CN103903408A - Device fault detecting and early warning method and system - Google Patents
Device fault detecting and early warning method and system Download PDFInfo
- Publication number
- CN103903408A CN103903408A CN201410135401.8A CN201410135401A CN103903408A CN 103903408 A CN103903408 A CN 103903408A CN 201410135401 A CN201410135401 A CN 201410135401A CN 103903408 A CN103903408 A CN 103903408A
- Authority
- CN
- China
- Prior art keywords
- fault
- parameter
- time
- early warning
- parameter value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000011835 investigation Methods 0.000 claims description 18
- 230000008676 import Effects 0.000 claims description 14
- 230000000694 effects Effects 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 7
- 230000013011 mating Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 231100000749 chronicity Toxicity 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Landscapes
- Alarm Systems (AREA)
Abstract
The invention provides a device fault detecting and early warning method and system, and belongs to the technical field of fault detection. The device fault detecting and early warning method includes the steps of building a fault parameter knowledge base and carrying out fault early warning according to the fault parameter knowledge base and real-time parameters. When the fault parameter knowledge base is built, a list of faults corresponding to devices is led in, parameter values of the devices are led in, the occurrence time point of each fault is determined, parameter values, related to each corresponding fault, of the corresponding device is obtained according to the occurrence time point of the fault, and the faults, the corresponding devices and the parameter values related to the faults are stored in the fault parameter knowledge base. By the device fault detecting and early warning method and system, the technical problems that an existing system is not accurate in early warning and early warning parameters cannot be optimized automatically are solved.
Description
Technical field
The present invention relates to fault detection technique field, relate in particular to a kind of equipment failure investigation method for early warning and system.
Background technology
Existing equipment warning system be the sensor element being arranged on equipment be to report to the police in basis, when certain index of part of appliance exceedes limit value, just report to the police, report to the police and mainly comprise the warning message of the surface phenomena such as part temperatures rising, hydraulic system pressure height, size of current.Warning function is very weak, need artificially again to analyze according to alarm parameters the expectation defect of finding out existence, it is the setting value of broad experience that warning system provides warning initial setting limit value, and it is that the limit value that carries out oneself is set that wind energy turbine set operations staff needs the many factors people such as comprehensive weather own, weather, type.
Fig. 1 a, Fig. 1 b shows respectively for the Organization Chart of the existing warning system of wind energy turbine set and alarm method flow process.As shown in Figure 1a, wind-force electrical machinery 1-n is connected with information collection apparatus 101, and information collection apparatus 101 is connected with main frame 102, and main frame 102 is connected with warning device 103.As shown in Figure 1 b, first, the parameter information of for example blower fan of information collection apparatus 101 collecting devices, and the parameter information of collection is sent to main frame 102; In main frame 102, store alarm threshold value, described alarm threshold value is predefined value, and the parameter information of main frame compare facilities and alarm threshold value, if parameter value exceeds alarm threshold value, given the alarm by warning device 103, otherwise continue collecting device parameter information to loop.As shown in Fig. 1 c, existing warning system has following functions substantially: comprise the collection of warning message, collect the Real-time Collection information that operational outfit need to be reported to the police; The comparison of information parameter, the warning limit value of the warning message of Real-time Collection and setting carries out the comparison of big or small limit value; The warning of out-of-limit information, carries out alarm to the collection value that exceeds limit value, adopts sound, figure, mode word to carry out alarm; Warning message historical query, preserves in real time to out-of-limit warning message, and user can be according to time inquiring warning message; And the setting of warning limit value, the interface that limit value is arranged is provided, the limit value of setting can be applied to the judgement of warning.
Existing warning system has following shortcoming: warning function is very weak.The warning that warning is just carried out for certain parameter value, due to blower fan internal part complex structure, contact between each parts is tight, the defect of parts can cause the fluctuation of many aspects parameter to change, and merely single parameter is carried out to particular location and the imminent moment of fault that alarm cannot location defect.Need to there is technical ability height specialty, operations staff that experience is very abundant adjusts limit value.The limit value of the setting of equipment limit value is not considered the factors such as local weather, season, height above sea level in the time dispatching from the factory, and operations staff need to, according to its own geographical implementations setup parameter, ceaselessly change the setting of limit value according to the variation of season, wind-resources.Artificial empirical early warning does not possess professional the statistical properties.For the variation of certain parameter, the real data that lacks fault pre-alarming system supports foundation, and the operations staff of different experiences may have different fault pre-alarming results, is unfavorable for forming the unified knowledge base based on long term data.Existing warning system very lacks in warning function, and the warning message of single parameter cannot directly be predicted operating condition in the future, needs the defect of artificial analytical equipment existence, carries out failure prediction according to the operating experience of self.Parameter limit value can not be according to the self-adjusting of the basic production such as season, region factor, needs artificial chronicity to participate in adjusting.The above defect that existing system exists has a strong impact on wind energy turbine set personnel to the operating defect elimination inspection of equipment work, be unfavorable for the growth of equipment operation life and the raising of production efficiency, urgent need is built a set of equipment failure investigation early warning system that can utilize on-the-spot abundant real-time data base automatic defect analysis, automatic early-warning, to realize giving warning in advance of equipment, maintenance planning in advance, reaches the object that equipment operation life increases, production efficiency improves.
Summary of the invention
In order to overcome problems of the prior art, the present invention proposes a kind of equipment failure investigation method for early warning and system.Described equipment failure investigation method for early warning comprises: set up fault parameter knowledge base; And carry out fault pre-alarming according to fault parameter knowledge base and real-time parameter.
According to an aspect of the present invention, the described fault parameter knowledge base of setting up comprises: import the list of the fault corresponding with each equipment; Import the parameter value of each equipment; Determine for each fault the time point that this fault occurs; The time point occurring according to each fault, the parameter value relevant to fault of acquisition corresponding device; And fault, corresponding device, the parameter value relevant to fault are stored in fault parameter knowledge base.
According to an aspect of the present invention, describedly carry out fault pre-alarming according to fault parameter knowledge base and real-time parameter and comprise: the various faults of equipment and the related parameter values of fault from described fault parameter knowledge base; Equipment real-time parameter value; Real-time parameter value and described related parameter values are compared; In the time that real-time parameter value is mated with described related parameter values, information gives a warning.
The list of the fault that according to an aspect of the present invention, described and each equipment is corresponding comprises the fault project of classifying according to unit type.
According to an aspect of the present invention, described in each, the parameter value of each equipment is corresponding with a time point.
According to an aspect of the present invention, describedly determine that for each fault the time point that this fault occurs comprises the time point of determining that in section seclected time, fault occurs.
According to an aspect of the present invention, the described time point occurring according to each fault, the parameter value relevant to fault that obtains corresponding device comprises: obtain the time point interior multiple parameter values relevant with each fault of predetermined amount of time before that each fault occurs.
According to an aspect of the present invention, described equipment real-time parameter value comprises equipment multiple real-time parameter values within a predetermined period of time; Described real-time parameter value and described related parameter values are compared and comprised: described equipment multiple real-time parameter values within a predetermined period of time and the related parameter values of the each fault corresponding to described equipment are made comparisons.
According to an aspect of the present invention, when the quantity of mating with multiple related parameter values when multiple real-time parameter values reaches predetermined threshold, described real-time parameter value is mated with related parameter values.
According to an aspect of the present invention, described warning message comprises that source of early warning is by the information breaking down.
According to an aspect of the present invention, describedly carry out fault pre-alarming according to fault parameter knowledge base and real-time parameter and further comprise: warning message is stored in warning message database; Described method for early warning further comprises to be evaluated early warning effect and optimizes fault parameter; Wherein said evaluation early warning effect comprises obtains every warning message of storing in warning message database; Judge whether the fault of predicting in every warning message occurs; The judged result whether fault is occurred is stored in rating database; Described optimization fault parameter comprises and from rating database, obtains the judged result whether fault occurs; In the time that described judged result indication fault does not occur, adjust the relevant parameter value of fault in fault parameter knowledge base.
Described equipment failure investigation early warning system comprises: set up module, for setting up fault parameter knowledge base; And warning module, for carrying out fault pre-alarming according to fault parameter knowledge base and real-time parameter.
According to an aspect of the present invention, the described module of setting up comprises: fault imports unit, for importing the list of the fault corresponding with each equipment; Parameter value imports unit, for importing the parameter value of each equipment; Parameter value imports unit, for the time point of determining that for each fault this fault occurs; Parameter value obtains unit, for the time point occurring according to each fault, obtains the parameter value relevant to fault of corresponding device; And parameter value storage unit, for fault, corresponding device, the parameter value relevant to fault are stored in to fault parameter knowledge base.
According to an aspect of the present invention, described warning module comprises: fault acquiring unit, for the various faults from described fault parameter knowledge base equipment and the related parameter values of fault; Implement parameter acquiring unit, for equipment real-time parameter value; Comparing unit, for comparing real-time parameter value and described related parameter values; Warning message issue unit, in the time that real-time parameter value is mated with described related parameter values, information gives a warning.
The list of the fault that according to an aspect of the present invention, described and each equipment is corresponding comprises the fault project of classifying according to unit type.
According to an aspect of the present invention, described in each, the parameter value of each equipment is corresponding with a time point.
According to an aspect of the present invention, describedly determine that for each fault the time point that this fault occurs comprises the time point of determining that in section seclected time, fault occurs.
According to an aspect of the present invention, the described time point occurring according to each fault, the parameter value relevant to fault that obtains corresponding device comprises: obtain the time point interior multiple parameter values relevant with each fault of predetermined amount of time before that each fault occurs.
According to an aspect of the present invention, described equipment real-time parameter value comprises equipment multiple real-time parameter values within a predetermined period of time; Described real-time parameter value and described related parameter values are compared and comprised: described equipment multiple real-time parameter values within a predetermined period of time and the related parameter values of the each fault corresponding to described equipment are made comparisons.
According to an aspect of the present invention, when the quantity of mating with multiple related parameter values when multiple real-time parameter values reaches predetermined threshold, described real-time parameter value is mated with related parameter values.
According to an aspect of the present invention, described warning message comprises that source of early warning is by the information breaking down.
According to an aspect of the present invention, described warning module further comprises: warning message storage unit, for warning message being stored in to warning message database; Described early warning system further comprises evaluation module, for evaluating early warning effect; And optimization module, for optimizing fault parameter; Wherein said evaluation module comprises warning message acquiring unit, every warning message of storing for obtaining warning message database; Judging unit, for judging whether the fault that every warning message is predicted occurs; And judged result storage unit, be stored in rating database for the judged result whether fault is occurred; Described optimization module comprises judged result acquiring unit, for obtain the judged result whether fault occurs from rating database; And parameter value adjustment unit, in the time that described judged result indication fault does not occur, adjust the relevant parameter value of fault in fault parameter knowledge base.
Accompanying drawing explanation
Fig. 1 a, Fig. 1 b, Fig. 1 c shows respectively the functional schematic for the Organization Chart of the existing warning system of wind energy turbine set, alarm method flow process and warning system;
Fig. 2 shows the process flow diagram of the investigation of equipment failure according to an embodiment of the invention method for early warning;
Fig. 3 shows the process flow diagram of setting up according to an embodiment of the invention fault parameter knowledge base;
Fig. 4 shows the process flow diagram of fault pre-alarming according to an embodiment of the invention;
Fig. 5 shows the process flow diagram of evaluating according to an embodiment of the invention early warning effect;
Fig. 6 shows the process flow diagram of optimizing according to an embodiment of the invention fault parameter;
Fig. 7 shows the block diagram of the investigation of equipment failure according to an embodiment of the invention early warning system.
Embodiment
As shown in Figure 2, the equipment failure investigation method for early warning that the present invention proposes mainly comprises to be set up fault parameter knowledge base, carries out fault pre-alarming according to fault parameter knowledge base and real-time parameter.In one embodiment, also comprise and evaluate early warning effect and optimize fault parameter.Below, equipment failure investigation method for early warning the present invention being proposed is described in detail.
As shown in Figure 3, set up fault parameter knowledge base and comprise the list that imports the fault corresponding with each equipment, the list of described fault comprises the fault project of classifying according to unit type, for example, and the corresponding fault F of equipment 1
11, F
12..., F
1f, the corresponding fault F of equipment 2
21, F
22..., F
2fetc.; Import the parameter value of each equipment, in one embodiment, for each equipment, described parameter value is the value that under predetermined time interval, the parameters to this equipment is measured, and described parameter value is corresponding with time point; Determine for each fault the time point that this fault occurs, because fault may occur repeatedly, therefore described time point can be the time point that fault occurs in user's section seclected time; The time point occurring according to each fault, obtain the parameter value relevant to this fault of corresponding device, in one embodiment, the parameter value of acquisition is described the time point interior parameter value relevant to this fault, for example multiple parameter values in first 20 minutes to first 10 minutes of predetermined amount of time before; Fault, corresponding device, the parameter value relevant to fault are stored in fault parameter knowledge base, thereby set up described fault parameter knowledge base.
As shown in Figure 4, carry out fault pre-alarming according to fault parameter knowledge base and comprise the various faults of equipment from fault parameter knowledge base and the related parameter values of fault; Equipment real-time parameter value; Real-time parameter value and related parameter values are compared, describedly relatively can use any determination methods to carry out, in one embodiment, for example, the relatively real-time parameter value of interval acquiring and multiple related parameter values of fault on schedule in a period of time, the multiple real-time parameter value M in during this period of time
1.。。Mwith multiple related parameter values N
1.。。, mwhen coupling, for example, for 1≤i≤m, M
iwith N
ibetween the difference quantity that is less than the i of preset parameter difference be more than or equal to predetermined quantity threshold value, think that real-time parameter value mates with related parameter values; In the time that real-time parameter value is mated with related parameter values, information gives a warning, in one embodiment, for example described related parameter values is multiple related parameter values of first 20 minutes to first 10 minutes, and mate with multiple real-time parameter values of obtaining in nearest 10 minutes, described warning message can be, due to the real-time parameter M of equipment 1
1 ..., mcoupling produces fault F
1fcorrelation parameter N
1.。。, m, predict device 1 will produce fault F after 10 minutes
1f.In one embodiment, also comprise warning message is stored in warning message database.
In example above, only provided the example of for example temperature of a kind of parameter for real-time parameter value and related parameter values, and in practical operation, the parameter relevant to fault may be multiple, except temperature mentioned above, also can be the parameters such as pressure, electric current, voltage, at this moment, in described fault parameter knowledge base, store the parameter value of the many kinds of parameters relevant to this fault, in the time judging whether to give a warning information, need the real-time parameter value of more every kind of parameter whether to mate with related parameter values.
As shown in Figure 5, evaluating early warning effect comprises and obtains every warning message of storing in warning message database; Judge whether the fault of predicting in every warning message occurs; The judged result whether fault is occurred is stored in rating database.
As shown in Figure 6, optimizing fault parameter comprises and from rating database, obtains the judged result whether fault occurs; In the time that described judged result indication fault does not occur, adjust the relevant parameter value of fault in fault parameter knowledge base, in one embodiment, again seclected time section, search the time point that fault occurs in the again selected time period, thereby determine according to this time point the parameter value that fault is relevant; In another embodiment, all time points that occur with reference to fault are determined the parameter value that fault is relevant, for example, determine described relevant parameter value based on methods such as weighting are averaging; In another embodiment, adjust the relevant parameter value of fault by artificial reference historical data.
As shown in Figure 7, the invention allows for a kind of equipment failure investigation early warning system, for carrying out equipment failure investigation method for early warning mentioned above.Described fault investigation early warning system comprises sets up module, for setting up fault parameter knowledge base; Warning module, for carrying out fault pre-alarming according to fault parameter knowledge base and real-time parameter.In one embodiment, also comprise evaluation module, for evaluating early warning effect and optimizing module, for optimizing fault parameter.Below, equipment failure investigation early warning system the present invention being proposed is described in detail.
The described module of setting up comprises that fault imports unit, and for importing the list of the fault corresponding with each equipment, the list of described fault comprises the fault project of classifying according to unit type, for example, and the corresponding fault F of equipment 1
11, F
12..., F
1f, the corresponding fault F of equipment 2
21, F
22..., F
2fetc.; Parameter value imports unit, and for importing the parameter value of each equipment, in one embodiment, for each equipment, described parameter value is the value that under predetermined time interval, the parameters to this equipment is measured, and described parameter value is corresponding with time point; Time point determining unit, for the time point of determining that for each fault this fault occurs, because fault may occur repeatedly, therefore described time point can be the time point that fault occurs in user's section seclected time; Parameter value obtains unit, for the time point occurring according to each fault, obtain the parameter value relevant to this fault of corresponding device, in one embodiment, the parameter value obtaining is described the time point interior parameter value relevant to this fault, for example multiple parameter values in first 20 minutes to first 10 minutes of predetermined amount of time before; Parameter value storage unit, for fault, corresponding device, the parameter value relevant to fault are stored in to fault parameter knowledge base, thereby sets up described fault parameter knowledge base.
Warning module comprises fault acquiring unit, for the various faults from fault parameter knowledge base equipment and the related parameter values of fault; Implement parameter acquiring unit, for equipment real-time parameter value; Comparing unit, for real-time parameter value and related parameter values are compared, describedly relatively can use any determination methods to carry out, in one embodiment, for example, the relatively real-time parameter value of interval acquiring and multiple related parameter values of fault on schedule in a period of time, the multiple real-time parameter value M in during this period of time
1.。。Mwith multiple related parameter values N
1.。。, mwhen coupling, for example, for 1≤i≤m, M
iwith N
ibetween the difference quantity that is less than the i of preset parameter difference be more than or equal to predetermined quantity threshold value, think that real-time parameter value mates with related parameter values; Warning message issue unit, for in the time that real-time parameter value is mated with related parameter values, information gives a warning, in one embodiment, for example described related parameter values is multiple related parameter values of first 20 minutes to first 10 minutes, and mate with multiple real-time parameter values of obtaining in nearest 10 minutes, described warning message can be, due to the real-time parameter M of equipment 1
1 ..., mcoupling produces fault F
1fcorrelation parameter N
1.。。, m, predict device 1 will produce fault F after 10 minutes
1f.In one embodiment, also comprise warning message storage unit, for warning message being stored in to warning message database.
In example above, only provided the example of for example temperature of a kind of parameter for real-time parameter value and related parameter values, and in practical operation, the parameter relevant to fault may be multiple, except temperature mentioned above, also can be the parameters such as pressure, electric current, voltage, at this moment, in described fault parameter knowledge base, store the parameter value of the many kinds of parameters relevant to this fault, in the time judging whether to give a warning information, need the real-time parameter value of more every kind of parameter whether to mate with related parameter values.
Evaluation module comprises warning message acquiring unit, every warning message of storing for obtaining warning message database; Judging unit, for judging whether the fault that every warning message is predicted occurs; And judged result storage unit, be stored in rating database for the judged result whether fault is occurred.
Optimize module and comprise judged result acquiring unit, for obtain the judged result whether fault occurs from rating database; Parameter value adjustment unit, for in the time that described judged result indication fault does not occur, adjust the relevant parameter value of fault in fault parameter knowledge base, in one embodiment, again seclected time section, search the time point that fault occurs in the again selected time period, thereby determine according to this time point the parameter value that fault is relevant; In another embodiment, all time points that occur with reference to fault are determined the parameter value that fault is relevant, for example, determine described relevant parameter value based on methods such as weighting are averaging; In another embodiment, adjust the relevant parameter value of fault by artificial reference historical data.
Equipment failure investigation early warning system from angle of statistics by the extraction and analysis of historical equipment failure data having been set up to fault phase related parameter information excavating model, take this model and existing industrial Runtime Library as basis, form the fault phase related parameter information knowledge storehouse of specific model equipment.With the relevant parameter information of fault phase related parameter information knowledge storehouse real-time watch device specific fault, set up an equipment failure investigation Early-warning Model to meeting the early warning of carrying out of knowledge base parameter value and logic.Take historical early warning information and early warning recruitment evaluation as basis, set up an equipment fault early-warning self-optimizing model, realize the optimization in early-warning parameters information knowledge storehouse, thereby reached improving constantly of early warning information accuracy.Early warning system has customer parameter and adjusts interface, guarantee the user of authority can be rule of thumb the direct configuration information such as fault phase related parameter information knowledge storehouse of add-on system, guarantee making full use of of operation manpower think tank.Native system designs with the principle of " artificial few participation, data model self-optimizing ", has realized system automatic early-warning, self-adjusting target, and more original warning system has following advantage:
1, system can be used in various practical applications, and for example, for wind power equipment fault pre-alarming designs, the warning system of more original shortage warning function has greatly improved.Based on the real-time running data of enriching constantly, form the early warning information knowledge base that contains different types of machines, there are higher projected depth and accuracy to guarantee.
2, system is carried out Modeling and Design with statistical theory thought, and history, real time data to equipment are carried out the statistical study of Life cycle, forms take large data as basic statistics early-warning function, and more original early warning system with single experience is more scientific, more comprehensively.
3, system only needs the little participation of operations staff can carry out automatic early-warning, and system can be optimized self model parameter according to the study of real time execution storehouse automatically.Participate in adjusting the manpower maintenance cost of the system of more saving compared with artificial Life cycle in original system.
Above-mentioned embodiment proposes just to explanation, not as limiting the scope of the invention.It will be understood by those skilled in the art that by above-mentioned embodiment is adjusted, can be applied in different practical applications.
Claims (22)
1. an equipment failure investigation method for early warning, is characterized in that, the method comprises:
Set up fault parameter knowledge base; And
Carry out fault pre-alarming according to fault parameter knowledge base and real-time parameter.
2. method for early warning according to claim 1, is characterized in that:
The described fault parameter knowledge base of setting up comprises:
Import the list of the fault corresponding with each equipment;
Import the parameter value of each equipment;
Determine for each fault the time point that this fault occurs;
The time point occurring according to each fault, the parameter value relevant to fault of acquisition corresponding device; And
Fault, corresponding device, the parameter value relevant to fault are stored in fault parameter knowledge base.
3. method for early warning according to claim 2, is characterized in that:
Describedly carry out fault pre-alarming according to fault parameter knowledge base and real-time parameter and comprise:
The various faults of equipment and the related parameter values of fault from described fault parameter knowledge base;
Equipment real-time parameter value;
Real-time parameter value and described related parameter values are compared;
In the time that real-time parameter value is mated with described related parameter values, information gives a warning.
4. method for early warning according to claim 2, is characterized in that:
The list of the fault that described and each equipment is corresponding comprises the fault project of classifying according to unit type.
5. method for early warning according to claim 2, is characterized in that:
Described in each, the parameter value of each equipment is corresponding with a time point.
6. method for early warning according to claim 2, is characterized in that:
Describedly determine that for each fault the time point that this fault occurs comprises the time point of determining that in section seclected time, fault occurs.
7. method for early warning according to claim 3, is characterized in that:
The described time point occurring according to each fault, the parameter value relevant to fault that obtains corresponding device comprises:
Obtain the time point interior multiple parameter values relevant to each fault of predetermined amount of time before that each fault occurs.
8. method for early warning according to claim 7, is characterized in that:
Described equipment real-time parameter value comprises equipment multiple real-time parameter values within a predetermined period of time;
Described real-time parameter value and described related parameter values compared and comprised:
Described equipment multiple real-time parameter values within a predetermined period of time and the related parameter values of the each fault corresponding to described equipment are made comparisons.
9. method for early warning according to claim 8, is characterized in that:
When the quantity of mating with multiple related parameter values when multiple real-time parameter values reaches predetermined threshold, described real-time parameter value is mated with related parameter values.
10. method for early warning according to claim 9, is characterized in that:
Described warning message comprises that source of early warning is by the information breaking down.
11. method for early warning according to claim 3, is characterized in that:
Describedly carry out fault pre-alarming according to fault parameter knowledge base and real-time parameter and further comprise: warning message is stored in warning message database;
Described method for early warning further comprises to be evaluated early warning effect and optimizes fault parameter; Wherein
Described evaluation early warning effect comprises obtains every warning message of storing in warning message database; Judge whether the fault of predicting in every warning message occurs; The judged result whether fault is occurred is stored in rating database;
Described optimization fault parameter comprises and from rating database, obtains the judged result whether fault occurs; In the time that described judged result indication fault does not occur, adjust the relevant parameter value of fault in fault parameter knowledge base.
12. 1 kinds of equipment failure investigation early warning systems, is characterized in that, this system comprises:
Set up module, for setting up fault parameter knowledge base; And
Warning module, for carrying out fault pre-alarming according to fault parameter knowledge base and real-time parameter.
13. early warning systems according to claim 12, is characterized in that:
The described module of setting up comprises:
Fault imports unit, for importing the list of the fault corresponding with each equipment;
Parameter value imports unit, for importing the parameter value of each equipment;
Parameter value imports unit, for the time point of determining that for each fault this fault occurs;
Parameter value obtains unit, for the time point occurring according to each fault, obtains the parameter value relevant to fault of corresponding device; And
Parameter value storage unit, for being stored in fault parameter knowledge base by fault, corresponding device, the parameter value relevant to fault.
14. early warning systems according to claim 13, is characterized in that:
Described warning module comprises:
Fault acquiring unit, for the various faults from described fault parameter knowledge base equipment and the related parameter values of fault;
Implement parameter acquiring unit, for equipment real-time parameter value;
Comparing unit, for comparing real-time parameter value and described related parameter values;
Warning message issue unit, in the time that real-time parameter value is mated with described related parameter values, information gives a warning.
15. early warning systems according to claim 13, is characterized in that:
The list of the fault that described and each equipment is corresponding comprises the fault project of classifying according to unit type.
16. early warning systems according to claim 13, is characterized in that:
Described in each, the parameter value of each equipment is corresponding with a time point.
17. early warning systems according to claim 13, is characterized in that:
Describedly determine that for each fault the time point that this fault occurs comprises the time point of determining that in section seclected time, fault occurs.
18. early warning systems according to claim 14, is characterized in that:
The described time point occurring according to each fault, the parameter value relevant to fault that obtains corresponding device comprises:
Obtain the time point interior multiple parameter values relevant to each fault of predetermined amount of time before that each fault occurs.
19. early warning systems according to claim 18, is characterized in that:
Described equipment real-time parameter value comprises equipment multiple real-time parameter values within a predetermined period of time;
Described real-time parameter value and described related parameter values compared and comprised:
Described equipment multiple real-time parameter values within a predetermined period of time and the related parameter values of the each fault corresponding to described equipment are made comparisons.
20. early warning systems according to claim 19, is characterized in that:
When the quantity of mating with multiple related parameter values when multiple real-time parameter values reaches predetermined threshold, described real-time parameter value is mated with related parameter values.
21. early warning systems according to claim 20, is characterized in that:
Described warning message comprises that source of early warning is by the information breaking down.
22. early warning systems according to claim 14, is characterized in that:
Described warning module further comprises: warning message storage unit, for warning message being stored in to warning message database;
Described early warning system further comprises evaluation module, for evaluating early warning effect; And optimization module, for optimizing fault parameter; Wherein
Described evaluation module comprises warning message acquiring unit, every warning message of storing for obtaining warning message database; Judging unit, for judging whether the fault that every warning message is predicted occurs; And judged result storage unit, be stored in rating database for the judged result whether fault is occurred;
Described optimization module comprises judged result acquiring unit, for obtain the judged result whether fault occurs from rating database; And parameter value adjustment unit, in the time that described judged result indication fault does not occur, adjust the relevant parameter value of fault in fault parameter knowledge base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410135401.8A CN103903408B (en) | 2014-04-04 | 2014-04-04 | Method for early warning and system are investigated in equipment fault |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410135401.8A CN103903408B (en) | 2014-04-04 | 2014-04-04 | Method for early warning and system are investigated in equipment fault |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103903408A true CN103903408A (en) | 2014-07-02 |
| CN103903408B CN103903408B (en) | 2017-07-21 |
Family
ID=50994709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410135401.8A Expired - Fee Related CN103903408B (en) | 2014-04-04 | 2014-04-04 | Method for early warning and system are investigated in equipment fault |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103903408B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104103021A (en) * | 2014-07-15 | 2014-10-15 | 南京南瑞集团公司 | Filtering method for aiming at hydropower station production process data |
| CN105159288A (en) * | 2015-10-15 | 2015-12-16 | 珠海格力电器股份有限公司 | Method and system for determining fault reason of electrical equipment |
| CN105629938A (en) * | 2016-02-24 | 2016-06-01 | 上海和鹰机电科技股份有限公司 | Intelligent monitoring method for vulnerable part |
| CN105645209A (en) * | 2016-03-03 | 2016-06-08 | 宁夏电通物联网科技股份有限公司 | Maintenance system and maintenance method for elevators based on big data support of Internet of Things |
| CN106292618A (en) * | 2015-06-08 | 2017-01-04 | 上海通用汽车有限公司 | Vehicle trouble quick positioning analysis system and the quick method for positioning analyzing of vehicle trouble |
| CN106557773A (en) * | 2015-09-25 | 2017-04-05 | 北汽福田汽车股份有限公司 | A kind of method and system of car fault diagnosis |
| CN106600003A (en) * | 2015-10-16 | 2017-04-26 | 中芯国际集成电路制造(上海)有限公司 | Machine maintenance system and method |
| CN106599201A (en) * | 2016-12-15 | 2017-04-26 | 河海大学常州校区 | Full life circle management method of gas transmission and distribution equipment |
| CN106768000A (en) * | 2017-01-06 | 2017-05-31 | 科诺伟业风能设备（北京）有限公司 | A kind of wind driven generator set converter water-cooling system pressure anomaly detection method |
| CN106959652A (en) * | 2017-05-08 | 2017-07-18 | 北京百度网讯科技有限公司 | Intelligent control method and device |
| CN107943098A (en) * | 2018-01-01 | 2018-04-20 | 余绍祥 | A kind of intelligent O＆M robot system based on machine learning |
| CN108171341A (en) * | 2017-12-19 | 2018-06-15 | 深圳交控科技有限公司 | The state analysis method and device of signalling arrangement |
| CN108509645A (en) * | 2018-04-13 | 2018-09-07 | 华润电力风能(威海)有限公司 | A kind of equipment method for early warning |
| CN108600704A (en) * | 2018-05-08 | 2018-09-28 | 深圳市智汇牛科技有限公司 | A kind of monitoring system framework in automatic kitchen field |
| CN108683517A (en) * | 2018-03-26 | 2018-10-19 | 国网冀北电力有限公司信息通信分公司 | A kind of O＆M robot network's fault detection system based on machine learning |
| CN109816136A (en) * | 2017-11-21 | 2019-05-28 | 财团法人资讯工业策进会 | Equipment maintenance prediction system and its operation method |
| CN110287347A (en) * | 2019-07-05 | 2019-09-27 | 黑龙江电力调度实业有限公司 | Using the method for big data detection electric power computer room failure |
| CN110706433A (en) * | 2019-10-16 | 2020-01-17 | 珠海格力电器股份有限公司 | Fault early warning method, fault early warning device and electric cabinet |
| CN110852484A (en) * | 2019-10-15 | 2020-02-28 | 浙江运达风电股份有限公司 | A system and method for early warning of wind turbine failure |
| CN110967566A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Electrical appliance fault detection method and device |
| CN112907911A (en) * | 2021-01-19 | 2021-06-04 | 安徽数分智能科技有限公司 | Intelligent anomaly identification and alarm algorithm based on equipment process data |
| CN114090323A (en) * | 2021-11-29 | 2022-02-25 | 施耐德电气（中国）有限公司 | A kind of abnormal data identification method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030149547A1 (en) * | 2001-08-31 | 2003-08-07 | Takashi Nakao | Method for diagnosing failure of a manufacturing apparatus and a failure diagnosis system |
| CN1838161A (en) * | 2005-03-23 | 2006-09-27 | 大亚湾核电运营管理有限责任公司 | Method and apparatus for nuclear power station equipment risk evaluation by computer |
| CN101515315A (en) * | 2008-12-10 | 2009-08-26 | 北京燕化正邦设备检修有限公司 | Petrochemical equipment refinement maintenance system |
| CN102169646A (en) * | 2011-04-13 | 2011-08-31 | 深圳市双合电气股份有限公司 | Dynamic data-based online load modeling system |
| CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
| CN103306893A (en) * | 2012-03-09 | 2013-09-18 | 北京光耀能源技术股份有限公司 | Failure early warning and alarming method for wind-driven generator |
-
2014
- 2014-04-04 CN CN201410135401.8A patent/CN103903408B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030149547A1 (en) * | 2001-08-31 | 2003-08-07 | Takashi Nakao | Method for diagnosing failure of a manufacturing apparatus and a failure diagnosis system |
| CN1838161A (en) * | 2005-03-23 | 2006-09-27 | 大亚湾核电运营管理有限责任公司 | Method and apparatus for nuclear power station equipment risk evaluation by computer |
| CN101515315A (en) * | 2008-12-10 | 2009-08-26 | 北京燕化正邦设备检修有限公司 | Petrochemical equipment refinement maintenance system |
| CN102169646A (en) * | 2011-04-13 | 2011-08-31 | 深圳市双合电气股份有限公司 | Dynamic data-based online load modeling system |
| CN103306893A (en) * | 2012-03-09 | 2013-09-18 | 北京光耀能源技术股份有限公司 | Failure early warning and alarming method for wind-driven generator |
| CN102765643A (en) * | 2012-05-31 | 2012-11-07 | 天津大学 | Elevator fault diagnosis and early-warning method based on data drive |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104103021B (en) * | 2014-07-15 | 2017-04-05 | 南京南瑞集团公司 | A kind of filter method for power station production process data |
| CN104103021A (en) * | 2014-07-15 | 2014-10-15 | 南京南瑞集团公司 | Filtering method for aiming at hydropower station production process data |
| CN106292618A (en) * | 2015-06-08 | 2017-01-04 | 上海通用汽车有限公司 | Vehicle trouble quick positioning analysis system and the quick method for positioning analyzing of vehicle trouble |
| CN106292618B (en) * | 2015-06-08 | 2019-10-01 | 上海通用汽车有限公司 | The quick positioning analysis system of vehicle trouble and the quick method for positioning analyzing of vehicle trouble |
| CN106557773A (en) * | 2015-09-25 | 2017-04-05 | 北汽福田汽车股份有限公司 | A kind of method and system of car fault diagnosis |
| CN106557773B (en) * | 2015-09-25 | 2020-04-24 | 北京宝沃汽车有限公司 | Vehicle fault diagnosis method and system |
| CN105159288B (en) * | 2015-10-15 | 2019-01-15 | 珠海格力电器股份有限公司 | Method and system for determining fault reason of electrical equipment |
| CN105159288A (en) * | 2015-10-15 | 2015-12-16 | 珠海格力电器股份有限公司 | Method and system for determining fault reason of electrical equipment |
| CN106600003A (en) * | 2015-10-16 | 2017-04-26 | 中芯国际集成电路制造(上海)有限公司 | Machine maintenance system and method |
| CN105629938A (en) * | 2016-02-24 | 2016-06-01 | 上海和鹰机电科技股份有限公司 | Intelligent monitoring method for vulnerable part |
| CN105645209A (en) * | 2016-03-03 | 2016-06-08 | 宁夏电通物联网科技股份有限公司 | Maintenance system and maintenance method for elevators based on big data support of Internet of Things |
| CN106599201A (en) * | 2016-12-15 | 2017-04-26 | 河海大学常州校区 | Full life circle management method of gas transmission and distribution equipment |
| CN106599201B (en) * | 2016-12-15 | 2020-05-01 | 河海大学常州校区 | Full life cycle management method of gas transmission and distribution equipment |
| CN106768000B (en) * | 2017-01-06 | 2019-05-24 | 科诺伟业风能设备（北京）有限公司 | A kind of wind driven generator set converter water-cooling system pressure anomaly detection method |
| CN106768000A (en) * | 2017-01-06 | 2017-05-31 | 科诺伟业风能设备（北京）有限公司 | A kind of wind driven generator set converter water-cooling system pressure anomaly detection method |
| CN106959652B (en) * | 2017-05-08 | 2019-08-16 | 北京百度网讯科技有限公司 | Intelligent control method, device and readable computer storage medium |
| CN106959652A (en) * | 2017-05-08 | 2017-07-18 | 北京百度网讯科技有限公司 | Intelligent control method and device |
| CN109816136A (en) * | 2017-11-21 | 2019-05-28 | 财团法人资讯工业策进会 | Equipment maintenance prediction system and its operation method |
| TWI663510B (en) * | 2017-11-21 | 2019-06-21 | 財團法人資訊工業策進會 | Equipment maintenance forecasting system and operation method thereof |
| CN108171341A (en) * | 2017-12-19 | 2018-06-15 | 深圳交控科技有限公司 | The state analysis method and device of signalling arrangement |
| CN107943098A (en) * | 2018-01-01 | 2018-04-20 | 余绍祥 | A kind of intelligent O＆M robot system based on machine learning |
| CN108683517A (en) * | 2018-03-26 | 2018-10-19 | 国网冀北电力有限公司信息通信分公司 | A kind of O＆M robot network's fault detection system based on machine learning |
| CN108683517B (en) * | 2018-03-26 | 2021-03-23 | 国网冀北电力有限公司信息通信分公司 | Operation and maintenance robot network fault detection system based on machine learning |
| CN108509645A (en) * | 2018-04-13 | 2018-09-07 | 华润电力风能(威海)有限公司 | A kind of equipment method for early warning |
| CN108600704A (en) * | 2018-05-08 | 2018-09-28 | 深圳市智汇牛科技有限公司 | A kind of monitoring system framework in automatic kitchen field |
| CN110967566A (en) * | 2018-09-28 | 2020-04-07 | 珠海格力电器股份有限公司 | Electrical appliance fault detection method and device |
| CN110287347A (en) * | 2019-07-05 | 2019-09-27 | 黑龙江电力调度实业有限公司 | Using the method for big data detection electric power computer room failure |
| CN110852484A (en) * | 2019-10-15 | 2020-02-28 | 浙江运达风电股份有限公司 | A system and method for early warning of wind turbine failure |
| CN110852484B (en) * | 2019-10-15 | 2023-03-10 | 浙江运达风电股份有限公司 | Fault early warning system and method for wind generating set |
| CN110706433A (en) * | 2019-10-16 | 2020-01-17 | 珠海格力电器股份有限公司 | Fault early warning method, fault early warning device and electric cabinet |
| CN112907911A (en) * | 2021-01-19 | 2021-06-04 | 安徽数分智能科技有限公司 | Intelligent anomaly identification and alarm algorithm based on equipment process data |
| CN114090323A (en) * | 2021-11-29 | 2022-02-25 | 施耐德电气（中国）有限公司 | A kind of abnormal data identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103903408B (en) | 2017-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103903408A (en) | Device fault detecting and early warning method and system | |
| CN114202129B (en) | Wind power output prediction method, electronic device, storage medium and system | |
| CN105548949B (en) | The fault remote determination methods of a kind of intelligent electric energy meter and system thereof | |
| CN104200396B (en) | A kind of wind turbine component fault early warning method | |
| CN111191878A (en) | A method and system for state evaluation of station area and electric energy meter based on abnormal analysis | |
| CN106054104A (en) | Intelligent ammeter fault real time prediction method based on decision-making tree | |
| CN104283318A (en) | Power equipment integrated monitoring and early warning system based on big data and analysis method thereof | |
| CN118094262B (en) | A load outlier detection method based on spatial clustering | |
| CN116736134B (en) | A real-time energy storage battery data monitoring method and device | |
| CN120542643A (en) | Energy consumption optimization method and system based on multi-dimensional data fusion | |
| CN119944624A (en) | Power quality monitoring system and method for distributed photovoltaic grid-connected distribution network | |
| CN117114254B (en) | Power grid new energy abnormal data monitoring method and system | |
| CN119402363A (en) | An Internet of Things gateway and an operation method thereof | |
| CN113177718B (en) | Intelligent power grid infrastructure project analysis management system based on data visualization | |
| CN118280069A (en) | A Power Grid Disaster Monitoring and Early Warning System Based on GIS | |
| CN117235193A (en) | A multi-energy complementary source-load-storage optimization allocation method for virtual power plants | |
| CN114216558B (en) | Method and system for predicting remaining life of battery of wireless vibration sensor | |
| CN107478997A (en) | A kind of base station storage batteries appraisal procedure and device | |
| KR20210107372A (en) | Method and system for maintenance of building | |
| CN120701921A (en) | A system and method for dynamic monitoring and precise positioning of urban water supply network leakage | |
| CN120511654A (en) | Industrial park load prediction method based on artificial intelligence | |
| CN118052447B (en) | A real-time detection method and system for construction progress | |
| CN119222578B (en) | A fuel monitoring and control system for industrial automation | |
| CN119721688A (en) | A method for fault risk perception in distribution network | |
| CN113129160A (en) | Electric power communication network inspection method based on equipment state perception and intellectualization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170721 Termination date: 20200404 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |