintenance method for elevator faults on basis of Internet of Things |
Non-Patent Citations (2)
Title |
---|
樊重俊,刘臣,霍良安: "《大数据分析与应用》", 31 January 2016, 立信会计出版社 * |
王玉荣: "《商务预测方法》", 30 September 2014, 对外经济贸易大学出版社 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110817628A (en) * | 2018-08-08 | 2020-02-21 | 北京感瞰科技有限公司 | Intelligent fault diagnosis method, device and system for elevator |
CN109033450A (en) * | 2018-08-22 | 2018-12-18 | 太原理工大学 | Lift facility failure prediction method based on deep learning |
CN109033450B (en) * | 2018-08-22 | 2021-11-05 | 太原理工大学 | Elevator equipment fault prediction method based on deep learning |
CN111994749A (en) * | 2020-08-14 | 2020-11-27 | 揭阳市聆讯软件有限公司 | Elevator intelligent supervision and on-demand maintenance system and method based on PHM technology |
CN114154667A (en) * | 2020-09-07 | 2022-03-08 | 思维实创(哈尔滨)科技有限公司 | Mixed time series elevator operation parameter prediction method based on big data |
CN112978531A (en) * | 2021-02-07 | 2021-06-18 | 猫岐智能科技(上海)有限公司 | Elevator operation evaluation system |
CN113673558A (en) * | 2021-07-13 | 2021-11-19 | 华南理工大学 | Elevator fault diagnosis method based on machine learning |
CN113673558B (en) * | 2021-07-13 | 2023-12-05 | 华南理工大学 | Elevator fault diagnosis method based on machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106516923A (en) | Elevator running failure prediction method based on technology of Internet of Things | |
US20190285517A1 (en) | Method for evaluating health status of mechanical equipment | |
CN109102189B (en) | Electrical equipment health management system and method | |
CN110371815B (en) | Elevator maintenance system on demand based on Internet of things | |
CN110221139A (en) | A kind of failure prediction method of dry-type transformer, apparatus and system | |
CN106586796A (en) | System and method for monitoring state of escalator | |
CN104925613A (en) | Online safety detection prewarning device of elevator and detection prewarning method thereof | |
CN106017551A (en) | Intelligent transmission line integrated monitoring analysis and early warning method | |
CN104297002B (en) | A kind of subway Electric plug sliding door fault prediction device | |
CN105527112B (en) | A kind of rotating machinery health status comprehensive estimation method influenceed based on use with maintenance | |
KR20170075267A (en) | System for prognosticating failure of elevator | |
Chellaswamy et al. | Optimized railway track health monitoring system based on dynamic differential evolution algorithm | |
CN108928744B (en) | Container crane online diagnosis and maintenance system based on big data | |
CN110058103A (en) | Intelligent transformer fault diagnosis system based on Vxworks platform | |
CN104318347A (en) | Power transmission line icing state assessment method based on information fusion of multiple sensors | |
TWI721693B (en) | Network behavior anomaly detection system and method based on mobile internet of things | |
CN104318485A (en) | Power transmission line fault identification method based on nerve network and fuzzy logic | |
CN104991549A (en) | Track circuit red-light strip default diagnosis method based on FTA and multilevel fuzzy-neural sub-networks | |
El-Hag | Application of machine learning in outdoor insulators condition monitoring and diagnostics | |
CN110763286A (en) | Boarding corridor bridge state monitoring and fault diagnosis system and method | |
CN111348535B (en) | Health state monitoring system and method for escalator used in rail transit station | |
CN104050377A (en) | Method for determining probability of time-varying equipment failures | |
CN114781657A (en) | Power equipment maintenance system and method based on artificial intelligence | |
CN110533300B (en) | Intelligent decision-making system for transformer based on game set pair cloud | |
CN104598969A (en) | High-voltage electrical appliance operation quality evaluation method and system based on neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 210005 No. 268, Hanzhoung Road, Nanjing, Jiangsu Applicant after: CLP Hongxin Information Technology Co., Ltd Address before: 210005 No. 268, Hanzhoung Road, Nanjing, Jiangsu Applicant before: Jiangsu Hongxin System Integration Co., Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |