CN102063119A - Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data - Google Patents
Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data Download PDFInfo
- Publication number
- CN102063119A CN102063119A CN 201010541512 CN201010541512A CN102063119A CN 102063119 A CN102063119 A CN 102063119A CN 201010541512 CN201010541512 CN 201010541512 CN 201010541512 A CN201010541512 A CN 201010541512A CN 102063119 A CN102063119 A CN 102063119A
- Authority
- CN
- China
- Prior art keywords
- data
- parameter
- equipment
- dcs
- fault
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an equipment failure prediction method based on point polling data and DCS (Data Communication System) online data, which comprises the steps of: establishing an equipment overhauling information base, wherein the overhauling information base comprises equipment point polling data and DCS online data as well as equipment overhauling data; carrying out relevance storage on the equipment point polling data, the DCS online data and equipment overhauling data; and then periodically carrying out data matching on data of equipment in current state and data in the overhauling information base, when the data of the equipment in the current state are matched with some overhauling data in the overhauling information base, predicting a failure type of the equipment according to the data in the overhauling information base and predicting the failure generating time. With the data accumulation of the data in the equipment overhauling information base, most of equipment failure types are predicted, an effective basis is provided for the predictable overhauling of the equipment and the basic protection is provided for the normal production.
Description
Technical field
The present invention relates to a kind of equipment failure forecast method, particularly a kind ofly patrol and examine the equipment failure Forecasting Methodology of data and DCS online data, mainly be aimed at the prediction of equipment failure non sudden, under the state gradual change situation based on point.Described point is patrolled and examined data and is meant and equipment is being carried out spot check and/or patrolling and examining the device parameter service data that writes down in the process, described DCS online data is meant the device parameter service data that collects in the DCS system, DCS is the english abbreviation of Distributed Control System, and the DCS system claims dcs or collective and distributive type control system again.
Background technology
In industrial processes, the normal operation of production equipment is to ensure to produce the pacing items of carrying out smoothly.In order to guarantee the normal operation of production equipment, need often equipment to be carried out repair and maintenance.
Overhaul of the equipments can be divided into fault maintenance, preventative maintenance and three kinds of modes of planned maintenance.The fault maintenance is meant after equipment is out of order and overhauls passively.Preventative maintenance is meant that discovering device is about to be out of order, in conjunction with overhauling the opportunity that condition of production arrangement is suitable.Planned maintenance is meant according to certain cycle equipment is overhauled no matter whether equipment is out of order.
In three kinds of modes of overhaul of the equipments, the influence minimum of preventative maintenance to producing is so in actual production, a lot of enterprises adopt preventative maintenance.
The foundation of preventative maintenance decision-making at present mainly is the warning of DCS system and artificial checking, shortcoming is to find fault as early as possible, prepare so that early do maintenance, tend to take place owing to reasons such as spare part can not be in time cause service work to influence the situation of ordinary production.In addition, owing to can not find fault early, the situation of the state of affairs that also can break down sometimes extension results in greater loss.Therefore need a kind ofly can carry out forecast method to equipment failure.
Summary of the invention
The invention provides and a kind ofly patrol and examine the equipment failure forecast method of data, DCS online data based on point, the time that fault type that will take place equipment and fault take place predicts, normally provides basic guarantee for what produce.Described point is patrolled and examined data and is meant and equipment is being carried out spot check and/or patrolling and examining the device parameter service data that writes down in the process, described DCS online data is meant the device parameter service data that collects in the DCS system, DCS is the english abbreviation of Distributed Control System, and the DCS system claims dcs or collective and distributive type control system again.
Technical scheme of the present invention is:
A kind of equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point, it is characterized in that, apparatus for establishing maintenance information bank, comprise in the described maintenance information bank that the equipment point patrols and examines data and DCS online data and overhaul of the equipments data, and the equipment point is patrolled and examined data and DCS online data and overhaul of the equipments data carry out association store; Periodically the data of equipment current generation being carried out Data Matching with the data in the maintenance information bank then handles, when the data of equipment current generation and certain overhaul data in the maintenance information bank are complementary, equipment is carried out the prediction of fault type and the prediction of time of failure according to the data in the maintenance information bank; Described point is patrolled and examined data and is meant and equipment is being carried out spot check and/or patrolling and examining the device parameter service data that writes down in the process, described DCS online data is meant the device parameter service data that collects in the DCS system, DCS is the english abbreviation of Distributed Control System, and the DCS system claims dcs or collective and distributive type control system again.
The method that described overhaul of the equipments information bank is set up comprises that noting the equipment point in chronological order patrols and examines data and DCS online data and all previous overhaul of the equipments data, described overhaul of the equipments data comprise overhaul of the equipments time and equipment failure description, and described equipment failure is described and represented with fault type.
Described point is patrolled and examined data and is comprised organoleptic indicator's data and apparatus measures data, described organoleptic indicator's data numeral that quantizes.
Described Data Matching is only handled and is carried out at the supplemental characteristic that is associated with equipment failure, when carrying out the Data Matching processing, at first carries out the relation analysis of parameter that is associated with equipment failure.
The method of described relation analysis of parameter may further comprise the steps: 1) service data with each time fault of each parameter in the overhaul of the equipments information bank fits to straight line, the corresponding fitting a straight line of the service data of each fault of each parameter; 2) judge that the slope of each time failure operation data fitting straight line of a certain parameter is whether consistent, if the slope of fitting a straight line is all greater than zero or all less than zero, then this parameter is associated with the fault of current device, if the fitting a straight line slope has greater than 0 and also has less than 0, then the fault of this parameter and current device has nothing to do.
The method that described Data Matching is handled may further comprise the steps: 1) each parameter service data of current device is fitted to curve, the corresponding matched curve of the current service data of each parameter; 2) service data that will overhaul each time fault of the relevant parameter in the information bank also fits to curve, the corresponding matched curve of each failure operation data of each parameter; 3) adopt matching algorithm, carry out matching treatment one by one at curve with the service data match of each time fault of the relevant parameter in the curve of the current service data match of each parameter of current device and the maintenance information bank; 4) judge whether Satisfying Matching Conditions of matching result, if Satisfying Matching Conditions stops matching treatment; 5) if Satisfying Matching Conditions is not then proceeded matching treatment, up to the maintenance information bank in the service data of each time fault mate and finish.
Described matching algorithm comprises following content:
1) the similarity A of the current service data matched curve of calculating parameter j and the i time failure operation data fitting curve
j,
The curvilinear function of setting parameter j in current service data matched curve is x=f
Bj(y), the curvilinear function in the i time failure operation data fitting curve is x=f
Aj(y); The numerical value of x representation parameter wherein, the acquisition time of y representation parameter, Δ Y are represented the time period of the current operational factor record of collecting device, according to device type and requirement definition, then
Wherein, for any k value, work as f
Bj(Y
I+k)＞f
Aj(Y
k) time, S
k=f
Aj(Y
k), L
k=f
Bj(Y
I+k), otherwise, S
k=f
Bj(Y
I+k), L
k=f
Aj(Y
k), n is an integer, expression is divided into the n equal portions with Δ Y.
2) the overall similarity A of current each the parameter service data matched curve of calculating and the i time failure operation data fitting curve, A=A
1* A
2* A
3* ... * A
m, wherein m represents the number of parameter.
Described matching condition is: for all A
j(j=0,1,2 ... m), A
j〉=A
Ss, and A 〉=A
As, then the match is successful; For any one A
j(j=0,1,2 ... m), A
j＜A
Ss, or A＜A
As, then it fails to match; Wherein, A
SsBe setting value to the requirement of single parameter matching similarity degree, A
AsIt is setting value to the requirement of whole parameter matching similarity degree.
Described fault type prediction and time of failure forecast method are meant that when Satisfying Matching Conditions the fault type that the current device of described prediction will take place is the fault type of the overhaul data record that overhauls that time fault of Satisfying Matching Conditions in the information bank; The time that fault will take place obtains by calculating, and establishes fault and estimates to pass through Δ T again
mTime takes place, and the data in the maintenance information bank are at Y
iConstantly be complementary, then Δ T with current data
m=Y
T-(Y
i+ Δ Y), Y
TBe the time of certain corresponding in maintenance information bank fault generation.
Technique effect of the present invention:
Equipment failure Forecasting Methodology provided by the invention along with the data accumulation in the overhaul of the equipments information bank, can be predicted most equipment failure type, for the preventative maintenance of equipment provides effective foundation, normally provides basic guarantee for what produce.
Description of drawings
Fig. 1 is the synoptic diagram of the content of a certain equipment in the maintenance information bank.
Fig. 2 is the correlation analysis synoptic diagram of equipment failure and parameter.
Fig. 3 is a Data Matching disposal route synoptic diagram.
Fig. 4 is a Data Matching algorithm synoptic diagram.
Embodiment
Below in conjunction with accompanying drawing the specific embodiment of the present invention is elaborated:
A kind of equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point, it is characterized in that, apparatus for establishing maintenance information bank, comprise in the described maintenance information bank that the equipment point patrols and examines data and DCS online data and overhaul of the equipments data, and the equipment point is patrolled and examined data and DCS online data and overhaul of the equipments data carry out association store; Periodically the data of equipment current generation being carried out Data Matching with the data in the maintenance information bank then handles, when the data of equipment current generation and certain overhaul data in the maintenance information bank are complementary, equipment is carried out the prediction of fault type and the prediction of time of failure according to the data in the maintenance information bank; Described point is patrolled and examined data and is meant and equipment is being carried out spot check and/or patrolling and examining the device parameter service data that writes down in the process, described DCS online data is meant the device parameter service data that collects in the DCS system, DCS is the english abbreviation of Distributed Control System, and the DCS system claims dcs or collective and distributive type control system again.
Implementation method of the present invention comprises the method for building up and the equipment failure forecast method of overhauling information bank.
The method for building up of overhaul of the equipments information bank comprises, comprise that noting the equipment point in chronological order patrols and examines data and DCS online data and all previous overhaul of the equipments data, the overhaul of the equipments data comprise overhaul of the equipments time and equipment failure description, and equipment failure is described and represented with fault type.
In order to carry out the equipment failure prediction, need to obtain device-dependent data as analysis foundation.In actual applications, we will comprise that at first a little patrolling and examining the online historical data of historical data, DCS and all previous overhaul of the equipments content record that obtain gets off to form database, is called the maintenance information bank with this database about each parameter service data of equipment.Wherein all previous maintenance content comprises overhaul of the equipments time and equipment failure description, and equipment failure is described with the equipment failure type.
Fig. 1 is the content synoptic diagram of parameter in the maintenance information bank of a certain equipment.In the life cycle of a certain equipment, the process that the meeting generation repeatedly moves and overhauls, the service data of equipment all parameters is during this period got off (comprise and a little patrol and examine data and DCS online data) according to sequence of event, and set up corresponding relation with the equipment failure type, just device parameter service data record and overhaul of the equipments data recording are carried out association store, use during in order to the equipment failure prediction.The maintenance information bank of present embodiment comprises equipment failure maintenance content and facilities plan maintenance content, does not comprise the content of facilities plan maintenance.Among Fig. 1: m, n, j are integer, m represents the number of times that fault takes place, n represents the number of parameters of this equipment, and j represents the number of the record data of a certain parameter in the logout in certain fault data, and the j value of a plurality of parameters of a plurality of fault datas may be inequality.The method for expressing of data in the logout.With P-1-2-3 is example, and it represents the 3rd data of the logout in the 2nd fault data of the 1st parameter.
In point is patrolled and examined, some data is organoleptic indicator's data of people, some data is measurement data of utilizing instrument to obtain, for the ease of processing to data, this method requirement organoleptic indicator's data to the people in point is patrolled and examined are carried out quantificational description, and for example the description to vibration no longer is " not vibrating ", " slight vibration ", " high vibration " etc., and the description to vibration that replaces is the numeral between 0 to 10,0 expression is not vibrated, the most violent vibration of 10 expressions.Like this, all carried out digitizing about all parameters of a certain equipment, mathematical method easy to use is handled supplemental characteristic.
The equipment failure forecast method comprises, periodically the data of equipment current generation are mated with the data in the maintenance information bank, when the data of equipment current generation are complementary with the data of overhauling certain fault in the information bank, equipment is carried out the prediction of fault type and the prediction of time of failure according to the data in the maintenance information bank.
The equipment failure forecast method may further comprise the steps:
The ■ relation analysis of parameter.A certain equipment has a plurality of parameters, and not all parameter is all relevant with equipment failure, and which parameter this will analyze is associated with equipment failure, and this analytic process is called relation analysis of parameter.Relation analysis of parameter is to provide foundation for the selection of giving the used parameter of failure prediction.
The ■ Data Matching is handled.Data Matching is handled and to be meant that supplemental characteristic that equipment is current and the data in the maintenance information bank mate, if supplemental characteristic and the Data Matching of overhauling certain fault in the information bank that discovering device is current, illustrate that the current device state is similar to state at that time, the situation that equipment failure takes place also may be similar.
The judgement of ■ fault type and time of origin.If in the maintenance information bank, found the overhaul data of a coupling, can predict that then the pairing fault type of this overhaul data can take place this equipment once more.Check the time period of Data Matching point and fault origination point, can dope the time that fault will take place.
For convenience of description, this paper failure definition time of origin is the time that equipment is overhauled.
Fig. 2 is the correlation analysis synoptic diagram of equipment failure and parameter, the numerical value of x axle representation parameter wherein, the acquisition time of y axle representation parameter.Shown in Figure 2 is the service data record of the repeatedly fault of a certain equipment.In the drawings, the service data with each time fault of each parameter fits to straight line, the corresponding fitting a straight line of the service data of each fault of each parameter; If the slope of the service data fitting a straight line of each time fault of a parameter all greater than 0 or all less than 0, thinks that then this parameter is relevant with the fault of current device, for example the parameter a among Fig. 2.If the slope of the service data fitting a straight line of each time fault of a parameter has greater than 0 and also has less than 0, think that then the fault of this parameter and current device is irrelevant, for example the parameter b among Fig. 2.
Data Matching is only handled and is carried out at the parameter relevant with the fault of equipment.At first the service data with the current logout of equipment fits to curve, the corresponding matched curve of the current service data of each parameter; The service data that to overhaul the repeatedly fault of the relevant parameter in the information bank then also fits to curve, the corresponding matched curve of each failure operation data of each parameter; The curve of the log data match of each time fault of each parameter in the curve of each parameter service data match of current device and the overhaul of the equipments information bank is carried out matching treatment one by one; If the energy Satisfying Matching Conditions, then the current operation conditions of devices illustrated can be carried out failure prediction according to this, otherwise not process with situation was similar at that time.
Fig. 3 has illustrated the situation that the log data of certain equipment failure in current log data and the overhaul of the equipments information bank is mated, the numerical value of x axle representation parameter wherein, the acquisition time of y axle representation parameter.The data fitting of the current logout of Fig. 3 b indication equipment becomes curve, and the log data that Fig. 3 a represents to overhaul the i time fault in the information bank fits to curve, and Δ Y is the time period of the current operational factor record of equipment, according to device type and requirement definition.In the drawings, in Fig. 3 a, find the shadow pattern among one section shadow pattern and Fig. 3 b to be complementary exactly.Concrete treatment scheme is:
When 1. initial, Y
i=0.
2. judge Y
T-Y
iWhether more than or equal to Δ Y, Y
TThe moment of representing the i time fault generation.
3. if, treatment scheme continues, if not, stop matching treatment.
4. get Y
i+ Δ Y uses matching algorithm to mate.
5. if Satisfying Matching Conditions stops matching treatment.
6. if Satisfying Matching Conditions is not then got Y
i+ Y
s+ Δ Y, wherein Y
SThe step-length that moves down for shadow pattern.
7. 2. treatment scheme forwards to.
Fig. 4 is a Data Matching algorithm synoptic diagram, the numerical value of x axle representation parameter wherein, the acquisition time of y axle representation parameter.
Δ Y is divided into the n equal portions along the y direction of principal axis, and the x value of the intersection point of the cut-off rule of two groups of data and each self-corresponding curve is relatively represented the similarity degree of two groups of data with the mean value of the ratio of the x value of all intersection points.Concrete treatment scheme is:
1. Δ Y is divided into the n equal portions, n is an integer, and the result of the big more coupling of n is accurate more.
2. compare the pairing shadow pattern of each parameter in two groups of data one by one.With the b of parameter among Fig. 41 figure and a figure be the example comparison, the curvilinear function of setting parameter 1 in b figure is x=f
B1(y), the curvilinear function of parameter 1 in a figure is x=f
A1When (y), comparing is exactly will be with the Y among the b figure
iX value f on the pairing curve
B1(Y
i) with a figure in Y
0Pairing x value f
A1(Y
0) compare, with the Y among the b figure
I+1X value f on the pairing curve
B1(Y
I+1) with a figure in Y
1Pairing x value f
A1(Y
1) compare, opinion pushes away successively, with the Y among the b figure
I+nX value f on the pairing curve
B1(Y
I+n) with a figure in Y
nPairing x value f
A1(Y
n) compare.If the similarity degree of parameter 1 is A among Fig. 4
1, A then
1Computing formula be:
Wherein, for any k value, work as f
B1(Y
I+k)＞f
A1(Y
k) time, S
k=f
A1(Y
k), L
k=f
B1(Y
I+k), otherwise, S
k=f
B1(Y
I+k), L
k=f
A1(Y
k).
Use identical method, can calculate A
2, A
3A
m, wherein m represents the number of parameter.
3. calculate the global similarity degree.If overall similarity is A, then computing formula is:
A＝A
1×A
2×A
3×…×A
m
4. matching result.The possibility of result has two kinds: the one, and maintenance does not have the log data of the fault of Satisfying Matching Conditions in the information bank, is called that it fails to match.Another is the log data that maintenance has the fault of Satisfying Matching Conditions in the information bank, is called that the match is successful.Concrete matching condition is as follows:
The match is successful: for all A
j(j=0,1,2 ... m), A
j〉=A
Ss, and A 〉=A
As
It fails to match: for any one A
j(j=0,1,2 ... m), A
j＜A
Ss, or A＜A
As
Wherein, A
SsBe setting value to the requirement of single parameter matching similarity degree, A
AsIt is setting value to the requirement of whole parameter matching similarity degree.
After Data Matching is finished dealing with,, do not carry out the fault pre-alarming prompting if it fails to match.If the match is successful, then to carry out early warning to the fault type that will take place and the time of generation.The fault type that will take place is the fault type in the maintenance record that overhauls that time fault of Satisfying Matching Conditions in the information bank.The time that fault will take place obtains by calculating, and establishes fault and estimates to pass through Δ T again
mTime takes place, and is example with Fig. 4, suppose to overhaul data in the information bank at Y
iConstantly be complementary, then Δ T with current data
m=Y
T-(Y
i+ Δ Y), Y
TBe the time that certain corresponding in maintenance information bank fault takes place, Δ Y is the time period of the current operational factor record of equipment, according to device type and requirement definition.
Should be pointed out that the above embodiment can make those skilled in the art more fully understand the invention, but do not limit the present invention in any way creation.Therefore, although this instructions and embodiment have been described in detail to the invention,, it will be appreciated by those skilled in the art that still and can make amendment or be equal to replacement the invention; And all do not break away from the technical scheme and the improvement thereof of the spirit and scope of the invention, and it all is encompassed in the middle of the protection domain of the invention patent.
Claims (9)
1. equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point, it is characterized in that, apparatus for establishing maintenance information bank, comprise in the described maintenance information bank that the equipment point patrols and examines data and DCS online data and overhaul of the equipments data, and the equipment point is patrolled and examined data and DCS online data and overhaul of the equipments data carry out association store; Periodically the data of equipment current generation being carried out Data Matching with the data in the maintenance information bank then handles, when the data of equipment current generation and certain overhaul data in the maintenance information bank are complementary, equipment is carried out the prediction of fault type and the prediction of time of failure according to the data in the maintenance information bank; Described point is patrolled and examined data and is meant and equipment is being carried out spot check and/or patrolling and examining the device parameter service data that writes down in the process, described DCS online data is meant the device parameter service data that collects in the DCS system, DCS is the english abbreviation of Distributed Control System, and the DCS system claims dcs or collective and distributive type control system again.
2. equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point according to claim 1, it is characterized in that, the method that described overhaul of the equipments information bank is set up comprises that noting the equipment point in chronological order patrols and examines data and DCS online data and all previous overhaul of the equipments data, described overhaul of the equipments data comprise overhaul of the equipments time and equipment failure description, and described equipment failure is described and represented with fault type.
3. according to claim 2ly patrol and examine the equipment failure Forecasting Methodology of data and DCS online data based on point, it is characterized in that described point is patrolled and examined data and comprised organoleptic indicator's data and apparatus measures data, described organoleptic indicator's data are with the numeral that quantizes.
4. equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point according to claim 1, it is characterized in that, described Data Matching is only handled and is carried out at the supplemental characteristic that is associated with equipment failure, when carrying out the Data Matching processing, at first carry out the relation analysis of parameter that is associated with equipment failure.
5. equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point according to claim 4, it is characterized in that, the method of described relation analysis of parameter may further comprise the steps: 1) service data with each time fault of each parameter in the overhaul of the equipments information bank fits to straight line, the corresponding fitting a straight line of the service data of each fault of each parameter; 2) judge that the slope of each time failure operation data fitting straight line of a certain parameter is whether consistent, if the slope of fitting a straight line is all greater than zero or all less than zero, then this parameter is associated with the fault of current device, if the fitting a straight line slope has greater than 0 and also has less than 0, then the fault of this parameter and current device has nothing to do.
6. equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point according to claim 5, it is characterized in that, the method that described Data Matching is handled may further comprise the steps: 1) each parameter service data of current device is fitted to curve, the corresponding matched curve of the current service data of each parameter; 2) service data that will overhaul each time fault of the relevant parameter in the information bank also fits to curve, the corresponding matched curve of each failure operation data of each parameter; 3) adopt matching algorithm, the curve of the service data match of each time fault of the relevant parameter in the curve of each parameter service data match of current device and the maintenance information bank is carried out matching treatment one by one; 4) judge whether Satisfying Matching Conditions of matching result, if Satisfying Matching Conditions stops matching treatment; 5) if Satisfying Matching Conditions is not then proceeded matching treatment, up to the maintenance information bank in the service data of each time fault mate and finish.
7. according to claim 6ly patrol and examine the equipment failure Forecasting Methodology of data and DCS online data, it is characterized in that described matching algorithm comprises following content based on point:
1) the similarity A of the current service data matched curve of calculating parameter j and the i time failure operation data fitting curve
j,
The curvilinear function of setting parameter j in current service data matched curve is x=f
Bj(y), the curvilinear function in the i time failure operation data fitting curve is x=f
Aj(y); The numerical value of x representation parameter wherein, the acquisition time of y representation parameter, Δ Y are represented the time period of the current operational factor record of collecting device, according to device type and requirement definition, then
Wherein, for any k value, work as f
Bj(Y
I+k)＞f
Aj(Y
k) time, S
k=f
Aj(Y
k), L
k=f
Bj(Y
I+k), otherwise, S
k=f
Bj(Y
I+k), L
k=f
Aj(Y
k), n is an integer, expression is divided into the n equal portions with Δ Y.
2) the overall similarity A of current each the parameter service data matched curve of calculating and the i time failure operation data fitting curve, A=A
1* A
2* A
3* ... * A
m, wherein m represents the number of parameter.
8. according to claim 7ly patrol and examine the equipment failure Forecasting Methodology of data and DCS online data, it is characterized in that described matching condition is: for all A based on point
j(j=0,1,2 ... m), A
j〉=A
Ss, and A 〉=A
As, then the match is successful; For any one A
j(j=0,1,2 ... m), A
j＜A
Ss, or A＜A
As, then it fails to match; Wherein, A
SsBe setting value to the requirement of single parameter matching similarity degree, A
AsIt is setting value to the requirement of whole parameter matching similarity degree.
9. equipment failure Forecasting Methodology of patrolling and examining data and DCS online data based on point according to claim 8, it is characterized in that, described fault type prediction and time of failure forecast method are meant that when Satisfying Matching Conditions the fault type that the current device of described prediction will take place is the fault type of the overhaul data record that overhauls that time fault of Satisfying Matching Conditions in the information bank; The time that fault will take place obtains by calculating, and establishes fault and estimates to pass through Δ T again
mTime takes place, and the data in the maintenance information bank are at Y
iConstantly be complementary, then Δ T with current data
m=Y
T-(Y
i+ Δ Y), Y
TBe the time of certain corresponding in maintenance information bank fault generation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010541512 CN102063119B (en) | 2010-11-11 | 2010-11-11 | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010541512 CN102063119B (en) | 2010-11-11 | 2010-11-11 | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102063119A true CN102063119A (en) | 2011-05-18 |
| CN102063119B CN102063119B (en) | 2012-10-24 |
Family
ID=43998427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010541512 Active CN102063119B (en) | 2010-11-11 | 2010-11-11 | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102063119B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020773A (en) * | 2012-12-13 | 2013-04-03 | 广州市特种机电设备检测研究院 | Elevator intelligent checking information management system based on radio frequency identification device (RFID) |
| CN103839302A (en) * | 2014-02-24 | 2014-06-04 | 西安西热控制技术有限公司 | Intelligent inspection system and method in thermal power plant |
| CN103887877A (en) * | 2014-02-24 | 2014-06-25 | 西安西热控制技术有限公司 | intelligent routing inspection system reverse prompting terminal and method for the same |
| CN104464232A (en) * | 2014-12-04 | 2015-03-25 | 广东振声科技股份有限公司 | Forecasting and early warning detection model in emulsion explosive production technological process based on danger source |
| CN104750144A (en) * | 2015-02-03 | 2015-07-01 | 北京金控自动化技术有限公司 | Method of early warning operating condition of equipment |
| CN104848885A (en) * | 2015-06-04 | 2015-08-19 | 北京金控自动化技术有限公司 | Method for predicting time of future failure of equipment |
| CN103698637B (en) * | 2013-12-25 | 2016-05-18 | 云南电力调度控制中心 | A kind of electric power critical Indexes Abnormality method for quick and device |
| CN107533733A (en) * | 2015-05-21 | 2018-01-02 | 三菱电机株式会社 | Long-Range Surveillance Unit, remotely monitor maintenance system, remote monitoring method and remotely monitor program |
| CN108022020A (en) * | 2017-12-15 | 2018-05-11 | 东软集团股份有限公司 | Equipment fault management method, device, storage medium and electronic equipment |
| CN108037722A (en) * | 2017-12-25 | 2018-05-15 | 山东星火科学技术研究院 | Five in one new energy sells demonstration centre vestibular apparatus control system |
| 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 |
| CN108880907A (en) * | 2018-07-06 | 2018-11-23 | 上海财经大学 | Network equipment automation inspection maintenance system based on running log |
| CN109032058A (en) * | 2018-07-23 | 2018-12-18 | 华电重工股份有限公司 | A kind of device management method, device, system and storage medium |
| CN113932849A (en) * | 2021-09-30 | 2022-01-14 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Fault detection method of mining equipment and terminal equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040199573A1 (en) * | 2002-10-31 | 2004-10-07 | Predictive Systems Engineering, Ltd. | System and method for remote diagnosis of distributed objects |
| CN1547145A (en) * | 2003-12-08 | 2004-11-17 | 西安交通大学 | Dynamic detecting and ensuring method for equipment operating status data quality |
| CN101477375A (en) * | 2009-01-05 | 2009-07-08 | 东南大学 | Sensor data verification method based on matrix singular values association rules mining |
| CN101498931A (en) * | 2008-12-26 | 2009-08-05 | 北京三博中自科技有限公司 | Communication method for assembly line RFID interface control unit and upper computer |
| CN101582195A (en) * | 2009-06-09 | 2009-11-18 | 深圳中兴力维技术有限公司 | Method for generating alarm in dynamic environment monitoring system |
-
2010
- 2010-11-11 CN CN 201010541512 patent/CN102063119B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040199573A1 (en) * | 2002-10-31 | 2004-10-07 | Predictive Systems Engineering, Ltd. | System and method for remote diagnosis of distributed objects |
| CN1547145A (en) * | 2003-12-08 | 2004-11-17 | 西安交通大学 | Dynamic detecting and ensuring method for equipment operating status data quality |
| CN101498931A (en) * | 2008-12-26 | 2009-08-05 | 北京三博中自科技有限公司 | Communication method for assembly line RFID interface control unit and upper computer |
| CN101477375A (en) * | 2009-01-05 | 2009-07-08 | 东南大学 | Sensor data verification method based on matrix singular values association rules mining |
| CN101582195A (en) * | 2009-06-09 | 2009-11-18 | 深圳中兴力维技术有限公司 | Method for generating alarm in dynamic environment monitoring system |
Non-Patent Citations (2)
| Title |
|---|
| 《北京航空航天大学学报》 20070515 李青等 基于案例推理方法在飞机故障诊断中的应用 622-626 1-9 第33卷, 第05期 * |
| 《辽宁工程技术大学学报》 19980430 李琳等 三相异步电动机状态计算机检测与处理 203-206 1-9 第17卷, 第02期 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020773A (en) * | 2012-12-13 | 2013-04-03 | 广州市特种机电设备检测研究院 | Elevator intelligent checking information management system based on radio frequency identification device (RFID) |
| CN103698637B (en) * | 2013-12-25 | 2016-05-18 | 云南电力调度控制中心 | A kind of electric power critical Indexes Abnormality method for quick and device |
| CN103839302A (en) * | 2014-02-24 | 2014-06-04 | 西安西热控制技术有限公司 | Intelligent inspection system and method in thermal power plant |
| CN103887877A (en) * | 2014-02-24 | 2014-06-25 | 西安西热控制技术有限公司 | intelligent routing inspection system reverse prompting terminal and method for the same |
| CN103839302B (en) * | 2014-02-24 | 2016-03-02 | 西安西热控制技术有限公司 | A kind of thermal power plant's intelligent inspection system and method |
| CN103887877B (en) * | 2014-02-24 | 2016-08-17 | 西安西热控制技术有限公司 | A kind of thermal power plant's reverse prompt terminal of intelligent inspection system and method |
| CN104464232A (en) * | 2014-12-04 | 2015-03-25 | 广东振声科技股份有限公司 | Forecasting and early warning detection model in emulsion explosive production technological process based on danger source |
| CN104750144A (en) * | 2015-02-03 | 2015-07-01 | 北京金控自动化技术有限公司 | Method of early warning operating condition of equipment |
| CN104750144B (en) * | 2015-02-03 | 2017-01-11 | 北京金控数据技术股份有限公司 | Method of early warning operating condition of equipment |
| CN107533733A (en) * | 2015-05-21 | 2018-01-02 | 三菱电机株式会社 | Long-Range Surveillance Unit, remotely monitor maintenance system, remote monitoring method and remotely monitor program |
| CN107533733B (en) * | 2015-05-21 | 2018-12-28 | 三菱电机株式会社 | Long-Range Surveillance Unit and method, long-range monitoring maintenance system and recording medium |
| CN104848885B (en) * | 2015-06-04 | 2017-05-10 | 北京金控数据技术股份有限公司 | Method for predicting time of future failure of equipment |
| CN104848885A (en) * | 2015-06-04 | 2015-08-19 | 北京金控自动化技术有限公司 | Method for predicting time of future failure of equipment |
| CN108022020A (en) * | 2017-12-15 | 2018-05-11 | 东软集团股份有限公司 | Equipment fault management method, device, storage medium and electronic equipment |
| CN108022020B (en) * | 2017-12-15 | 2020-09-18 | 东软集团股份有限公司 | Equipment fault management method and device, storage medium and electronic equipment |
| CN108037722A (en) * | 2017-12-25 | 2018-05-15 | 山东星火科学技术研究院 | Five in one new energy sells demonstration centre vestibular apparatus control system |
| 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 |
| CN108880907A (en) * | 2018-07-06 | 2018-11-23 | 上海财经大学 | Network equipment automation inspection maintenance system based on running log |
| CN109032058A (en) * | 2018-07-23 | 2018-12-18 | 华电重工股份有限公司 | A kind of device management method, device, system and storage medium |
| CN113932849A (en) * | 2021-09-30 | 2022-01-14 | 深圳市中金岭南有色金属股份有限公司凡口铅锌矿 | Fault detection method of mining equipment and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102063119B (en) | 2012-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102063119B (en) | Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data | |
| CN102880115B (en) | A kind of numerically controlled machine remote cooperative diagnosis system based on Internet of Things | |
| CN107851057A (en) | The Dynamic Execution of forecast model | |
| CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
| CN105046402A (en) | State evaluating method applied to secondary equipment of intelligent transformer station | |
| CN113112635B (en) | Conventional inspection system for intelligent equipment | |
| CN106650963A (en) | Electric car charging equipment detection and maintenance managing method and device | |
| CN104218570A (en) | Method and system for online evaluating overall measuring errors of electric energy measuring device | |
| CN106503807A (en) | A kind of modified model RCM analysis methods and the dynamic appliance integrality evaluation system based on which | |
| KR20110048771A (en) | The engineering platform system of the electric power- telemetrics and its using method | |
| CN107656518A (en) | A kind of system failure inference method | |
| CN110569997A (en) | charging station operation maintenance method based on multi-dimensional data system | |
| CN113177650A (en) | Predictive maintenance method and device for wagon compartment | |
| CN106802599A (en) | A kind of diagnosing fault of power transformer system based on expert database | |
| CN115376296A (en) | Production fault early warning system based on industrial internet | |
| Deng et al. | Analysis of failures and influence factors of critical infrastructures: a case of metro | |
| CN104794771B (en) | One kind patrols inspection automatic planning and a device | |
| CN117592975A (en) | Operation and maintenance decision processing method and system for electromechanical equipment of expressway based on cloud computing | |
| CN113806478A (en) | Excavator fault auxiliary decision-making method based on graph neural network | |
| CN110601214A (en) | Distribution network reactive voltage governance monitoring system | |
| Zafar et al. | A deep neural network-based optimal power flow approach for identifying network congestion and renewable energy generation curtailment | |
| Xiao et al. | Maintenance cycle optimisation of multi-component systems under the constraints of overall cost and reliability | |
| CN114897262A (en) | Rail transit equipment fault prediction method based on deep learning | |
| Ming | Decision approach of maintenance for urban rail transit based on equipment supervision data mining | |
| CN113469343A (en) | Industrial time sequence data processing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data Effective date of registration: 20131111 Granted publication date: 20121024 Pledgee: Zhongguancun Beijing technology financing Company limited by guarantee Pledgor: Sanbo Zhongzi Tech Co., Ltd. Beijing Registration number: 2013990000835 |
|
| PLDC | Enforcement, change and cancellation of contracts on pledge of patent right or utility model | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20191015 Granted publication date: 20121024 Pledgee: Zhongguancun Beijing technology financing Company limited by guarantee Pledgor: Sanbo Zhongzi Tech Co., Ltd. Beijing Registration number: 2013990000835 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201104 Address after: 518000 24th floor, North building, zhongguanghe building, Shennan Middle Road, Fuzhong community, Lianhua street, Futian District, Shenzhen City, Guangdong Province Patentee after: CGN Intelligent Technology (Shenzhen) Co., Ltd Address before: 100190 Zhongguancun East Road, Beijing, No. 95, No. Patentee before: BEIJING SCIAMPLE TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |