CN104848885A - Method for predicting time of future failure of equipment - Google Patents
Method for predicting time of future failure of equipment Download PDFInfo
- Publication number
- CN104848885A CN104848885A CN201510303320.9A CN201510303320A CN104848885A CN 104848885 A CN104848885 A CN 104848885A CN 201510303320 A CN201510303320 A CN 201510303320A CN 104848885 A CN104848885 A CN 104848885A
- Authority
- CN
- China
- Prior art keywords
- equipment
- time
- stability bandwidth
- time point
- service 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.)
- Granted
Links
Abstract
The invention relates to the field of equipment failure prediction, and especially relates to a method for predicting the time of future failure of equipment. The method comprises the following steps: acquiring operation data of equipment in a set time interval during operation of the equipment, and establishing a curve of change of operation data of the equipment with time; determining the step size value according to the established curve, calculating the fluctuation ratio of the operation data of the equipment through derivation and obtaining the mean of fluctuation ratio, and fitting a time-fluctuation ratio mean curve by a least square method; and obtaining the mean of fluctuation ratio of the equipment at a future point of time based on the change trend of the established time-fluctuation ratio mean curve, judging whether the mean of fluctuation ratio is within a predetermined abnormal range, and judging that the equipment fails at the point of time and issuing overhaul warning if the mean of fluctuation ratio is within the predetermined abnormal range. The invention provides a prediction method for timely finding the time of future failure of equipment during maintenance of the equipment.
Description
Technical field
The present invention relates to equipment failure prediction field, particularly relate to a kind of method that equipment future malfunction time point is predicted.
Background technology
Machinery and equipment is in routine use and operation process, due to the impact of the factors such as external load, internal stress, wearing and tearing, corrosion and natural erosion, make the size of its individual sites or entirety, shape changes, and then affect mechanical property, the technological effect of equipment, equipment performance is declined, even scrap, this is that all devices all keeps away unavoidable objective law.In order to make equipment keep normal performance, extend its life cycle, must carry out maintenance and the daily maintenance work of appropriateness to equipment, this maintenance of equipment for all trades and professions is all particularly important.For different enterprise, due to the difference of scope of the enterprise, character and number of devices and complexity thereof, its inspection and repair system is also different.Such as, chemical system industry is many, and production procedure differs greatly, and some manufacturing technique requirent long periods run continuously, even preferably runs more than 330 days continuously in 1 year; Some production technologies are but batches, only require and run a period of time continuously; Some technique can not be interrupted; What have can stop by start-stop; Structure, the complexity difference of equipment in addition, maintenance requires also different.At present, most enterprise, producer all regularly carry out the maintenance of equipment, examination, substantially adopt preventive maintenance or production maintenance mode, cannot Timeliness coverage unit exception.
Summary of the invention
For above-mentioned technical matters, the present invention has designed and developed a kind of method predicted equipment future malfunction time point, object is that providing a kind of runs simply, to equipment without the need to newly-increased instrument, continuous monitoring can be realized, and in the maintenance work of equipment, the Forecasting Methodology of Timeliness coverage equipment future malfunction time point, to improve plant maintenance work efficiency, reach more efficient plant maintenance, ensure that technique is normally run, increase work efficiency.
Technical scheme provided by the invention is:
To the method that equipment future malfunction time point is predicted, comprise the following steps:
Step one, when equipment runs, within the time interval of setting, gather the service data of this equipment, and the time dependent curve of the service data setting up this equipment;
Step 2, the curve determination step value set up according to step one, by the stability bandwidth of the service data of this equipment of derived function, and then obtain stability bandwidth average, with stability bandwidth average for ordinate, time is horizontal ordinate, by stability bandwidth Mean curve m-during least square fitting;
Step 3, by step 2 set up time m-stability bandwidth Mean curve variation tendency obtain the stability bandwidth average of this equipment at certain time point following, judge this stability bandwidth average whether in predetermined abnormal ranges, if in predetermined abnormal ranges, then judge that this equipment will break down at this time point, and send maintenance early warning.
By the fluctuation situation of change of the service data of analytical equipment, carry out the analysis of data fluctuations rate, judgement, matching stability bandwidth average trend over time, by the abnormal ranges of definition stability bandwidth Change in Mean, equipment future malfunction time point is predicted, a fast step discovering device abnormal also anticipation trouble spot possibility time of origin, support equipment overhauls in time, improves service life of equipment.
Preferably, in the described method predicted equipment future malfunction time point, abnormal ranges predetermined in described step 3 is p
t> (1+ μ) p
0or p
t< (1-μ) p
0, wherein, p
tfor this equipment is in the stability bandwidth average of certain time point following, p
0for the stability bandwidth average stationary value of this equipment, μ is fluctuation parameters, μ ∈ (0,100%).Using the reference value whether the stability bandwidth average stationary value of this equipment breaks down as judgment device, improve the accuracy of judgement.
Preferably, in the described method predicted equipment future malfunction time point, μ is 10%, makes the judgement of trouble spot more timely.
Preferably, in the described method predicted equipment future malfunction time point, described stability bandwidth average stationary value is empirical value or calculates according to the initial launch data after this renewal of the equipment, to ensure the reliability of stability bandwidth average stationary value.
Preferably, in the described method predicted equipment future malfunction time point, described initial launch data are 200, to ensure the reliability of stability bandwidth average stationary value.
Preferably, in the described method predicted equipment future malfunction time point, in described step 2, the computing formula of the stability bandwidth of the service data of this equipment is:
Wherein, k
ifor this equipment at a time t
itime the stability bandwidth of service data, x
ifor this equipment at a time t
itime service data, x
jfor this equipment is at another moment t
jtime service data;
The computing formula of described stability bandwidth average is:
Wherein, p
ifor this equipment at a time t
itime stability bandwidth average, i is the number of service data of this equipment gathered.
Obtained the stability bandwidth of a certain this equipment operating data of moment by differentiate, method is simple, and the ultimate criterion of point using stability bandwidth average as failure judgement, the undulatory property of data variation is less, and it is more accurate to judge.
Preferably, in the described method that equipment future malfunction time point is predicted, also comprise in described step one: the service data of this equipment collected is carried out filtering, remove abnormity point, and mark, in order to avoid produce interference to the analysis of stability bandwidth, avoid the generation of the undetected situation of fault.
Preferably, in the described method predicted equipment future malfunction time point, described equipment is instrument and meter or motor, reacts its running status to the monitoring of instrument and meter, to the situation that the monitoring reaction motor of motor runs.
Preferably, in the described method predicted equipment future malfunction time point, the service data of described equipment is the Monitoring Data of instrument and meter or the running current of motor.The method has certain versatility, not only can be applied to environmental protection industry (epi), all can apply in the monitoring of the equipment operation condition of other every profession and trades, prediction, early warning.
In the method that equipment future malfunction time point is predicted of the present invention, for instrument class and the large kind equipment of electric machinery two, when normally being run by equipment, analytical equipment institute Monitoring Data (instrument class) or the data situation by monitoring equipment running current (electric machinery), carry out the analysis of data fluctuations rate, matching stability bandwidth average trend over time, obtain the stability bandwidth average of this equipment at certain time point following, by judging this stability bandwidth average whether in predetermined abnormal ranges, equipment future malfunction time point is predicted, a fast step discovering device abnormal also anticipation trouble spot possibility time of origin, can overhaul in time equipment before this time point to make enterprise, avoid the generation of equipment failure, ensure the normal operation of technique, and improve service life of equipment.
Accompanying drawing explanation
Fig. 1 is stability bandwidth and the time dependent curve of stability bandwidth average in Forecasting Methodology of the present invention;
Fig. 2 is stability bandwidth and the time dependent curve of stability bandwidth average of embodiment 1;
Fig. 3 is the enlarged diagram of the time dependent curve of stability bandwidth average of embodiment 1.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail, can implement according to this with reference to instructions word to make those skilled in the art.
As shown in Figure 1, the invention provides a kind of method that equipment future malfunction time point is predicted, comprise the following steps:
Step one, when equipment runs, within the time interval of setting, gather the service data of this equipment, for instrument and meter kind equipment, directly its Monitoring Data of acquisition is stored in database; Such as, for electric machinery equipment, water pump, blower fan etc., running current can be obtained by the sensor installing its running current of monitoring, it is analyzed, and the time dependent curve of the service data setting up this equipment.At the bivariate table that the data form of Database is time and service data, setting up according to this with time is transverse axis, the historical data curve being the longitudinal axis with filtered service data.Be located at certain time period (t
1, t
2, t
3..., t
n) in should n service data of equipment be (x
1, x
2, x
3..., x
n).
Filtering is the important measures suppressing and prevent to disturb, and in Monitoring Data, some abnormal datas need first to be removed by the method for filtering, in order to avoid produce interference to the analysis of stability bandwidth.The present invention adopts the method for mechanical filtering, and remove the abnormity point in data, as negative value appears in COD value, this does not obviously conform to reality, is be abnormity point, should removes.For abnormity point, while filtering is removed, also should make mark, provide prompting, avoid the undetected situation of fault.
Step 2, the curve determination step value set up according to step one, by the stability bandwidth of the service data of this equipment of derived function, and then obtain stability bandwidth average, with stability bandwidth average for ordinate, time is horizontal ordinate, by stability bandwidth Mean curve m-during least square fitting.Least square method is a kind of mathematical optimization techniques, for finding the optimal function coupling of data.Utilize least square method can try to achieve unknown data easily, and between the data that these are tried to achieve and real data, the quadratic sum of error is minimum.
The computing formula of the stability bandwidth of the service data of this equipment is:
Wherein, k
ifor this equipment at a time t
itime the stability bandwidth of service data, x
ifor this equipment at a time t
itime service data, x
jfor this equipment is at another moment t
jtime service data;
The computing formula of described stability bandwidth average is:
Wherein, p
ifor this equipment at a time t
itime stability bandwidth average, i is the number of service data of this equipment gathered.
Step 3, by step 2 set up time m-stability bandwidth Mean curve variation tendency obtain the stability bandwidth average of this equipment at certain time point following, judge this stability bandwidth average whether in predetermined abnormal ranges, predetermined abnormal ranges is p
t> (1+ μ) p
0or p
t< (1-μ) p
0, wherein, p
tfor this equipment is in the stability bandwidth average of certain time point following, p
0for the stability bandwidth average stationary value of this equipment, μ is fluctuation parameters, μ ∈ (0,100%), concrete numerical value can be regulated according to machine operation voluntarily by user, in the present invention, μ is 10%, if in predetermined abnormal ranges, then judge that this equipment will break down at this time point, this time point is equipment future malfunction time point, and sending maintenance early warning, enterprise should overhaul equipment in time before this time point.
In the described method that equipment future malfunction time point is predicted, described stability bandwidth average stationary value is empirical value or calculates according to the initial launch data after this renewal of the equipment, described initial launch data are 200, also empirical value and calculated value can be considered determine stability bandwidth average stationary value.
In Fig. 1, curve a represents the stability bandwidth of the service data of this equipment, curve b represents the stability bandwidth average of the service data of this equipment, straight line c represents the stability bandwidth average stationary value of the service data of this equipment, curve d represents the predicted value of the stability bandwidth average of the service data of this equipment, moment e is the terminal moment gathering service data, moment f is the critical point that equipment breaks down, and namely enterprise should should overhaul equipment in time before this time point.
Monitoring Data when various instrument and meter kind equipment runs or the running current of electric machinery equipment all have certain undulatory property, there is the change of certain law in its cymomotive force and stability bandwidth variation tendency, such as, after electric machinery equipment regular update, maintenance, its running current is relatively stable, fluctuation tendency is also relatively stable, after long-time running certain hour, equipment weares and teares to some extent, current stability reduces, fluctuation becomes large, and Monitoring Data when running for instrument and meter kind equipment is like this equally.According to the Variation Features of Monitoring Data or running current stability bandwidth, we consider, by a kind of technological means, can form the change curve of Monitoring Data or running current stability bandwidth, i.e. Monitoring Data (running current) rate of change model, and then the operation conditions of consersion unit.Based on this, we propose to carry out modeling to forms data collection (a certain Monitoring Data is at seasonal effect in time series stability bandwidth), analysis, the Monitoring Data of discriminating device when actual motion or the variation tendency of running current stability bandwidth, predict the future malfunction time point of instrument class or electric machinery equipment by stability bandwidth situation of change.Such as, data modeling is carried out to wastewater treatment effluent quality COD value, select time step-length
dt, (the t of acquisition
1, t
1+ ndt) the Monitoring Data stability bandwidth (k of time period
1, k
2..., k
n), stability bandwidth average is (p
2, p
3..., p
n), m-stability bandwidth Mean curve when matching obtains, differentiates stability bandwidth variation tendency, by the future malfunction time point of curvilinear motion law forecasting instrument and meter kind equipment (COD monitor).And for electric machinery equipment, we can carry out stability bandwidth analysis, as certain time period (t by the running current of monitoring this equipment
1, t
2) stability bandwidth of interior water pump electric current be (k '
1, k '
2..., k '
n), stability bandwidth average be (p '
2, p '
3..., p '
n), m-stability bandwidth Mean curve when matching obtains, by the future malfunction time point of curvilinear motion law forecasting electric machinery equipment (water pump).For making the judgement of trouble spot more timely, we define when stability bandwidth average departs from stationary value 10% is fault origination point, time corresponding to this point is future malfunction point time of origin, enterprise can overhaul in time instrument class or electric machinery equipment before this time point, avoid the generation of equipment failure, ensure the normal operation of technique, and improve service life of equipment.
The present invention is directed to the quality index of industrial circle equipment and instrument and meter, early warning is carried out to equipment operation condition.Instrument and meter aspect, we carry out the analysis of Monitoring Data stability bandwidth to Monitoring Indexes instrument and meters such as pH, dissolved oxygen concentration, sludge concentration, flow, liquid level, oxidation-reduction potential, COD, ammonia nitrogen, total phosphorus, total nitrogen, sulphuric dioxide, carbon monoxide, PM2.5, predict these instrumentation devices future malfunction time points; In equipment, can monitor the fluctuation of motor current such as water pump, blower fan, analyze, its future malfunction time point is predicted.The method has certain versatility, not only can be applied to environmental protection industry (epi), all can apply in the monitoring and early warning of the equipment operation condition of other every profession and trades.
The prophylactic repair that the invention solves equipment cannot the problem of generation of look-ahead fault; Equipment is little, the easy uncared-for problem of fault; Plant maintenance is monitored complicated operation continuously, is spent high problem etc.The present invention runs simply, to instrumentation devices without the need to newly-increased instrument, continuous monitoring, the prediction of future malfunction time point can be realized, stability bandwidth analysis is carried out to the Monitoring Data of these representing ambient quality, consersion unit running status or the running current of motor, to the maintenance of equipment, safeguards that there is important practical significance.
Embodiment 1
Certain water factory gathers an influent COD value every 0.5h, and namely step value is 0.5, unit of account hour influent COD stability bandwidth, and computing formula is as follows:
Calculate stability bandwidth average, formula is as follows
Rule of thumb, p
0value gets 2.8.
Being listed as follows of all data:
This water factory's unit hour influent COD stability bandwidth and the time dependent curve of stability bandwidth average is obtained according to above table, as shown in Figure 2, in figure, curve a represents the stability bandwidth of this water factory's unit hour influent COD, curve b represents the stability bandwidth average of this water factory's unit hour influent COD, and straight line c represents the stability bandwidth average stationary value of this water factory's unit hour influent COD.In Fig. 3, curve d represents the stability bandwidth average of this water factory's unit hour influent COD, and straight line e represents the stability bandwidth average stationary value of this water factory's unit hour influent COD.As can be seen from Fig. 2 and Fig. 3 all, starting stage stability bandwidth average fluctuation is comparatively large, therefore during judgment device future malfunction time point at least from 10 hours later.
Although embodiment of the present invention are open as above, but it is not restricted to listed in instructions and embodiment utilization, it can be applied to various applicable the field of the invention completely, for those skilled in the art, can easily realize other amendment, therefore do not deviating under the universal that claim and equivalency range limit, the present invention is not limited to specific details and illustrates here and the legend described.
Claims (9)
1., to the method that equipment future malfunction time point is predicted, it is characterized in that, comprise the following steps:
Step one, when equipment runs, within the time interval of setting, gather the service data of this equipment, and the time dependent curve of the service data setting up this equipment;
Step 2, the curve determination step value set up according to step one, by the stability bandwidth of the service data of this equipment of derived function, and then obtain stability bandwidth average, with stability bandwidth average for ordinate, time is horizontal ordinate, by stability bandwidth Mean curve m-during least square fitting;
Step 3, by step 2 set up time m-stability bandwidth Mean curve variation tendency obtain the stability bandwidth average of this equipment at certain time point following, judge this stability bandwidth average whether in predetermined abnormal ranges, if in predetermined abnormal ranges, then judge that this equipment will break down at this time point, and send maintenance early warning.
2. the method predicted equipment future malfunction time point as claimed in claim 1, it is characterized in that, abnormal ranges predetermined in described step 3 is p
t> (1+ μ) p
0or p
t< (1-μ) p
0, wherein, p
tfor this equipment is in the stability bandwidth average of certain time point following, p
0for the stability bandwidth average stationary value of this equipment, μ is fluctuation parameters, μ ∈ (0,100%).
3. the method predicted equipment future malfunction time point as claimed in claim 2, it is characterized in that, μ is 10%.
4. the method predicted equipment future malfunction time point as claimed in claim 3, it is characterized in that, described stability bandwidth average stationary value is empirical value or calculates according to the initial launch data after this renewal of the equipment.
5. the method predicted equipment future malfunction time point as claimed in claim 4, it is characterized in that, described initial launch data are 200.
6. the method as claimed in claim 3 equipment future malfunction time point predicted, it is characterized in that, in described step 2, the computing formula of the stability bandwidth of the service data of this equipment is:
Wherein, k
ifor this equipment at a time t
itime the stability bandwidth of service data, x
ifor this equipment at a time t
itime service data, x
jfor this equipment is at another moment t
jtime service data;
The computing formula of described stability bandwidth average is:
Wherein, p
ifor this equipment at a time t
itime stability bandwidth average, i is the number of service data of this equipment gathered.
7. the method predicted equipment future malfunction time point as claimed in claim 1, is characterized in that, also comprise in described step one: the service data of this equipment collected is carried out filtering, removes abnormity point, and marks.
8. the method predicted equipment future malfunction time point as claimed in claim 1, it is characterized in that, described equipment is instrument and meter or motor.
9. the method predicted equipment future malfunction time point as claimed in claim 8, it is characterized in that, the service data of described equipment is the Monitoring Data of instrument and meter or the running current of motor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510303320.9A CN104848885B (en) | 2015-06-04 | 2015-06-04 | Method for predicting time of future failure of equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510303320.9A CN104848885B (en) | 2015-06-04 | 2015-06-04 | Method for predicting time of future failure of equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104848885A true CN104848885A (en) | 2015-08-19 |
| CN104848885B CN104848885B (en) | 2017-05-10 |
Family
ID=53848706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510303320.9A Active CN104848885B (en) | 2015-06-04 | 2015-06-04 | Method for predicting time of future failure of equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104848885B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105223293A (en) * | 2015-11-09 | 2016-01-06 | 江苏省电力公司电力科学研究院 | Based on the transformer state method for early warning of oil chromatography on-line monitoring |
| CN105279580A (en) * | 2015-11-13 | 2016-01-27 | 广州供电局有限公司 | Method for predicting number of times of cable external force damage failure and system thereof |
| CN105572540A (en) * | 2015-11-09 | 2016-05-11 | 上海凌翼动力科技有限公司 | Self-adaptive electric automobile high-voltage safety fault diagnosis early-warning positioning monitoring system |
| CN107390646A (en) * | 2016-05-17 | 2017-11-24 | 通用电气公司 | Intelligent management system for factory's balance |
| CN107944573A (en) * | 2017-11-28 | 2018-04-20 | 许继集团有限公司 | A kind of proofreading method and system of Transformer Substation Online Monitoring System data accuracy |
| CN108737193A (en) * | 2018-06-05 | 2018-11-02 | 亚信科技（中国）有限公司 | A kind of failure prediction method and device |
| CN109061390A (en) * | 2018-09-07 | 2018-12-21 | 中电普瑞电力工程有限公司 | A kind of region traveling wave fault positioning method and system |
| CN109919488A (en) * | 2019-03-07 | 2019-06-21 | 中国南方电网有限责任公司 | A kind of protective device Trend Analysis method based on online monitoring data |
| 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 |
| CN111737635A (en) * | 2020-07-01 | 2020-10-02 | 华电潍坊发电有限公司 | Method for predicting future data curve trend based on data trajectory curve |
| CN112990552A (en) * | 2021-02-20 | 2021-06-18 | 节点互联(北京)科技有限公司 | Equipment operation parameter short-time prediction method and system based on change rate |
| CN116260235A (en) * | 2023-03-11 | 2023-06-13 | 傲视恒安科技（北京）有限公司 | Power supply switching method and device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063119A (en) * | 2010-11-11 | 2011-05-18 | 北京三博中自科技有限公司 | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data |
| CN102155988A (en) * | 2010-02-11 | 2011-08-17 | 中国钢铁股份有限公司 | Equipment monitoring and diagnosing method |
| JP2012242985A (en) * | 2011-05-18 | 2012-12-10 | Hitachi-Ge Nuclear Energy Ltd | Equipment abnormality determination device and equipment abnormality determination method |
| JP2013041173A (en) * | 2011-08-18 | 2013-02-28 | Fuji Xerox Co Ltd | Failure prediction system and program |
| CN103824129A (en) * | 2014-02-26 | 2014-05-28 | 国家电网公司 | High-speed rail power quality abnormal condition prewarning method based on dynamic threshold |
| CN104075749A (en) * | 2014-06-30 | 2014-10-01 | 通号通信信息集团有限公司 | Abnormal state detecting method and system for equipment in internet of things |
-
2015
- 2015-06-04 CN CN201510303320.9A patent/CN104848885B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102155988A (en) * | 2010-02-11 | 2011-08-17 | 中国钢铁股份有限公司 | Equipment monitoring and diagnosing method |
| CN102063119A (en) * | 2010-11-11 | 2011-05-18 | 北京三博中自科技有限公司 | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data |
| JP2012242985A (en) * | 2011-05-18 | 2012-12-10 | Hitachi-Ge Nuclear Energy Ltd | Equipment abnormality determination device and equipment abnormality determination method |
| JP2013041173A (en) * | 2011-08-18 | 2013-02-28 | Fuji Xerox Co Ltd | Failure prediction system and program |
| CN103824129A (en) * | 2014-02-26 | 2014-05-28 | 国家电网公司 | High-speed rail power quality abnormal condition prewarning method based on dynamic threshold |
| CN104075749A (en) * | 2014-06-30 | 2014-10-01 | 通号通信信息集团有限公司 | Abnormal state detecting method and system for equipment in internet of things |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105572540A (en) * | 2015-11-09 | 2016-05-11 | 上海凌翼动力科技有限公司 | Self-adaptive electric automobile high-voltage safety fault diagnosis early-warning positioning monitoring system |
| CN105223293B (en) * | 2015-11-09 | 2017-05-17 | 江苏省电力公司电力科学研究院 | Transformer state early warning method based on online monitoring of oil chromatography |
| CN105223293A (en) * | 2015-11-09 | 2016-01-06 | 江苏省电力公司电力科学研究院 | Based on the transformer state method for early warning of oil chromatography on-line monitoring |
| CN105572540B (en) * | 2015-11-09 | 2019-07-05 | 上海凌翼动力科技有限公司 | Adaptive electric automobile high-voltage safety fault diagnosis early warning positioning monitoring system |
| CN105279580B (en) * | 2015-11-13 | 2018-12-25 | 广州供电局有限公司 | Predict that the method and system of the number of external force destructive malfunction occurs for cable |
| CN105279580A (en) * | 2015-11-13 | 2016-01-27 | 广州供电局有限公司 | Method for predicting number of times of cable external force damage failure and system thereof |
| CN107390646A (en) * | 2016-05-17 | 2017-11-24 | 通用电气公司 | Intelligent management system for factory's balance |
| CN107944573A (en) * | 2017-11-28 | 2018-04-20 | 许继集团有限公司 | A kind of proofreading method and system of Transformer Substation Online Monitoring System data accuracy |
| CN108737193A (en) * | 2018-06-05 | 2018-11-02 | 亚信科技（中国）有限公司 | A kind of failure prediction method and device |
| CN109061390A (en) * | 2018-09-07 | 2018-12-21 | 中电普瑞电力工程有限公司 | A kind of region traveling wave fault positioning method and system |
| CN109061390B (en) * | 2018-09-07 | 2023-12-15 | 中电普瑞电力工程有限公司 | Regional traveling wave fault positioning method and system |
| 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 |
| CN109919488A (en) * | 2019-03-07 | 2019-06-21 | 中国南方电网有限责任公司 | A kind of protective device Trend Analysis method based on online monitoring data |
| CN111737635A (en) * | 2020-07-01 | 2020-10-02 | 华电潍坊发电有限公司 | Method for predicting future data curve trend based on data trajectory curve |
| CN111737635B (en) * | 2020-07-01 | 2024-03-19 | 华电潍坊发电有限公司 | Method for predicting future data curve trend based on data track curve |
| CN112990552A (en) * | 2021-02-20 | 2021-06-18 | 节点互联(北京)科技有限公司 | Equipment operation parameter short-time prediction method and system based on change rate |
| CN116260235A (en) * | 2023-03-11 | 2023-06-13 | 傲视恒安科技（北京）有限公司 | Power supply switching method and device, electronic equipment and readable storage medium |
| CN116260235B (en) * | 2023-03-11 | 2023-08-22 | 傲视恒安科技（北京）有限公司 | Power supply switching method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104848885B (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104848885A (en) | Method for predicting time of future failure of equipment | |
| CN104793605B (en) | A kind of method that utilization normal distribution judges equipment fault | |
| CN110320892B (en) | Sewage treatment equipment fault diagnosis system and method based on L asso regression | |
| CN108375715B (en) | Power distribution network line fault risk day prediction method and system | |
| CN103969066B (en) | The system and method for monitoring the process of operation | |
| CN103758696A (en) | SCADA (supervisory control and data acquisition) temperature parameter based wind turbine set security evaluation method | |
| CN102252843B (en) | Assessment method for rolling bearing performance variation | |
| CN111898691A (en) | River sudden water pollution early warning tracing method, system, terminal and medium | |
| CN102393299A (en) | Method for quantitatively calculating operational reliability of rolling bearing | |
| CN102541013A (en) | Remote monitoring, early warning and fault-diagnosing system and method for anodic protection device | |
| CN103321839A (en) | Fan vibration monitoring method and system as well as fan monitor | |
| CN110162555A (en) | A kind of fired power generating unit start and stop and drop power output measure of supervision | |
| CN205644200U (en) | Real -time water utilities monitoring system of thermal power plant | |
| CN104750144B (en) | Method of early warning operating condition of equipment | |
| CN115806344B (en) | ORP (integrated pressure and pressure) control precise aeration system | |
| CN114252216B (en) | Detection method for lubricating oil leakage of gas turbine | |
| CN202433761U (en) | Remote monitoring, warning and fault diagnosis system of anode protecting device based on Internet of things | |
| CN110083131A (en) | Technological parameter on-line early warning method and readable storage medium storing program for executing based on amplitude of variation | |
| CN104133437A (en) | Continuous-type chemical-engineering device and performance indicator real-time evaluation method and device thereof | |
| CN108537174B (en) | Online monitoring method and system for running state of rotating machinery under time-varying working condition | |
| CN111341396A (en) | Method and system for evaluating material corrosion safety in atmospheric environment | |
| Walker et al. | Transformer Health Monitoring Using Dissolved Gas Analysis | |
| CN104699056A (en) | Sewage treatment process unit running performance monitoring method | |
| CN116562580B (en) | Waste water and waste gas treatment system and method for lithium carbonate production workshop | |
| CN113903099B (en) | Equipment monitoring method and system based on scada |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100048 room C03, room 7, building 91, No. three West Third Ring Road, Beijing, Haidian District Applicant after: BEIJING JINKONG DATA TECHNOLOGY CO., LTD. Address before: 100048 room C03, room 7, building 91, No. three West Third Ring Road, Beijing, Haidian District Applicant before: Beijing Jinkong Automatic Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |