CN102999038A - Diagnostic device for power generating equipment, and diagnostic method for power generating equipment - Google Patents
Diagnostic device for power generating equipment, and diagnostic method for power generating equipment Download PDFInfo
- Publication number
- CN102999038A CN102999038A CN2012102884544A CN201210288454A CN102999038A CN 102999038 A CN102999038 A CN 102999038A CN 2012102884544 A CN2012102884544 A CN 2012102884544A CN 201210288454 A CN201210288454 A CN 201210288454A CN 102999038 A CN102999038 A CN 102999038A
- Authority
- CN
- China
- Prior art keywords
- measuring
- generating set
- signal
- service condition
- diagnostic
- 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
Abstract
A diagnostic device reduces a false negative rate that abnormal phenomena can not be detected when the abnormal phenomena occur, and has a high diagnostic accuracy. The diagnostic device for power generating equipment, which diagnoses an operation state of the equipment based on a measuring signal obtained from measuring quantity of state of the power generating equipment and displays a diagnostic result onto an image display device, comprises: a model building unit for building a model used in diagnosis by using the measuring signal obtained by measuring the quantity of state of the power generating equipment in the diagnostic device for power generating equipment; a model defining unit for defining operation conditions of diagnosis using the model and a normalization method of the measuring signal; and a diagnosing unit for diagnosing the operation state of the power generation equipment by using the model built by the model building unit, wherein the model defining unit has an operation condition judging part for judging the operation condition of the power generating equipment and a normalization condition determining part for determining a normalization condition of data according to each operation condition judged by the operation condition judging part, the diagnosing unit is matched with the operation condition to switch a diagnosing model to perform diagnosis.
Description
Technical field
The present invention relates to the diagnostic device of generating set (plant) and the diagnostic method of generating set.
Background technology
When the diagnostic device of generating set produces unusual transient or accident in equipment, according to survey this generation unusual or accident from the measuring-signal of equipment.
Diagnostic device as the equipment of known case in TOHKEMY 2005-165375 communique, discloses the diagnostic device of the equipment of use self-elevating platform ART (Adaptive Resonance Theory:ART).At this, ART is the technology that the data of multidimensional is categorized as classification according to its similarity.
In the technology of the diagnostic device of the equipment that this JP 2005-165375 communique is put down in writing, at first, come the state of extraction equipment to be considered to measuring-signal during normal according to the measuring-signal in past of the service data that has recorded equipment, be used as the data mapping data.Then, using ART, is a plurality of classifications (normal category) with the data mapping Data classification, makes the normal model that uses in the diagnosis.Next, with ART the current measuring-signal of equipment is categorized as classification.When this current measuring-signal and normal model are inconsistent, in the time of namely normal category can't being categorized as, generate new classification (new classification).That is, the generation of new classification means that the tendency of measuring-signal changes, and variation has occured the state of equipment.Therefore, this is to judge unusual generation with the generation of new classification, has surpassed in the generation ratio of new classification in the situation of threshold value to be diagnosed as unusual technology.
Patent documentation
Patent documentation 1:JP JP 2005-165375 communique
Generating set is started, is stopped, constant load, load variations etc. are all moved under various conditions.If the condition of operation is different, then the scope of the variation of measuring-signal is also different.
In addition, as the pre-treatment of the measuring-signal that in diagnosis, uses, be normalized.In normalized, normalized lower limit is made as 0, normalized higher limit is made as 1, so process measuring-signal.Normalized lower limit and higher limit need to be set in advance.In the diagnostic device of prior art, no matter service condition how, is all processed measuring-signal under identical normalizing condition.Therefore, the normalization scope need to be made as wider scope, so that can comprise the variation range of the measuring-signal under whole service conditions.
If the normalization scope is larger than the variation range of measuring-signal, then the variation of the value after measuring-signal is carried out normalization will diminish.Therefore, the tendency of the measuring-signal in the time of can't catching unusual the generation changes, and also can't produce new classification even exist when unusual the generation.This becomes the reason of failing to report.
Summary of the invention
The object of the present invention is to provide a kind ofly by suitably determining the normalization scope with service condition coupling, suppress thus to have failed to report, improved the diagnostic device of diagnostic accuracy.
The diagnostic device of generating set, come the running status of diagnostic device based on the measuring-signal that obtains from generating set measuring state amount, and diagnostic result is shown in the image display device, it is characterized in that, possess: the data mapping unit, it uses the measuring-signal of measuring the quantity of state of generating set and obtain in the diagnostic device of generating set, constructs the model that uses in diagnosis; The model definition unit, the service condition that its definition is diagnosed by described model and the method for normalizing of measuring-signal; And diagnosis unit, it uses the model of being constructed by described data mapping unit to diagnose the running status of generating set; In described model definition unit, possess: the service condition detection unit, it judges the service condition of generating set; With the normalizing condition determination section, it decides the normalizing condition of data by each service condition of being judged by the service condition detection unit, in described diagnosis unit, mates to switch diagnostic model with service condition and diagnoses.
The diagnostic device of the generating set of the application of the invention can't detect unusual failing to report in the time of reducing unusual the generation, has improved diagnostic accuracy.In addition, can automatically determine the normalization scope, can shorten diagnostic device the adjustment period between.
Description of drawings
Fig. 1 is the control block diagram of formation of diagnostic device of the generating set of expression one embodiment of the present of invention.
Fig. 2 is process flow diagram and the expression action key diagram regularly of elemental motion of the diagnostic device of expression generating set shown in Figure 1.
Fig. 3 is the key diagram that is illustrated in the installation example of the function of in data mapping unit in the diagnostic device of equipment shown in Figure 1, the diagnosis unit data being classified.
Fig. 4 is that expression is by the key diagram of the data mapping unit in the diagnostic device of generating set shown in Figure 1 with the example of measuring-signal classification.
Fig. 5 is the key diagram of the relation of originate mode in the generating set shown in the presentation graphs 4 (a) and process values.
Fig. 6 is the key diagram of the action of the service condition detection unit 500 in the diagnostic device of generating set shown in Figure 1.
Fig. 7 is the key diagram of the 1st embodiment of the normalizing condition determination section 600 in the diagnostic device of generating set shown in Figure 1.
Fig. 8 is the key diagram of the 2nd embodiment of the normalizing condition determination section 600 in the diagnostic device of generating set shown in Figure 1.
Fig. 9 is the key diagram of the 3rd embodiment of the normalizing condition determination section 600 in the diagnostic device of generating set shown in Figure 1.
Figure 10 is the key diagram of the motion flow of data mapping pattern in the diagnostic device of generating set shown in Figure 1 and diagnostic mode.
Figure 11 is the key diagram of the data form in the database that is kept in the diagnostic device of generating set shown in Figure 1.
Figure 12 is the key diagram of effect of the diagnostic device of generating set shown in Figure 1.
Figure 13 is the key diagram of the picture on the image display device that is shown in the diagnostic device of generating set shown in Figure 1.
Symbol description:
1,3,4 measuring-signals
2 external input signals
5,6,7 model definition information
8,9 model informations
10 diagnostic results
11 picture disply information
50 diagnostic device information
100 equipment
200 diagnostic devices
210 outer input interfaces
220 outside output interfaces
310 measuring-signal databases
320 model definition databases
330 diagnostic model databases
400 model definition unit
500 service condition detection units
600 normalizing condition determination sections
700 data mapping unit
800 diagnosis units
Operational management chambers 900
910 external input device
920 keyboards
930 mouses
940 image display devices
Embodiment
Next, with reference to accompanying drawing diagnostic device as the generating set of embodiments of the invention is described below.
Fig. 1 is that explanation is as the block diagram of the diagnostic device of the generating set of one embodiment of the present of invention.In the diagnostic device of generating set shown in Figure 1, come the state of diagnostic device 100 by diagnostic device 200.
In the database of measuring-signal database 310, model definition database 320 and diagnostic model database 330, record the information of electronization, usually they are called e-file (electronic data).
Data mapping unit 700 is according to the measuring-signal of the running status of measuring equipment 100, based on the savings data of the measuring-signal of the running status in the past of having put aside equipment 100, makes the diagnostic model of the normal condition of the equipment of having learnt.
The method for normalizing of the measuring-signal the when service condition that 400 pairs of model definition unit are diagnosed with diagnostic model and data mapping defines.
The data of the measuring-signal of the data of the value of the diagnostic model that diagnosis unit 800 will be made by data mapping unit 700 and the equipment 100 of measuring compare.If measuring-signal is consistent with the value of the diagnostic model of having learnt normal condition, then the condition judgement with equipment is normal, if inconsistent then being judged to be unusually.
In addition, diagnostic device 200 possesses outer input interface 210 and outside output interface 220, is used as the interface with the outside.
Then, via outer input interface 210 running status of equipment 100 various quantity of states have namely been measured and external input signal 2 that the measuring-signal 1 that obtains and the operation by the external input device 910 that is made of keyboard 920 and mouse 930 that possesses in the operational management chamber 900 make is taken in the diagnostic device 200.In addition, via outside output interface 220 image display information 11 is exported to the image display device 940 that operational management chamber 900 possesses.
In addition, in the diagnostic device of the equipment of present embodiment, possess model definition unit 400, data mapping unit 700, diagnosis unit 800, measuring-signal database 310, model definition database 320, diagnostic model database 330 in the inside of diagnostic device 200, but also their part can be disposed at the outside of diagnostic device 200, between these devices, only data be communicated.
In addition, show in the diagnostic device of the equipment of present embodiment, be 1 situation as the equipment 100 of diagnosis object, but also can diagnose many seat apparatus 100 with 1 diagnostic device 200.
Next, the action of the diagnostic device 200 that possesses in the diagnostic device of equipment of present embodiment is described.
In the diagnostic device of the equipment of present embodiment shown in Figure 1, the measuring-signal 1 that will be measured the various quantity of states of equipment 100 via outer input interface 210 is taken into.Measuring-signal 3 is stored in the measuring-signal database 310 that is arranged in the diagnostic device 200.
In model definition unit 400, possess respectively service condition detection unit 500 and normalizing condition determination section 600.Model definition unit 400 is exported to model definition database 320 with respect to the input of measuring-signal 4 with model definition information 5.
Generating set has the starting operation of the constant constant load operation that moves of the output of making, starting equipment, the load variations out of service, that make exporting change of arrestment is moved.In service condition detection unit 500, use the savings data of the equipment 100 of savings in measuring-signal database 310, with these Data Segmentations be that constant load is in service, in the starting operation, out of service in, the operating operational mode of load variations.In addition, extract the characteristic quantity of operational mode separately.With Fig. 6 the detailed of this function is described.
In addition, in data mapping unit 700, measuring-signal is carried out normalized, as the pre-treatment that is used for constructing model.In normalizing condition determination section 600, decide suitable normalizing condition for each operational mode.Use Fig. 7～Fig. 9 to narrate in the back the detailed of this function.Aforesaid model definition information 5 is made of service condition data and normalizing condition data.
In data mapping unit 700, use the measuring-signal 4 of the equipment 100 in measuring-signal database 310, put aside and be kept at model definition information 6 in the model definition database 320, construct the model that in diagnosis, uses.To be kept in the diagnostic model database 330 by the model information 8 that data mapping unit 700 makes.
As the technology that data mapping unit 700 is installed, cluster (clustering) technology of self-elevating platform ART, vector quantization etc. is arranged.In addition, the model that uses in diagnosis is not limited to above-mentioned clustering method, can also use the statistical model of the model that utilized physical type, neural network etc.
In the diagnosis unit 800 in being arranged at described diagnostic device 200, input with respect to measuring-signal 4, by the model definition information 7 of reference model definition database 320 and the model information 9 of diagnostic model database 330, come the running status of equipment 100 is diagnosed, and export this diagnostic result 10.
The diagnostic result 10 with respect to the current running status of equipment 100 that diagnosis unit 800 is diagnosed out is sent to image display device set in the operational management chamber 900 940 via outside output interface 220, as image display information 11, and shown.Thus, will notify to the operating personnel that are positioned at operational management chamber 900 with respect to the diagnostic result of the running status of equipment 100.
So, in the diagnostic device 200 of the equipment of present embodiment, to the state of operating personnel's announcement apparatus situation about changing has occured.
In addition, be arranged at the image display device 940 that the diagnostic device information 50 of preserving in measuring-signal database 310 in the diagnostic device 200, model definition database 320, the diagnostic model database 330 can at random be shown in operational management chamber 900.In addition, these information can be revised by the external input signal 2 that the external input device 910 that is made of keyboard 920 and mouse 930 of operation generate.
Next, the action of diagnostic device of the equipment of present embodiment is described.Below, using the process flow diagram of the elemental motion of the diagnostic device that represents equipment shown in Figure 1 is the action flow chart that Fig. 2 (a) illustrates diagnostic device 200.
Like that, the elemental motion combination step 201,202,203 of diagnostic device 200 is carried out shown in the process flow diagram of Fig. 2 (a).
At first, in step 201, judge that the pattern of diagnostic device 200 is data mapping pattern or diagnostic mode.Then, in the situation that is the data mapping pattern, advance to step 202, when being diagnostic mode, advance to step 203.
If make step 202 action, then model definition unit 400,700 actions of data mapping unit.Its result, generation model definition information 5 and model information 8, the information that makes is stored in respectively in model definition database 320, the diagnostic model database 330.Use Figure 10 (a) narrate in the back the data mapping pattern action in detail.
In addition, if make step 203 action, then come the running status of equipment 100 is diagnosed by diagnosis unit 800, send to image display device 940 by the image display information 11 that will comprise diagnostic result, the running status of display device 100 on image display device 940.Use Figure 10 (b) narrate in the back diagnostic mode action in detail.
Can at random be specified by operating personnel the timing that makes data mapping pattern and diagnostic mode action of diagnostic device 200.Below, use Fig. 2 (b)～(d) illustrates respectively the various embodiment of the timing that makes data mapping pattern and diagnostic mode action.
In the embodiment shown in Fig. 2 (b), make data mapping pattern and diagnostic mode action in the sampling period of each measuring-signal, diagnose thus.
By when obtaining measuring-signal, all upgrading diagnostic model, can always use up-to-date diagnoses of models.
But, when the data volume in being used in data mapping is more, owing in data mapping, need the time, therefore have the possibility that within the sampling period, can't finish to calculate.
Under these circumstances, the embodiment shown in Fig. 2 (c) is such, can also make the action of normal condition data mapping pattern during the setting of each regulation, and each sampling period only makes the diagnostic mode action, diagnoses thus.In the method for the embodiment shown in Fig. 2 (b) and Fig. 2 (c), just carry out diagnostic mode whenever the sampling period, online the state of diagnostic device.
In addition, the embodiment shown in Fig. 2 (d) is such, by 200 inputs are used for the external input signal 2 that implementation model is constructed, diagnosed to diagnostic device by operating personnel, can regularly make arbitrarily the action of data mapping pattern and diagnostic mode.That is, can change various conditions comes the running status of equipment 100 is diagnosed.
Next, with Fig. 3, Fig. 4 the function that the measuring-signal 4 to equipment 100 that possesses in the data mapping unit 700 of diagnostic device 200 of diagnostic device of the equipment that consists of present embodiment and the diagnosis unit 800 is classified is described.
In the diagnostic device of the equipment of present embodiment, the situation of using self-elevating platform ART (Adaptive Resonance Theoty:ART) in the Data classification function is narrated.In addition, as the Data classification function, can use other the clustering method such as vector quantization.
Shown in Fig. 3 (a), the Data classification function is made of data pre-processing device 710 and ART module 720.Data pre-processing device 710 is transformed to service data the input data of ART module 720.
Below, their order (operation) that described data pre-processing device 710 and ART module 720 are carried out describes.
At first, in data pre-processing device 710, use the information of the normalizing condition of in model definition database 320, preserving to come by each measure the item data to be carried out normalization.To comprise measuring-signal will be carried out data Nxi (n) after the normalization and the complement CNxi (n) (=1-Nxi (n)) of the data after the normalization is made as input data I i (n) in interior data.This input data I i (n) is imported in the ART module 720.
In ART module 720, will be categorized as a plurality of classifications as the measuring-signal 4 of the equipment 100 of inputting data.
Next, the algorithm of ART module 720 is described.
The input data are inputed to the summary of algorithm of the situation of ART module 720, as following processing 1～processing 5.
Process 1: with input vector normalization, remove denoising by F0 layer 721.
Process 2: compare by input data and the weight coefficient that will be input to F1 layer 722, select the candidate of the classification that is fit to.
Process 3: by with parameter ρ recently estimate rationality by chooser system 725 selected classifications.If be judged as rationally, then will input Data classification and be this classification, advance to and process 4.On the other hand, if be not judged as rationally, this classification of then resetting, the candidate (repeatedly processing 2) of the classification that selection is fit to from other classification.As make the value of parameter ρ larger, and then the classification of classification is just careful, if make the value of parameter ρ less, then classification just becomes rough.This parameter ρ is called warning (vigilance) parameter.
Process 4: if processing whole known classification of having reset in 2, then be judged as the input data and belong to new classification, generate the new weight coefficient of the prototype of the new classification of expression.
Process 5: be classification J if will input Data classification, then the weight coefficient WJ corresponding with classification J is (new: as new) to use weight coefficient WJ in the past (old: as old) and the input data p data of input data fork (perhaps by), to upgrade according to following formula (1).
[several 1]
WJ (new)=Kwp+ (1-Kw) WJ (old) ... formula (1)
At this, Kw is Study rate parameter (0＜Kw＜1), is the value that determines input vector is reflected in the degree in the new weight coefficient.
In addition, formula (1) and formula described later (2) each arithmetic expression to formula (12) is embedded in the described ART module 720.
The data classification algorithm of ART module 720 is characterised in that above-mentioned processing 4.
Processing in 4, in the situation of having inputted the different input data of pattern (pattern) when having carried out study, can not change the pattern ground that has recorded and record new pattern.Therefore, while the pattern of the study of recording over records new pattern.
So, if give the service data of giving in advance as the input data, then 720 pairs of patterns of giving of ART module are learnt.Therefore, if the new input data of ART module 720 inputs to finishing study then can judge these input data approach which pattern in the past by above-mentioned algorithm.In addition, if the pattern that do not live through of past then is categorized as it new classification.
Fig. 3 (b) is the block diagram of the formation of expression F0 layer 721.In F0 layer 721, at each constantly once again to the input data I
iCarry out normalization, make the normalization input vector u that is input to F1 layer 721 and chooser system 725
i 0
At first, according to the input data I
i, calculate w according to formula (2)
i 0, at this, a is constant.
[several 2]
w
i 0=I
i+ au
i 0Formula (2)
Next, use formula (3) is calculated W
i 0Carry out the x that obtains after the normalization
i 0At this, || || be the mark of expression norm (norm).
[several 3]
Then, use formula (4) is calculated from x
i 0In except the V behind the denoising
i 0Wherein, θ is for the constant except denoising.The calculating of through type (4) because small value becomes 0, therefore, has been removed the noise of input data.
[several 4]
At last, use formula (5) is asked for normalization input vector u
i 0u
i 0It is the input of F1 layer.
[several 5]
Fig. 3 (c) is the block diagram of the formation of expression F1 layer 722.In F1 layer 722, the u that will ask in formula (5)
i 0Kept as short-term storage, calculated the p of input in F2 layer 722
iThe calculating formula of F2 layer is shown in formula (6)～formula (12) with gathering.Wherein, a, b are constants, and f () is the function by formula (4) expression, T
jIt is the grade of fit of calculating at F2 layer 722.
" several 6]
w
i=u
i 0+ au
iFormula (6)
[several 7]
[several 8]
v
i=f (x
i)+bf (q
i) ... formula (8)
[several 9]
[several 10]
[several 11]
Wherein,
[several 12]
Next, with Fig. 4 the function that possesses in the data mapping unit 700 of diagnostic device 200 of diagnostic device of the equipment that consists of present embodiment, construct model with the measuring-signal 4 of equipment 100 is described.
At first, use Fig. 4 (a) to come the embodiment of devices illustrated 100, narration is included in the information in the measuring-signal 4.Next, use Fig. 4 (b) and Fig. 4 (c) to narrate the appearance that measuring-signal 4 is categorized into classification.
Fig. 4 (a) is that the embodiment of indication equipment 100 is the block diagram of steam power plant.
In Fig. 4 (a), steam power plant 100 comprises gas turbo-generator 110, control device 120 and data sending device 130.Gas turbo-generator 110 comprises generator 111, compressor 112, burner 113 and turbine 114.
When generating electricity, the air that is sucked by compressor 112 is compressed and forms pressurized air, this pressurized air is sent into burner 113, burn with fuel mix.Make turbine 114 rotations with the gases at high pressure that produce by burning, generate electricity by generator 111.
In control device 120, correspondingly control the output of gas turbo-generator 110 with electricity needs.In addition, control device 120 will be arranged at the measured service data 102 conduct input data of sensor (not shown) of gas turbo-generator 110.Service data 102 is quantity of states of suction temperature, fuel input amount, turbine exhaust gas temperature, secondary speed, generator power output, turboshaft vibration etc., measures in each sampling period.In addition, also measure the weather information of atmospheric temperature etc.
In control device 120, calculate for the control signal 101 of controlling gas turbo-generator 110 with these service datas 102.In addition, in control device 120, the processing that the value that also is implemented in service data 102 has given the alarm when having broken away from predefined scope.Alarm signal is the digital signal of " 0 " in the time of in scope as being " 1 " when service data 102 has broken away from predefined scope, processes thus.When alarm signal is " 1 ", with sound or picture disply etc. with the context notification of alarm to operating personnel.
Signal data dispensing device 130 will comprise by the measured service data 102 of control device 120 and by control signal 101 and alarm signal that control device 120 is calculated and send to diagnostic device 200 at interior measuring-signal 1.
Fig. 4 (b) is that explanation will be categorized into from the measuring-signal 1 that equipment 100 is obtained the result's of classification figure.Transverse axis is the time, and the longitudinal axis is measuring-signal, classification numbering.Fig. 4 (c) is the figure of an example of the classification results that is categorized into classification of the measuring-signal 1 with equipment 100.
Fig. 4 (c) has shown 2 projects in the measuring-signal as an example, comes mark with two-dimentional chart.In addition, the longitudinal axis and transverse axis have carried out normalization to the measuring-signal of each project and have represented.
Measuring-signal is split into a plurality of classifications 1000 (circle shown in Fig. 4 (c)) by the ART module 720 of Fig. 3 (a).A circle is equivalent to 1 classification.
In the present embodiment, measuring-signal is classified as 4 classifications.The value of classification numbering 1 expression project A is large, the less group of value of project B, the all less group of value of classification numbering 2 expression project A, project B, the larger group of value value less, project B of classification numbering 3 expression project A, the value of classification numbering 4 expression project A, project B be larger group all.
Shown in Fig. 4 (b), the data between the normal epoch before the diagnosis beginning are classified as classification 1～3.The data of the first half after the diagnosis beginning are classified as classification 2, be with normal epoch between identical classification.In this case, since identical between the tendency of data and normal epoch, therefore be diagnosed as normal.On the other hand, the later half data after the diagnosis beginning are classified as classification 4, be from normal epoch between different classification.Because the tendency of data is different, therefore there are the state variation of equipment, the possibility of abnormal.In this case, in diagnostic device 200 of the present invention, this situation of possibility that has abnormal is shown to the operating personnel of equipment in image display device 940, notice is to operating personnel.
In addition, in the present embodiment, narrate the example that the measuring-signal of 2 projects is categorized as classification, but also can to 3 measuring-signals more than the project, be categorized as classification with multidimensional coordinate.
Fig. 5 is the figure of the relation of originate mode in the generating set shown in the key diagram 4 (a) and process values, shows the temporal evolution of output order value and turbine actuator temperature.
As representational originate mode, hot start and cold start are arranged.The situation of turbine and compressor being carried out restart under the state for heat is called hot start.In addition, will stop through the long time, the situation of carrying out restart under the state that turbine, compressor cool down is called cold start.Like that, if originate mode is different, the turbine actuator temperature when then beginning to start, the variation range of the temperature in the load variations are also different shown in Fig. 5 (b).
In existing diagnostic device, no matter how service condition all constructs 1 diagnostic model, therefore the normalization scope need to be determined as comprising data.That is, for example, the higher limit of normalization scope is made as 1010, lower limit is made as 1011.
For example, when the low load of hot start, compare with the scope 1020 that process values changes, normalization scope 1022 broadens.
If compare normalization wider range with the variation range of data, then the variation of the value after the normalization diminishes.Therefore, the variation of the data in the time of can't catching unusual the generation also can not produce new classification sometimes when unusual the generation.This becomes the reason of failing to report.
The model definition unit 400 that the application of the invention possesses can come suitably to determine the normalization scope matchingly with service condition.By this function, can suppress to fail to report, and improve diagnostic accuracy.Below, concrete method is described.
Fig. 6 is that the inscape of explanation model definition unit 400 is the process flow diagram of the action of service condition detection unit 500.As shown in Figure 6, this algorithm combination step 510,520,530,540,550 carry out.
At first, in step 510, with the Data Segmentation of savings in the measuring-signal 4 be that constant load is in service, in the starting operation, out of service in, load variations is operating during each.
When output did not change, in the situation that namely rate of change of the measuring-signal of output is less, it was in service to be made as constant load.In addition, according to the signal in being used for the difference starting, stopping in the measuring-signal that is included in generating set, in the load variations, be divided in the starting operation, out of service in, load variations operating during.
In the operating situation of constant load, advance to step 520, advance to step 530 in the situation in starting operation, advance to step 540 in the situation in out of service, in the operating situation of load variations, advance to step 550.
In step 520, extract the information relevant with the load band.For example, 0～50% of specified output is made as low output, is made as high output etc. with 50～100%, according to output the load band is classified.In step 530, extract with the kind of originate mode, the relevant information of loading rate in starting.As originate mode, hot start pattern, cold start pattern etc. are arranged.In step 540, extraction is the relevant information of output with stop mode, when stopping to move beginning.As stop mode, the pattern of arrestment in usually using is continuously arranged, when unusual the generation, carry out the pattern of emergency cut-off etc.In step 550, extraction and loading rate, output when load variations begins, the relevant information of output when load variations finishes.
In addition, in the present embodiment, in service, the starting operation of difference constant load in step 520,530,540,550, out of service in, the operating state of load variations, extract foregoing information, but can also increase this quantity of information.For example, the information that obtains so long as secondary speed, speed-raising rate, the kind that offers the fuel of equipment, atmospheric temperature etc. are processed the measuring-signal of equipment 100 then also can be appended in the information of extracting in step 520,530,540,550.
Shown in Fig. 6 (b), the set of having used diagnostic model 710 usefulness of identical measure the item to be categorized as the model of sub-diagnostic model 720 based on the information of extracting at Fig. 6 (a) is constructed.Every different normalizing condition of sub-diagnostic model definition diagnosed.
Below, use the clear and decided embodiment that decides the normalizing condition determination section 600 of normalizing condition of Fig. 7～Fig. 9.Use the information of the normalizing condition that normalizing condition determination section 600 determines, by data pre-processing device 710 with measuring-signal normalization.If the data items number of measuring-signal xi is N, n measuring-signal is x (n).Data Nxi after the normalization (n) represents with following formula (13).Wherein, Nmin (n) is normalized lower limit, and Nmax (n) is normalized higher limit.
[several 13]
Nxi (n)=(xi (n)-Nmin (n))/(Nmax (n)-Nmin (n)) ... formula (13)
In normalizing condition determination section 600, determine Nmin (n), the Nmax (n) shown in (13) formula.
Fig. 7 is the key diagram of the 1st embodiment of normalizing condition determination section 600.
Fig. 7 (a) is the process flow diagram of the 1st embodiment of normalizing condition determination section 600.Shown in Fig. 7 (a), this algorithm combination step 611,612,613 carry out.
At first, in step 611, come parted pattern to construct by each service condition and use data.In step 612, extract the information of measuring-signal amplitude of variation by each service condition.
In step 613, determine higher limit Nmax1 (n), the lower limit Nmin1 (n) of normalization scope of normalization scope.
In the operating situation of constant load, use (14), (15) formula.At this, Dmax1 (n) is the maximal value of measuring-signal, and Dmin1 (n) is minimum value.α, β are constants.
[several 14]
Nmax1 (n)=Dmax1 (n) * (1+ α) ... formula (14)
[several 15]
Nmin1 (n)=Dmin1 (n) * (1-β) ... formula (15)
In load variations, in the starting, in the situation in stopping, coupling output order value decides the normalization scope like that suc as formula (16), (17).
[several 16]
Nmax2=MW*a+b ... formula (16)
[several 17]
Nmin2=MW*c+d ... formula (17)
At this, MW is the output order value, and a, c are the slopes the when measuring-signal in the load variations is carried out first-order approximation.In addition, b, d are the values of calculating in formula (18), (19).
[several 18]
B=f+Dmax2 * 1.2 ... formula (18)
[several 19]
D=f-Dmin2 * 1.2 ... formula (19)
At this, f is the square that cuts the when measuring-signal in the load variations is carried out first-order approximation, and Dmax2 carries out the straight line of first-order approximation and the maximal value of the deviation between measuring-signal to measuring-signal, and Dmin2 is the minimum value of deviation.
Fig. 7 (b) be the explanation load from low output during to high exporting change output and the time dependent figure of measuring-signal.Until constantly T0a is low output, be load variations till from moment T0a to moment T0b, be later on high output at moment T0b.
By making the process flow diagram action shown in Fig. 7 (a), the higher limit of the normalization scope during with low output determines to be 1030, lower limit is determined to be 1040, the higher limit of the normalization scope in the load variations is determined to be 1050, lower limit is determined to be 1060, it is 1070 that the higher limit of the normalization scope when height is exported determines, lower limit is determined to be 1080.So, normalization scope of the present invention and service condition change matchingly.
Fig. 8 is the key diagram of the 2nd embodiment of normalizing condition determination section 600, and shown in Fig. 8 (a), this algorithm combination step 631,632,633 is carried out.
In step 631, extract the data of load variations pattern.In step 632, estimate the meaningless time by each data items.Process signal as inputoutput data, is estimated the meaningless time according to pulse (impulse) response.As concrete computing method, can enumerate list of references " be used for control superior system sign " (Tokyo motor university press office) (" system is driven the upper Grade シ ス テ system of め with deciding " (East Jing Electricity Machine university press office)) method put down in writing.In step 633, after the data of the amount of the meaningless time of in the step 632 that has been shifted, estimating, decide the normalization scope by each data items.
Use Fig. 8 (b) that this appearance is described.Compared with the moment T1a that the output order value begins to increase, the moment that measuring-signal begins to change is slower.This time is exactly the meaningless time.The meaningless time of data items A is (T2a-T1a), and the meaningless time of data items B is (T3a-T1a).
Make after measuring-signal departed from the amount of meaningless time at the process flow diagram that uses Fig. 8 (a), use the process flow diagram of Fig. 7 to decide the normalization scope.Thus, can cooperate with the output order value normalization scope that decides measuring-signal.
Fig. 9 is the key diagram of the 3rd embodiment of the normalizing condition determination section 600 in the diagnostic device of generating set shown in Figure 1.
With the maximal value of measuring-signal, near the minimum value normalization expanded range, thereby be easy to survey near the variation of the measuring-signal maximal value, minimum value.
In addition, the method for normalizing of normalizing condition determination section 600 is not limited to above-mentioned content, as long as decide normalizing condition by each service condition.For example, the scope of coming the data estimator value to change according to the specification of the design information of equipment, measuring appliance, with this scope as the normalization scope.
Figure 10 is the process flow diagram of pattern of the diagnostic device 200 of explanation generating set shown in Figure 1.Figure 10 (a) is the action flow chart of the data mapping pattern among Fig. 2, and Figure 10 (b) is the action flow chart of diagnostic mode.
Shown in Figure 10 (a), data mapping mode combinations step 1200,1210,1220,1230 is carried out.In step 1200, from measuring-signal database 310 be extracted in use the data mapping during data.Can at random set by the operating personnel of equipment 100 during this period.Next, in step 1210, make 500 actions of service condition detection unit.Process flow diagram shown in Fig. 6 (a) moves, Data Segmentation during will using in data mapping is in service as constant load, in the starting operation, out of service in, operating each operational mode of load variations, and then make step 520,530,540,550 actions, cut apart the data of each pattern by each feature.Next, in step 1220, make 600 actions of normalizing condition determination section.The process flow diagram of explanation among Fig. 7 (a), Fig. 8 (a) is moved, decide normalizing condition by each group of in step 1210, cutting apart.The model definition information 5 that step 1210,1220 is moved and obtain is kept in the model definition database 320.At last, in step 1230, make 700 actions of data mapping unit.Each group of cutting apart in step 1210 is defined as sub-diagnostic model 720 (with reference to Fig. 6 (b)), uses the normalizing condition that defines by every sub-diagnostic model to process measuring-signal, constructs diagnostic model with the described ART of Fig. 3.
Shown in Figure 10 (b), diagnostic mode combination step 1300,1310,1320 is carried out.In step 1300, the data during extraction is diagnosed from measuring-signal database 310.Next, in step 1310, process data between diagnostic period with service condition detection unit 500.From a plurality of sub-diagnostic model of the data mapping pattern, constructing, extract the consistent sub-diagnostic model of service condition.At last, in step 1320, make diagnosis unit 800 actions.In diagnosis unit 800, from model definition database 320, be extracted in the sub-diagnostic model information that extracts in the step 1330.The classification of sub-diagnostic model numbering, the classification that obtains with ART the data between diagnostic period being classified numbered compare.Be and making data mapping pattern when action during identical classification, be diagnosed as normally, when having produced different classification numberings, be diagnosed as unusual.Diagnostic result 10 is outputed to outside output interface 220.
Figure 11 is the figure that explanation is kept at the form of the data in the database of the present invention.
Shown in Figure 11 (a), in measuring-signal database 310, preserve the value that the service data that equipment 100 is measured is measuring-signal 1 (in the drawings, having put down in writing data items A, B, C) by each sampling period (moment of the longitudinal axis).
In display frame 311, by using the scrolling bar 312 and 313 of energy cross shifting, the data of energy roll display wide region.
In model definition database 320, shown in Figure 11 (b), the information of service condition and normalization scope is set up correspondence preserve.
In the diagnostic model database, shown in Figure 11 (c), the relation of retention class numbering and weight coefficient.At this, weight coefficient is the centre coordinate of classification.
Figure 12 is the figure of effect of the diagnostic device of explanation generating set shown in Figure 1.
T4 begins load variations in the moment, finishes load variations at moment T5.After load variations finished, T6 had occured unusually in the moment.
Figure 12 is illustrated the relation of output order value and the turbine temperature relation with the measuring-signal of classification numbering, temperature.Follow unusual generation and the temperature rising, but owing to be in the scope of classification 4, therefore be classified as in the classification identical with normal condition.In existing mode, enlarged the normalization scope, can't catch the temperature of following unusual generation and rise, can not survey unusual.
In the present invention, the coupling service condition is switched diagnostic model.In the present embodiment, according to until constantly T4 diagnose with service condition 1 diagnostic model (constant load in service, hang down output model), between moment T4～T5, diagnose with service condition 2 diagnostic models (load variations is in service), switch in the mode that moment T5 uses later on service condition 3 diagnostic models (constant load is moved middle and high output model) to diagnose.
In service condition 3 diagnostic models, normal condition is categorized as classification numbering 1～5.Be classified as the classification identical with normal condition before unusual the generation, but the data after unusual the generation are classified as the new classification of classification numbering 6, can detect unusual.That is, owing to more meticulously state is classified than prior art, therefore can suppress to survey unusual failing to report.
Figure 13 is the figure of picture shown in the image display device 940 in the diagnostic device 200 of explanation generating set shown in Figure 1.
Operate cursor 951 with mouse 930, thereby can at random adjust the higher limit (954,956,958) of normalization scope, the lower limit (955,957,959) of normalization scope, the border moment (952,953) of service condition.For the result that will adjust is reflected in the model, click executive button 960 at the picture of Figure 13.By this operation, changed the service condition of the model definition database shown in Figure 10 (b) and the information of normalization scope, can be reflected in data mapping and the diagnostic action adjusting the result.
In addition, the present invention is not limited to the above embodiments, also comprises various variation.For example, for above-described embodiment has carried out detailed record for the explanation the present invention of easy to understand ground, but be not limited to possess whole formations of explanation.
In addition, each above-mentioned formation, function, handling part, processing unit etc. also can design etc. with hardware by integrated circuit and realize wherein part or all.In addition, each above-mentioned formation, function etc. also can realize by explain the program that realizes each function and the software of being carried out for the treatment of device.Realize that program, form, file, the measuring-signal of each function, the information of calculating information etc. can place the storage medium of the memory storage of storer or hard disk etc. or IC-card, SD card, DVD etc.Therefore, each is processed, respectively consists of and can realize as processing member, program module.
In addition, think needs and show information wire in explanation, but on the goods whole control lines or information wire might not be shown.In fact, can think that also most formation all is connected to each other.
According to present embodiment, can obtain to survey accurately the diagnostic device of unusual generating set of generating set and the diagnostic method of equipment.
Utilizability on the industry
The present invention can be as the diagnostic method of the diagnostic device of equipment and equipment and is widely used in various device etc.
Claims (14)
1. the diagnostic device of a generating set comes the running status of diagnostic device based on the measuring-signal that obtains from generating set measuring state amount, and diagnostic result is shown in the image display device, and the diagnostic device of this generating set is characterised in that to possess:
The data mapping unit, it uses the measuring-signal of measuring the quantity of state of generating set and obtain in the diagnostic device of generating set, constructs the model that uses in diagnosis;
The model definition unit, the service condition that its definition is diagnosed by described model and the method for normalizing of measuring-signal; With
Diagnosis unit, it uses the model of being constructed by described data mapping unit to diagnose the running status of generating set,
In described model definition unit, possess:
The service condition detection unit, it judges the service condition of generating set; With
The normalizing condition determination section, it decides the normalizing condition of measuring-signal by each service condition of being judged by the service condition detection unit,
In described diagnosis unit, mate to switch diagnostic model with service condition, thereby diagnose.
2. the diagnostic device of generating set according to claim 1 is characterized in that,
Described service condition detection unit possesses:
With the service condition of generating set be categorized as that constant load is in service, in the starting operation, out of service in, operating any one the arithmetic unit of load variations;
Be to extract the arithmetic unit of load band in the operating situation of constant load in service condition;
Be to extract the kind of originate mode and the arithmetic unit of loading rate in the situation in the starting operation in service condition;
Extract the kind of stop mode and the arithmetic unit that begins to export that stops to move in out of service; With
In load variations is in service, extract the arithmetic unit of loading rate, the output when load variations begins, the output when load variations finishes.
3. the diagnostic device of generating set according to claim 1 is characterized in that,
In described normalizing condition determination section, possess:
Come parted pattern to construct the arithmetic unit of using data by each service condition of being judged by described service condition detection unit;
Extract the arithmetic unit of information of the data variation amplitude of each service condition; With
Decide the arithmetic unit of normalization scope based on the information of described data variation amplitude.
4. the diagnostic device of generating set according to claim 3 is characterized in that,
The diagnostic device of described generating set possesses the arithmetic unit that the normalization scope of the measuring-signal in the load variations is made as the function of output order value.
5. the diagnostic device of generating set according to claim 3 is characterized in that,
In described normalizing condition determination section, make for the measuring-signal in the load variations and estimate the arithmetic unit of meaningless time and make after the arithmetic unit action of amount of the estimated meaningless time that goes out of measuring-signal displacement, make arithmetic unit action claimed in claim 3.
6. the diagnostic device of each described generating set is characterized in that according to claim 3～5,
In described normalizing condition determination section, possess and enlarge at the maximal value of measuring-signal, near the minimum value the arithmetic unit of normalization scope.
7. the diagnostic device of generating set according to claim 1 is characterized in that,
The diagnostic device of described generating set possesses picture display device, moment that this picture display device makes the time dependent trend chart of expression measuring-signal, switch the service condition of being judged by described service condition identifying unit and be piled up by the normalization scope that described normalizing condition determining means determines shows, and is used at random changing the moment and the described normalization scope that described service condition is switched.
8. the diagnostic method of a generating set, come the running status of diagnostic device based on the measuring-signal that obtains from generating set measuring state amount, and diagnostic result is shown in the image display device, the diagnostic method of this generating set is characterised in that to possess following steps:
Judge the step of the service condition of generating set;
Decide the step of the normalizing condition of measuring-signal by each service condition of being judged by the service condition detection unit;
Use is measured the quantity of state of generating set and the measuring-signal that obtains in the diagnostic device of generating set, the step of constructing the model that uses in the diagnosis;
The step of the service condition that definition is diagnosed by described model and the method for normalizing of measuring-signal; With
Mate to switch diagnostic model with service condition, thus the step of diagnosing.
9. the diagnostic method of generating set according to claim 8 is characterized in that,
The step of judging the service condition of described generating set possesses:
With the service condition of generating set be categorized as that constant load is in service, in the starting operation, out of service in, operating any one the step of load variations;
Be to extract the step of load band in the operating situation of constant load in service condition;
Be to extract the kind of originate mode and the step of loading rate in the situation in the starting operation in service condition;
Extract the kind of stop mode and the step that begins to export that stops to move in out of service; With
In load variations is in service, extract the step of loading rate, the output when load variations begins, the output when load variations finishes.
10. the diagnostic method of generating set according to claim 8 is characterized in that,
In the step that determines described normalizing condition, possess:
Come parted pattern to construct the step of using data by each service condition of being judged by described service condition detection unit;
Extract the step of information of the data variation amplitude of each service condition; With
Decide the step of normalization scope based on the information of described data variation amplitude.
11. the diagnostic method of generating set according to claim 10 is characterized in that,
Possesses the step that the normalization scope of the measuring-signal in the load variations is made as the function of output order value.
12. the diagnostic method of generating set according to claim 10 is characterized in that,
In determining the step of described normalizing condition, carry out estimate the step of meaningless time for the measuring-signal in the load variations and make the step of amount of the estimated meaningless time that goes out of measuring-signal displacement after, enforcement of rights requires 10 described steps.
13. the diagnostic method of each described generating set is characterized in that according to claim 10～12,
In determining the step of described normalizing condition, possess and enlarge in the maximal value of measuring-signal, near the minimum value the step of normalization scope.
14. the diagnostic method of generating set according to claim 8 is characterized in that,
Moment that makes the time dependent trend chart of expression measuring-signal, the service condition of being judged by described service condition identifying unit is switched and be piled up by the normalization scope that described normalizing condition determining means determines shows, and can at random change the moment and the described normalization scope that described service condition is switched.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2011-197837 | 2011-09-12 | ||
| JP2011197837A JP5337853B2 (en) | 2011-09-12 | 2011-09-12 | Power plant diagnostic device and power plant diagnostic method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102999038A true CN102999038A (en) | 2013-03-27 |
| CN102999038B CN102999038B (en) | 2015-12-02 |
Family
ID=47927732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210288454.4A Active CN102999038B (en) | 2011-09-12 | 2012-08-07 | The diagnostic device of generating set and the diagnostic method of generating set |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP5337853B2 (en) |
| CN (1) | CN102999038B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110506245A (en) * | 2017-06-28 | 2019-11-26 | 株式会社日立制作所 | Diagnostic device and diagnostic method |
| CN113287104A (en) * | 2019-03-12 | 2021-08-20 | 株式会社日立制作所 | Data sorting device |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6116466B2 (en) * | 2013-11-28 | 2017-04-19 | 株式会社日立製作所 | Plant diagnostic apparatus and diagnostic method |
| TR201909282T4 (en) * | 2014-04-01 | 2019-07-22 | Tlv Co Ltd | Risk assessment system, risk assessment program and risk assessment method for the trading system. |
| JP6514239B2 (en) * | 2015-01-20 | 2019-05-15 | 株式会社日立製作所 | Machine diagnostic device and machine diagnostic method |
| JP6438124B2 (en) * | 2015-04-20 | 2018-12-12 | 株式会社日立製作所 | Operation management system and operation management method |
| JP6606003B2 (en) * | 2016-03-31 | 2019-11-13 | 株式会社東芝 | Process diagnostic apparatus, process diagnostic method, and computer program |
| JP6802025B2 (en) * | 2016-09-30 | 2020-12-16 | メタウォーター株式会社 | Valve operation monitoring method and valve operation abnormality sign detection method |
| JP6772963B2 (en) * | 2017-06-05 | 2020-10-21 | トヨタ自動車株式会社 | Abnormality diagnosis device and abnormality diagnosis method |
| JP7138441B2 (en) * | 2018-01-11 | 2022-09-16 | 三菱電機株式会社 | Soundness evaluation device and power generation system |
| JP7097263B2 (en) * | 2018-08-28 | 2022-07-07 | 株式会社日立製作所 | Plant data analysis system |
| JP7408911B2 (en) * | 2018-10-26 | 2024-01-09 | 富士電機株式会社 | Anomaly detection device and anomaly detection method |
| JP7175752B2 (en) * | 2018-12-27 | 2022-11-21 | 株式会社クボタ | Diagnostic method for mechanical equipment and diagnostic device for mechanical equipment |
| JP7012888B2 (en) * | 2019-01-21 | 2022-01-28 | 三菱電機株式会社 | Abnormal factor estimation device, abnormal factor estimation method, and program |
| WO2020166468A1 (en) * | 2019-02-15 | 2020-08-20 | パナソニックＩｐマネジメント株式会社 | Playback system, recording system, playback method, program for playback, recording method, and program for recording |
| JP2021096492A (en) * | 2019-12-13 | 2021-06-24 | 三菱電機株式会社 | Diagnostic device, power generation facility, data creation method, and diagnostic program |
| JP7222943B2 (en) * | 2020-02-26 | 2023-02-15 | 株式会社日立製作所 | Operation improvement support system, operation improvement support method, and operation improvement support program |
| JP2021181145A (en) * | 2020-05-20 | 2021-11-25 | オムロン株式会社 | Screw tightening failure determination device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11161327A (en) * | 1997-11-28 | 1999-06-18 | Mitsubishi Chemical Corp | Method and device for diagnosing abnormality of process |
| CN102129013A (en) * | 2011-01-21 | 2011-07-20 | 昆明理工大学 | Distribution network fault location method utilizing natural frequency and artificial neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2809860B2 (en) * | 1990-10-18 | 1998-10-15 | 株式会社東芝 | Plant process input value generator |
| JP4313734B2 (en) * | 2004-07-16 | 2009-08-12 | ヤンマー株式会社 | Monitoring and diagnosis system |
| JP2010244149A (en) * | 2009-04-02 | 2010-10-28 | Hitachi Ltd | Data classification method, data classification device, diagnostic method and diagnostic device |
| JP5431235B2 (en) * | 2009-08-28 | 2014-03-05 | 株式会社日立製作所 | Equipment condition monitoring method and apparatus |
-
2011
- 2011-09-12 JP JP2011197837A patent/JP5337853B2/en active Active
-
2012
- 2012-08-07 CN CN201210288454.4A patent/CN102999038B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11161327A (en) * | 1997-11-28 | 1999-06-18 | Mitsubishi Chemical Corp | Method and device for diagnosing abnormality of process |
| CN102129013A (en) * | 2011-01-21 | 2011-07-20 | 昆明理工大学 | Distribution network fault location method utilizing natural frequency and artificial neural network |
Non-Patent Citations (1)
| Title |
|---|
| 巨林仓 等: ""基于LM算法建立风电机组神经网络故障预警诊断模型"", 《热力发电》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110506245A (en) * | 2017-06-28 | 2019-11-26 | 株式会社日立制作所 | Diagnostic device and diagnostic method |
| CN113287104A (en) * | 2019-03-12 | 2021-08-20 | 株式会社日立制作所 | Data sorting device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102999038B (en) | 2015-12-02 |
| JP5337853B2 (en) | 2013-11-06 |
| JP2013061695A (en) | 2013-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102999038B (en) | The diagnostic device of generating set and the diagnostic method of generating set | |
| JP5544418B2 (en) | Plant diagnostic device, diagnostic method, and diagnostic program | |
| WO2012073289A1 (en) | Plant diagnostic device and plant diagnostic method | |
| JP5199478B2 (en) | Plant diagnostic equipment | |
| EP3477412B1 (en) | System fault isolation and ambiguity resolution | |
| JP5427107B2 (en) | Monitoring and diagnosis apparatus and monitoring diagnosis method | |
| JP5301717B1 (en) | Equipment condition monitoring method and apparatus | |
| US7395188B1 (en) | System and method for equipment life estimation | |
| US7720640B2 (en) | Diagnostic data detection and control | |
| CN102713777B (en) | Diagnostic apparatus and diagnostic method | |
| US7933754B2 (en) | System and method for damage propagation estimation | |
| JP2019016209A (en) | Diagnosis device, diagnosis method, and computer program | |
| CN104756029B (en) | A kind of system of the parts group of monitoring device | |
| JP5097739B2 (en) | Plant abnormality diagnosis apparatus and abnormality diagnosis method | |
| CN107710089B (en) | Plant equipment diagnosis device and plant equipment diagnosis method | |
| JP5150590B2 (en) | Abnormality diagnosis apparatus and abnormality diagnosis method | |
| JP6830414B2 (en) | Diagnostic device and diagnostic method | |
| JP6685124B2 (en) | Diagnostic device and diagnostic method | |
| King et al. | Probabilistic approach to the condition monitoring of aerospace engines | |
| US20230046709A1 (en) | Prediction apparatus, prediction method, and program | |
| Breikin et al. | Application of Markov chains to identification of gas turbine engine dynamic models |
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 |