CN102890495B - Complete plant diagnosis methods and complete plant diagnosis apparatus - Google Patents
Complete plant diagnosis methods and complete plant diagnosis apparatus Download PDFInfo
- Publication number
- CN102890495B CN102890495B CN201210245867.4A CN201210245867A CN102890495B CN 102890495 B CN102890495 B CN 102890495B CN 201210245867 A CN201210245867 A CN 201210245867A CN 102890495 B CN102890495 B CN 102890495B
- Authority
- CN
- China
- Prior art keywords
- model
- classification
- input
- input variable
- equipments
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 110
- 238000003745 diagnosis Methods 0.000 title abstract description 34
- 238000002405 diagnostic procedure Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 abstract description 7
- 230000005856 abnormality Effects 0.000 abstract description 4
- 238000012217 deletion Methods 0.000 abstract description 3
- 230000037430 deletion Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 abstract description 3
- 239000003245 coal Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 230000002159 abnormal effect Effects 0.000 description 11
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000003825 pressing Methods 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 7
- 238000010248 power generation Methods 0.000 description 7
- 230000015572 biosynthetic process Effects 0.000 description 6
- 238000012937 correction Methods 0.000 description 6
- 239000007789 gas Substances 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 239000000523 sample Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000005611 electricity Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 102100024405 GPI-linked NAD(P)(+)-arginine ADP-ribosyltransferase 1 Human genes 0.000 description 1
- 101000981252 Homo sapiens GPI-linked NAD(P)(+)-arginine ADP-ribosyltransferase 1 Proteins 0.000 description 1
- 241001272996 Polyphylla fullo Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides complete plant diagnosis methods and a complete plant diagnosis apparatus. In a case of using a process signal obtained from a complete plant for abnormality or omen diagnosis, if the plant to be diagnosed is replaced or in maintenance, diagnosis results which has been accumulated previously or diagnosis functions which has been constructed in a diagnosis model can not be used, and the diagnosis model is required to be reconstructed. In the complete plant diagnosis method of the invention, a model in which correlations between input variables are modeled is maintained, input data is divided into a plurality of classes based on the correlations between the input variables, and the abnormality of the complete plant is detected based on the classes not belonging to normal classes after the classification, wherein if the complete plant is modified and the model is changed by the addition or deletion of the input variables, a new model is constructed by changing the numbers of the classes of the model.
Description
Technical field
The present invention relates in the abnormity diagnosis of the set of equipments be made up of multiple equipment (plant), even if also do not build again when newly adding in the maintenance after starting operation or delete the process relevant to abnormity diagnosis, diagnostic method and the device of the abnormality diagnostic set of equipments of set of equipments can be continued.
Background technology
About the power plant being representative with firepower or atomic power device or with in pharmaceuticals/food/chemical set of equipments industry set of equipments that is representative, in order to be embodied as the stable utilization of complete equipment, using multiple process signal as monitored object.
Specifically, in order to grasp the state of set of equipments, the measuring appliance being used for measuring pressure, temperature, flow, water level etc. is arranged at each portion, and the display of obtained process signal value is supplied to operations staff.In addition, in nearly all set of equipments, based on the viewpoint of exception or trouble shooting or maintenance, the process signal value of acquisition is kept at as in the process computer (processcomputer) of special purpose computer.
Operations staff deposits in varying situations in the state of set of equipments, in order to confirm whether the value of the process signal be associated also exists change, and monitoring image shows the value of this process signal.In addition, if be necessary, the value in the past of this process signal stored in process computer is also shown on monitoring image.Usually, the operating control device of set of equipments becomes to be integrated with monitoring arrangement, can be implemented as supervision or the control of complete equipment state in real time.
In prior art, when set of equipments state changes, operations staff makes the value of the process signal associated with monitoring arrangement be presented on monitoring image.Be taken into the cycle according to monitoring arrangement, upgrade the value of shown process signal online.The running status of set of equipments is grasped based on the state of this process values.Operating control device or monitoring arrangement (hereinafter referred to as " Monitor and Control device ") carry out interlock with the alarm device of the state of Kernel-based methods value.Such as, when certain force value is than setting value height, the stand by lamp be used in operations staff notifies carries out lighting.Further, starting, operates to the control of normal condition to impel operations staff for the recovering state from exception.
Recently, discuss before abnormality produces, the device that the abnormal sign of set of equipments is predicted or its method.In addition, also have after abnormal generation, carry out specific to its reason and analyze servicing unit or its method of reason.
In the system of patent documentation 1, the alert level corresponding to level is utilized to carry out the diagnosis of set of equipments.
In patent documentation 2, disclose possess for transmit operation and control information, field data, facility information network and show the device of information terminal device and the method for these information.
Patent documentation 1:JP JP 2005-258649 publication
Patent documentation 2:JP JP 2011-70334 publication
Non-patent literature 1:G.A.Carpenter and S.Grossberg: " ART2 Self-Organization of stable category recognition codes for analog input patterns ", Applied Optics, Vol.26, No.23, (1987)
Set of equipments is made up of multiple equipment.In addition, the scale of each equipment is also not of uniform size.When diagnosing set of equipments, according to scale or function, based on the process signal be associated, use wherein utilize statistically to process or situation that statistical model that study that neural network is representative etc. is constructed is such more.The correlationship of inputted process signal is carried out modelling by statistical model.
Patent documentation 1 and the method described in patent documentation 2 are all the diagnostic methods of the set of equipments that make use of self-elevating platform ART (Adaptive Resonance Theory, ART).ART is the one of the sorter Data classification of input being become multiple classification.
At this, by not inputing to ART containing abnormal plant process signal, be categorized into multiple classification.In diagnosis when abnormal generation, by process signal is input to ART, generate do not belong to existing new classification (category) that sort out time, owing to creating the set of equipments state do not had so far, therefore give a warning.
, power plant etc. are longer due to utilization year number, may add new equipment on the way, may chase after and establish or remove measuring appliance.In the diagnosis that make use of ART, due to maintenance as described above, when the process signal inputted changes or increases and decreases, directly can not diagnose, need the classification again implemented based on ART to classify.But, use when year, number was elongated, because the time series data amount of the process signal accumulated for this to this is huge, therefore be difficult to build again.
Summary of the invention
The object of the present invention is to provide a kind of diagnostic method and the device that solve the set of equipments of above-mentioned problem.
In order to solve aforementioned problems, in the diagnostic method of set of equipments of the present invention, the correlationship of input variable is kept to carry out the model after modelling, according to the correlationship of input variable, be multiple classification by inputted Data classification, and the exception of set of equipments is detected according to the sorted generation not belonging to the normal classification sorted out, wherein, create the model adding or delete such change of input variable about the amendment according to set of equipments, build new model by the change of the classification numbering that make use of this model.
In addition, when having added input variable to existing model, only build diagnostic model with the input variable added, number to generate based on the classification numbering obtained from existing model and the classification obtained from added diagnostic model the model that new classification numbers.
In addition, when deleting input variable from existing model, to be normalized and the value of the input variable of deleting in the input variable inputted is set to fixed value, and the time series data of each input variable in utilizing the classification of this model to number carrys out the change of execution model.
In addition, when deleting input variable from existing model, the value being normalized the input variable of deleting in the input variable of rear and input is set to fixed value, and the time series data of each input variable in utilizing the classification of this model to number carrys out the change of execution model, and additional process terminate after carry out delete processing.
For solving aforementioned problems, in the diagnostic method of set of equipments of the present invention, the correlationship of the input variable obtained from monitored object is carried out modelling, the Data classification being input to model is become multiple classification, and the exception of set of equipments is detected according to the sorted generation not belonging to the normal classification sorted out, wherein, the correlationship of the 1st input variable is carried out modelling and kept as feature model, and according to the correlationship of the 1st input variable, inputted Data classification is become multiple classification, and the correlationship of the 2nd added input variable is also carried out modelling, inputted Data classification is become multiple classification, form the unified model based on the 2nd input variable after feature model and institute's modelling.
In addition, unified model comprises the determined new classification of combination by the classification by the 2nd input variable after the classification of feature model and institute's modelling.
For solving aforementioned problems, the diagnostic device of set of equipments of the present invention is according to the measuring-signal obtained the control signal from the Monitor and Control device controlled monitored object or the process computer from the process signal of input monitored object, detect the exception of monitored object, the diagnostic device of this set of equipments possesses: feature model portion, the correlationship of the signal of input is carried out modelling to make feature model by it, the Data classification be input in feature model is become multiple classification by the correlationship according to input signal, and the exception of set of equipments is detected according to the sorted generation not belonging to the normal classification sorted out, and unified model portion, it possesses the unified model of the feature model at least comprising more than 1, the Data classification being input to unified model is become multiple classification by the correlationship according to input signal, and the exception of set of equipments is detected according to the sorted generation not belonging to the normal classification sorted out, the feature model added of input signal is created about the amendment according to control object, only build diagnostic model with the input signal added, number to generate new classification based on the classification numbering obtained from existing feature model with the classification obtained from added diagnostic model to number, and then the model that will generate new classification numbering and obtain is stored in unified model portion as unified model.
In addition, when deleting input variable from existing model, to be normalized and the value of the input variable of deleting in the input variable inputted is set to fixed value, and the time series data of each input variable in utilizing the classification of this model to number carrys out the change of execution model.
Invention effect
In the diagnostic method and device of set of equipments of the present invention, even if the process signal that should monitor at the input signal as diagnostic model or confirm occurs to change or add/delete, can constantly by diagnostic result or tendency display reminding to operations staff or maintenance person, the stable utilization of power plant or industry set of equipments can be conducive to.
Accompanying drawing explanation
Fig. 1 is the figure diagnostic device of set of equipments of the present invention being applied to power plant.
Fig. 2 is the system chart of the formation of the thermal power generation complete equipment represented as diagnosis object.
Fig. 3 is the enlarged drawing in pipe arrangement portion in thermal power generation complete equipment and air heater portion.
Fig. 4 is the figure of the storage format representing the data stored in process computer 300.
Fig. 5 is the figure of the example representing the information stored in model information database 450.
Fig. 6 is the figure of the example representing the information stored in model information database 450.
Fig. 7 is the figure of an example of the information representing the diagnostic result stored in diagnostic result database 480.
Fig. 8 is the process flow diagram of the contents processing representing feature model preparing department 420.
Fig. 9 is the process flow diagram of the contents processing representing unified model preparing department 430.
Figure 10 is the process flow diagram of the contents processing representing key element diagnostics division 460 and comprehensive diagnos portion 470.
Figure 11 is the figure of the initial picture represented shown by image display device.
Figure 12 is the figure of the diagnostic model setting screen represented shown by image display device.
Figure 13 is the figure of the tendency chart of the process signal represented shown by image display device.
Figure 14 is the figure of the diagnostic result display setting picture represented shown by image display device.
Figure 15 is the figure of the indication example of the diagnostic result represented shown by image display device.
Label declaration
100: power plant
200: Monitor and Control device
300: process computer
400: set of equipments diagnostic device
410: outer input interface
420: feature model preparing department
430: unified model preparing department
450: model information database
460: key element diagnostics division
470: comprehensive diagnos portion
480: diagnostic result database
490: outside output interface
900: input media
901: keyboard
902: mouse
910: aid
920: outer input interface
930: data transmission and reception handling part
940: outside output interface
950: image display device
Embodiment
Below, with reference to accompanying drawing, the diagnostic method of the set of equipments of preferred forms and device are described.
Embodiment
Fig. 1 illustrates the figure be applied to by the diagnostic device of the set of equipments involved by present embodiment as the example in the power plant 100 of a certain object.In power plant 100, be provided with multiple measuring appliance to grasp the state of set of equipments.Via industrial siding or general transmission line, the value by the process signal 10 measured by each measuring appliance is transferred to Monitor and Control device 200 and is used for the process computer 300 of store measurement values.
Monitor and Control device 200 exports the control signal 20 for set of equipments operation being remained the state of expectation based on the value of process signal 10.The control signal 20 exported is imported into power plant 100, and is also input to set of equipments diagnostic device 400.
The value of the process signal 10 obtained from power plant 100 is accumulated in process computer 300.The process signal 10 accumulated, according to its purposes, exports to exception/set of equipments diagnostic device 400 as process signal 30.About storage format, be described in detail with reference to Fig. 4 thereafter.
Control signal 20 needed for diagnosis or process signal 30 are taken into via outer input interface 410 by set of equipments diagnostic device 400.On the other hand, set of equipments diagnostic device 400 is connected with aid 910 via outside output interface 490, outer input interface 410, the operation signal of input user, the operation signal of such as input operator by the information displaying of necessity in display device 950.
The outer input interface 410 of set of equipments diagnostic device 400 according to the instruction from aid 910, switching model forming types and diagnostic mode.When for model construction pattern, the control signal 20 that feature model preparing department 420 is inputted or process signal 30, when diagnostic mode, the control signal 20 that key element diagnostics division 460 is inputted or process signal 30.
In feature model preparing department 420, make the ART model corresponding to diagnosis object.When there being multiple diagnosis object, make the ART model of equal number.When making ART model, the process signal 30 of normal condition is inputed to ART model.In ART model, according to the correlationship of inputted process signal 30, input data are classified.Be referred to as classification (category).The resolution of this classification is driven by the size of alarm parameters.About the suitable establishing method of this alarm parameters, propose in aforesaid patent documentation 1 or patent documentation 2.In addition, about the detailed action of ART model, it is recorded in detail in non-patent literature 1, therefore detailed.
The alarm parameters of each ART model or classification number etc. are stored in model information database 450.In addition, as required, information extraction from model information database 450.About the formation of the detailed action in feature model preparing department 420 or model information database 450, will in rear detailed description.The configuration example of model information database 450 as shown in Figure 5, Figure 6.
Next, in unified model preparing department 430, make and namely the output of the ART model made in feature model preparing department 420 is sorted out the new ART model of numbering as input data.Identically with feature model preparing department 420, by the alarm parameters of ART model or classification numbering etc., model information database 450 and outside output interface 490 is outputted to.In addition, as required, information extraction from model information database 450.About the formation of the detailed action in unified model preparing department 430 or model information database 450, will in rear detailed description.
When receiving the instruction of diagnostic mode by outer input interface 410, data are inputted to key element diagnostics division 460.In key element diagnostics division 460, from model information database 450, load the information of diagnostic model.To be loaded diagnostic model, input input data, diagnose.According to the data being input to diagnostic model, be categorized as the classification that makes in advance or make new classification based on the correlationship of new input data.
When having made new classification, meaning and having detected the state different from normal condition, be diagnosed as abnormal omen.The output comprised now is sorted out the ground such as numbering and is stored in diagnostic result database 480.In addition, comprehensive diagnos portion 470 is also exported to.About the formation of the detailed action in key element diagnostics division 460 or diagnostic result database 480, will in rear detailed description.The configuration example of diagnostic result database 480 as shown in Figure 7.
In comprehensive diagnos portion 470, from model information database 450, load the information of diagnostic model, the output from key element diagnostics division 460 is inputed to diagnostic model, diagnoses in the same manner.Diagnostic result is stored in outside output interface 490 and diagnostic result database 480.In addition, about the detailed action in comprehensive diagnos portion 470, will in rear detailed description.
The Output rusults in unified model preparing department 430 or comprehensive diagnos portion 470 is outputted to maintenance aid 910 by outside output interface 490.
As the user relevant to power plant 100, such as operator, by utilizing the input media 900 be made up of with mouse 902 keyboard 901 and the aid 910 be connected with image display device 950, can see the various information that power plant 100 is relevant.In addition, the information of the control signal 20 from Monitor and Control device 200, the process signal 30 from process computer 300, the diagnostic result of set of equipments diagnostics division 400, model information database 450, diagnostic result database 480 can be accessed.
Aid 910 is made up of outer input interface 920, data transmission and reception handling part 930, outside output interface 940.
The input signal 91 generated at input media 900 is taken in aid 910 via outer input interface 920.In addition, in aid 910, about the information of the control signal 20 from Monitor and Control device 200, the process signal 30 from process computer 300, diagnostic result 40 from set of equipments diagnostic device 400, model information database 450, diagnostic result database 480, be also taken into by outer input interface 920 in the same manner.In data transmission and reception handling part 930, the information according to the input signal 91 from user processes input signal 92, and sends to outside output interface 940 as output signal 93.Output signal 94 shows at image display device 950.
In the following description, data processing equipment of the present invention to be applied to the situation of thermal power generation complete equipment, the processing capacity about the information of preserving in database and signal is described.
Fig. 2 is the system chart of the formation of the thermal power generation complete equipment of the object represented as diagnosis.In this example, the structure of the generating in the thermal power generation complete equipment of coal combustion is described.
When taking coal as fuel, provide coal from the coal-hole 111 of storage coal via coal supply device 112 pairs of mullers 110.In muller 110, by the transfer roller of inside, coal grinding is thinned down to fine coal shape.1 air this fine coal and coal transmitted via burner 102 and 2 air of firing optimization are supplied to boiler 101.Fine coal and 1 air are led to boiler 101 from pipe arrangement 134, and 2 times air is led to boiler 101 from pipe arrangement 141.In addition, the rear wind (after air) that 2 grades burn is put in boiler 101 via rear air port 103 by pipe arrangement 142.
The high-temperature gas produced by burning of coal along boiler 101 path and after flowing, by air heater 104.Thereafter, after pump-down process via smoke stack emission in air.
On the other hand, the feedwater of boiler 101 Inner eycle is directed to boiler 101 via feed pump 105, is heated in heat exchanger 106 by gas, becomes the steam of High Temperature High Pressure.In addition, in present embodiment, the number of heat exchanger is set to 1, but also can configures multiple heat exchanger.
The steam that have passed the High Temperature High Pressure after heat exchanger 106 is directed to steam turbine 108 via turbine variable valve 107.By the energy had of steam to drive steam turbine 108, generated electricity by generator 109.The electric power obtained that generates electricity is supplied to electric system.
The exhaust of steam turbine 108 is again sent to feed pump 105 after condenser 113 is cooled.In way, utilize the steam extracted from turbine, configure the device heated that feeds water, the thermal efficiency is improved.
Be configured with various measuring appliance in the general thermal power generation complete equipment formed as above, be transferred to the Monitor and Control device 200 etc. of Fig. 1 from the information acquired by this measuring appliance as metrical information 10 (process signal 10).Such as, flow measuring probe 150, temperature meter 151, pressometer 152, generating output checker 153 and measurement of concetration device 154 is illustrated in fig. 2.
In addition, the flow of flow measuring probe 150 to the feedwater being supplied to boiler 101 from feed pump 105 is measured.In addition, temperature meter 151, pressometer 152 respectively to being supplied to the temperature of steam of steam turbine 108, pressure measures.Generator 109 the electric energy that obtains of generating electricity measured by generating output checker 153.With composition (CO, the NO contained by the gas passing through boiler 101
xdeng) concentration dependent information then can carry out measurement by measurement of concetration device 154 and obtain.In addition, generally speaking, beyond Fig. 2 is illustrated, is also configured with numerous measuring appliance at thermal power generation complete equipment, omits in fig. 2.
Further, in fig. 2 from 1 air input by burner 102 and 2 air, be described from the path of the rear wind input by rear air port 103.
1 time air is directed to pipe arrangement 130 from fan 120, branches into by the pipe arrangement 132 of air heater 104 and not by the pipe arrangement 131 of air heater 104, and again after pipe arrangement 133 collaborates, be directed to muller 110 in way.By the air of air heater 104 by gas-heated.Utilize this 1 air, send via pipe arrangement 134 fine coal generated in muller 110 to burner 102.
2 air and rear wind are directed to pipe arrangement 140 from fan 121, after being heated by the air device 104 heating, branch into the pipe arrangement 141 of 2 air and the pipe arrangement 142 of rear wind, are directed to burner 102 respectively with rear air port 103.
The pipe arrangement portion that Fig. 3 is 1 air, 2 air and rear wind pass through and the enlarged drawing of air heater 104.As shown in Figure 3, in pipe arrangement, be configured with air door (air damper) 160,161,162,163.By operation air door, the area that the air in pipe arrangement 133,141,142 passes through can be changed, therefore can adjust the air mass flow by pipe arrangement by the operation of air door.
Below, the information that the information of the process signal 10 stored in declarative procedure computing machine 300, model information database 500 and diagnostic result database are preserved and the calculation function in feature model preparing department 420, unified model preparing department 430, key element diagnostics division 460, comprehensive diagnos portion 470.
First, the information of the process signal 10 that process computer 300 is preserved is described.Fig. 4 is the figure of an example of the information of preserving for illustration of each process computer 300.The information obtained measured by power plant 100 as shown in Figure 4, is measured the moment by each measuring appliance preserve in the lump with each.Such as, measuring the moment by storing in the longitudinal axis project of Fig. 4, in transverse axis project, storing classification, the unit of measured value by the PID numbering association of giving inherently measuring appliance accordingly.
Such as, number about PID, PID150 means the data obtained measured by the flow measuring probe 150 of the feedwater flow of Fig. 2, PID151 means the data obtained measured by the temperature meter 151 of main steam, PID152 means the data obtained measured by the pressometer 152 of main steam, PID153 means the data obtained measured by generating output checker 153, and PID154 means the data obtained measured by the measurement of concetration device 154 of burning gases.In addition, as classification, F means flow, and T means temperature, and P means pressure, and E means that generating exports, and D means NO contained in Exhaust Gas
xconcentration.These unit be respectively kg/s, DEG C, Mps, MW, ppm.In this wise, the measured value so PID numbering and classification, unit showed and the information of time are preserved in the lump.
In addition, in the diagram, obtain data with the cycle of 1 second and preserve, about the sample period of Data Collection, can at random set.For ease of effectively utilizing the data stored in process computer 300, can to be numbered basis to the PID of the intrinsic setting of each measured value, specialization is carried out to process signal, or can utilize as the key word (key) when exploring the process signal expected.
Secondly, the information that model information database 450 is preserved is described.Fig. 5, Fig. 6 are the figure of the pattern representing information required in based on the diagnostic model of ART.As shown in Figure 5, Figure 6, prepare have feature model table TB420 and unified model to show TB430 in model information database 450.Feature model table TB420 is the table storing the information relevant to the feature model handled by feature model preparing department 420, and unified model table TB430 is the table storing the information relevant to the unified model handled by unified model preparing department 430.
The maximum numbering of the classification generated when being equipped with pattern number, model name, the PID numbering of the input variable inputed in model, alarm parameters, modelling in the feature model table TB420 of Fig. 5.In this record example, pattern number is set to E-001, model name is set to the main steam model relevant to the main steam of the power plant of Fig. 2, input variable is set to PID150 (flow measuring probe 150 of feedwater flow), PID151 (temperature meter 151 of main steam), alarm parameters is set to 0.82, and the maximum numbering of the classification generated during modelling is set to 21.In the example of this such feature model, main steam model is showed by feedwater flow and main steam temperature.
The maximum numbering of the classification generated when being equipped with pattern number, model name, the pattern number of the feature model inputed in model, alarm parameters, modelling in the unified model table TB430 of Fig. 5.In this record example, pattern number is set to T-001, model name is set to the main steam circulation model relevant to the main steam of the power plant of Fig. 2, input model is set to the main steam model E-001 that uses in feature model table TB420 and adds PID152 (pressometer 152 of main steam), alarm parameters is set to 0.89, and the maximum numbering of the classification generated during modelling is set to 25.In the example of this such unified model, as main steam circulation model, show as main steam pressure adds to the main steam model E-001 that uses in feature model table TB420 and obtain model.
As known from the above, as unified model, refer in this example, new process variable has been added to feature model and the composite model formed.Though not shown in diagram example, as unified model, also can be by feature model compound and the model that obtains each other.In addition, in this example, as feature model, being the model that simulation main steam monomer obtains, as unified model, is the model simulating main steam circulation.So, unified model can be referred to as performance wider scope, the model of more upper scope, by fully utilizing feature model or process variable, becomes the model that can realize wide Scoped, upperization.
In addition, feature model or unified model can realize by utilizing self-elevating platform ART (ART) network of the supervised learning type of multiple classification that become by multiple input Data classification disclosed in non-patent literature 1 etc., in this case, as long as using feature model as lower network, then can orientate unified model as upper network.
In addition, the number (number of times) of the process variable used in feature model is being set to N time (being 2 times in the example at Fig. 5), unified model is the model of (N+M) secondary (being 3 times in the example of Fig. 5), is can be considered user element model to make the more model of high order based on this unified model made.
Based on this, solution problem of the present invention: the change of the adding of the new equipment in set of equipments, the diagnostic device inner model chased after when establishing of measuring appliance is understood to feature model to be remained unchanged, by increase the process variable that adds and make unified model to realize.
In addition, the number of alarm parameters is different along be suitable for adjustment gimmick.In this case, each table when utilizing alarm parameters to be set with multiple.Fig. 6 is the example of alarm parameters when being set to single, and Fig. 7 shows the example of each table when being set to multiple by alarm parameters.The difference of Fig. 7 and Fig. 6 is, the pattern that alarm parameters carries according to sorting out numbering.
Fig. 7 is the figure of an example of the information representing the diagnostic result stored in diagnostic result database 480.In diagnostic result database 480, prepare have feature model table TB460 and unified model to show TB470.Feature model table TB460 is the table storing the diagnostic result information relevant to the feature model processed in key element diagnostics division 460, and unified model table TB470 is the table storing the diagnostic result information relevant to the unified model processed in comprehensive diagnos portion 470.
Pattern number, moment, classification numbering, diagnostic result is equipped with in the feature model table TB460 of Fig. 7.In this record example, store pattern number is E-001, and the moment is " 2010/01/0100:00:00 ", and the diagnostic result sorting out numbering 1 is normal.In addition, the unified model table TB470 of Fig. 7 is also formed with same project, and in this record example, store pattern number is T-001, and the moment is " 2010/01/0400:10:11 ", and the diagnostic result sorting out numbering 3 is "abnormal".
When forming the key element diagnostics division 460 in the present invention, comprehensive diagnos portion 470, applicable patent document 1 and the method described in patent documentation 2.Patent documentation 1 and the method described in patent documentation 2 are all the diagnostic methods of the set of equipments that make use of self-elevating platform ART (Adaptive Resonance Theory, ART).ART is the one inputted Data classification being become the sorter in multiple classification.
At this, ART will do not inputed to containing the process signal of abnormal set of equipments, and be categorized as multiple classification.In diagnosis when abnormal generation, by process signal is inputed in ART, and generate when not belonging to the existing new classification sorted out, owing to creating the set of equipments state do not had so far, thus give a warning.
In addition, diagnostic result, except normal, abnormal, generates the situation of the new classification not belonging to any state in the past in addition.In this case, as the unknown, point out this information via aid 910 to user.As long as this state is that normal or abnormal judgement is determined thereafter, the diagnostic result just in displacement diagnostic result database 480.After, when creating same classification, export diagnostic result based on this result.
Above, as apparatus of the present invention the set of equipments that is suitable for and describe the formation of power plant.In addition, about the concrete example of feature model table, unified model table, be illustrated with the example of the process variable in this situation.On the basis that understanding of this content, next the contents processing of feature model preparing department 420 is described.
Fig. 8 is the process flow diagram of the action represented in feature model preparing department 420.First in step S421, judgement is the model of new production or is applied with correction to existing model.When for new production, entering step S422, entering step S425 when not being new production.
In addition, model new production or revise the instruction content given according to input media 900 by the user relevant to power plant 100 such as operator and distinguish.Thus, when not giving the instruction relevant to the change of model from user, the process of Fig. 8 is not performed.User gives the instruction that model changes according to the change of power plant 100.Figure 12 is utilized to describe the concrete gimmick that model changes instruction later.
When the instruction that model changes is new production, in step S422, the process signal in the past utilizing Fig. 4 to store, makes new ART model.Thereafter, in step S423, the information of the ART model of making is stored in model information database 450.Make this result, the new ART model stored at model information database 450 becomes the main steam model E-001 of such as Fig. 5, becomes the feature model determined with feedwater flow and main steam temperature.
In step S424, judge whether the monitored item object model construction of all correspondences completes.As all completed, then terminate, then return step S421 as unfinished, repeatedly carry out step thereafter, until built all supervision project models.
When the instruction that model changes is the correction of existing model, in step S425, judgement is the input variable adding or delete existing model.As then entered step S426 for adding, as then entered step S427 for deleting.
In step S426 when having added input variable, the variable added existing model is only utilized to make diagnostic model based on ART.At this, suppose that existing model is the main steam model E-001 of Fig. 5, the variable that adds be PID152 (pressometer 152 of main steam).Thus, in step S426, only utilize the variable PID152 that adds make diagnostic model based on ART.After completing, in step S423 (information of the ART model of making being stored in model information database 450), enter step S424 (being confirmed whether corresponding with all supervision projects).
In addition, in step S423, existing pattern number E-001 and the unified model that the pattern number (being set to PID152) added is stored into the model information database 450 of Fig. 5 are shown in the input model hurdle of TB430.
In step S427 when deleting the input variable of existing model, the input variable not occurring to change will remain unchanged, and input fixed value for the variable after deletion, in this input 0.5.Wherein, in the present embodiment, suppose that the input variable of ART model has all been carried out normalization.That is, as maximal value being set to " 1 " and value minimum value being set to the scope of " 0 " is grasped.Thus, " inputting 0.5 " means the value of the not change as intermediate value, processes afterwards.
At this, suppose that existing model is the main steam model E-001 of Fig. 5, deleted variable is PID151 (temperature meter 151 of main steam).In this case, owing to inputting 0.5 to PID151, therefore later main steam model E-001 in fact implements process as the model only carrying out determining with the feedwater flow of input variable PID150.
In step S428, accept the fixed value signal PID151 of deletion being set to 0.5, existing classification is transformed to the classification of this model.In addition, in the main steam model E-001 of Fig. 5,21 classification are had, so these become the object of conversion.In order to this conversion, with reference to the feature model table TB460 of the diagnostic result database 480 of Fig. 7, utilize the moment of the classification numbering stored relative to the hurdle of main steam model E-001, input to the pid information of the variable in this model, take out the time series data of each input variable that process computer 300 is preserved.
When this example, utilize and number moment corresponding to " 1 " " 2010/01/0100:00:00 " with classification, input to the pid information (PID150, PID151) of the variable in main steam model E-001, with reference to Fig. 4, take out the time series data of each input variable (PID150, PID151) that process computer 300 is preserved.This time series data is input in ART model.This operation is implemented for whole classification (21).After whole classification is implemented, with hereto identical, enter step S423, step S424.
In addition, exist at same model and add with when deleting, in the process flow diagram that step S425 first performs additional side, be again back to step S421 in step S424, again perform the process flow diagram deleted in step S425.
Fig. 9 is the process flow diagram of the action represented in unified model preparing department 430.First, new production feature model is judged whether in step S431.As being new production, then enter step S436, otherwise (when having the change of feature model) enters step S432.In addition, when for new production, due to the process that should not process as unified model preparing department 430, so, be transferred to the project of step S431 to other via step S436 and judge or end process.
When the change having feature model, in step S432, judge the state of input variable.As then entered step S433 for adding, otherwise (when deleting input variable) enters step S436.In addition, due to when deleting input variable and deleting, the process that should not process as unified model preparing department 430, so, be transferred to the project of step S431 to other via step S436 and judge or end process.
In step S433, when feature model makes, again input the process signal of the additional mode input to existing model and new production.Such as in the additional case-handling (step S425) of Fig. 8, PID152 has been added to existing model (main steam model E-001), as the process signal associated with these, again input to discharge PID150 and main steam temperature PID151 and main steam pressure PID152 with reference to Fig. 4.In addition, in the process of the step S423 of Fig. 8, by existing pattern number E-001 with the pattern number (being set to PID152) that adds, the unified model being stored in the model information database 450 of Fig. 5 is shown in the input model hurdle of TB430.
In step S434, build the classification numbering that exports from each aforesaid model as the ART model of input variable.Be such as newly sort out the assembled classification that inputted classification is numbered, and it can be used as unified model.
Specifically, suppose about existing pattern number E-001, have 10 and sort out numbering (from A0 to A9), about the pattern number PID152 added, have 5 and sort out numbering (from B0 to B4).In this case, the combination as A0 (normally) and B0 (normally) is normally, be then C0 " normally " by new classification number definition.In addition when A0 (normally), B1 (exception), be C1 "abnormal" by new classification number definition.Until this operation is performed to final combination, the model with the classification numbering of new a group is kept in unified model table TB430 as unified model.
In addition, when creating newly the establishing of measuring appliance etc., the new model about whole process signals may make again entirely, even if such as with reference to the input data in 1 time in the past, and will become the situation of the data of the huge amount of process.
About this point, carry out modelling in the present invention with reference to the input data fraction of the year of the past 1, it is only added input variable that numbering is sorted out in new acquisition.Both the feature model established is paid close attention to classification numbering, so the input data volume in time in past 1 is summarized in multiple classification numbering.
Step S436 is entered when modelling completes.In step S436, judge whether correspondence for whole supervision projects.Being back to step S431 when not completing, carrying out repeatedly until whole projects completes.As completed, terminate.
Secondly, Figure 10 represents the process flow diagram of the algorithm in key element diagnostics division 460 and comprehensive diagnos portion 470.At this, first in step S461, from the feature model table TB420 of model information database 450, load the information of each feature model.Next, in step S462, from the unified model table TB430 of model information database 450, the information of each unified model is loaded.Thus, the data of Fig. 5, Fig. 6 are supplied to key element diagnostics division 460.
In step S463, judgement is the diagnosis only under feature model or the diagnosis under comprising unified model.When being only the diagnosis under feature model, entering step S464, entering step S466 when the diagnosis for needing under unified model.
In step S464, implement the diagnosis under each feature model.This is the diagnosis of Application elements model table TB420.In step S465, the diagnostic result of feature model is stored in the feature model table TB460 of diagnostic result database 480.
On the one hand, in step S466, first implement the diagnosis under each feature model.This is the diagnosis of each feature model implemented in unified model table TB430.Such as when for main steam circulation model T-001, each of feature model E-001 and additional model PID152 is diagnosed.The diagnostic result of feature model is stored in the feature model table TB460 of diagnostic result database 480.
In step S467, with reference to the feature model table TB460 of diagnostic result database 480, the classification exported from each feature model numbering is diagnosed as input.
In step S468, diagnostic result is stored in the unified model table TB480 of diagnostic result database 480.
Thereafter, in step S469, judge whether to implement diagnosis to whole supervision projects.Returning step S461 when not completing, carrying out repeatedly until whole supervision projects completes.Terminate in the completed.
In this process flow diagram, step S467 and step S468 becomes the action that comprehensive diagnos portion 470 carries out, and other step S is implemented by key element diagnostics division 460.
In outside output interface 490, each diagnostic result is sent to aid 910 as Output rusults.
Secondly, utilize aid 910 to make image display device 950 display control signal 20, process signal 30 to user, the method for information of diagnostic result 40 or model information database 450 and diagnostic result 480 is described.
Figure 11 ~ Figure 15 is the picture example shown by image display device 950.User utilizes keyboard 901, mouse 902 to the position becoming sky hurdle of these pictures 90, performs the operation of input parameter value etc.
First, Figure 11 is the initial picture shown by image display device 950.At picture 90, as initial picture, display diagnostic model makes button 951 and diagnostic result the Show Button 952, and user selects necessary button from these, utilizes mouse 902 to move to make cursor 953, by 902 pictures showing expectation of clicking the mouse.
Figure 12 is the setting screen of shown feature model and unified model when have selected diagnostic model making button 951 in initial picture.The picture that this picture is display information setting is shown in the hurdle, top of picture 90.In addition, form the hurdle that below display illustrates in each portion of picture 90, data are inputted to these hurdles or is selected the setting carrying out model by button.
In process signal display field 961, user will be input in input field 961 to the measuring-signal of diagnostic model input or operation signal, input its scope (upper limit/lower limit) in the lump.In illustrated example, as measuring-signal, button have selected main steam flow, higher limit is set to 300 (kg/s), and lower limit carries out numerical value input with being set to 0 (kg/s).In addition, unit (kg/s) concomitantly shows default value as measuring-signal have selected main steam flow with button.
In addition, when main steam flow is added to diagnostic model, the time-bands that will show used in modelling is input in moment input field 962.In illustrated example, using between 2010/01/01 1 day as beginning, finish time and setting.
On picture 90, by clicking the Show Button 963, as shown in Figure 13, tendency chart shows at image display device 950.In the example of Figure 13, the appearance of the variation in time of multiple various process variable can be shown.By clicking the return push-button 971 of Figure 13, be back to the picture of Figure 12.
The pattern number, model name, input variable etc. needed for feature model making is shown at the feature model making display field 964 of Figure 12.The newly-increased button 965 of right side display and the correction button 966 of display field 964 is made at feature model.
Wherein, when pressing newly-increased button 965, feature model makes display field 964 and shows blank and become input state, can make new model by the hand input of user.
The example that display field 964 shows the picture selected when revising button 966 is made at illustrated feature model.Illustrate pattern number E-001, model name is main steam model and input variable is the example of PID150, PID151.
In addition, it is shortcut that correction is carried out in new modelling based on existing model, and in this case, display becomes the model of object, after having pressed correction button 966, carries out revising.Thus, be set with search key input field 967 according to the mode can retrieving existing model, after have input search key, if pressing index button 968, then the information becoming the model of object shows in feature model display field 964.
Unified model making display field 974 substantially also makes display field 964 and forms identically with feature model.The pattern number, model name, input model etc. needed for unified model making is shown in unified model display field 974.When pressing newly-increased button 975, unified model display field 974 becomes input state, can make new model.When revising based on existing model, display becomes the model of object, revises after having pressed correction button 976.There is search key input field 977 according to the mode can retrieving existing model, after have input search key, if pressing index button 978, then the information becoming the model of object will be presented at unified model display field 974.
After above setting, make button 992 by pressing, make each model.In fig. 12, by clicking return push-button 969, the picture of Figure 11 can be back to.
Figure 14 is the setting screen 90 for making diagnostic result be shown in image display device 950.By clicking diagnostic result the Show Button 952 in the initial picture of Figure 11, the picture of display Figure 14.In the hurdle, top of the picture 90 of Figure 14, show the picture that this picture is diagnostic result display setting.In addition, form the hurdle that below display illustrates in each portion of picture 90, data inputted to these hurdles or is selected by button, carrying out the setting of model.
In process signal selectionbar 981, the measuring-signal that user will make the picture 90 of image display device 950 show or operation signal and its scope (upper limit/lower limit) input in input field 981 in the lump.In illustrated example, show picture when generator output being inputted in the lump with main steam flow and its scope (upper limit/lower limit).
In addition, the time that will show inputs to moment input field 982.After the process signal that will show is determined, undertaken making a mark by click selectionbar and determine to select.
In feature model selectionbar 983, ground identical with the display information setting picture of Figure 12 display model is numbered, model name, input variable etc.In order to retrieve the model that will show and have search key input field 984.After have input search key, pressing index button 985 is retrieved.Result for retrieval is presented at feature model selectionbar 983, is undertaken choosing determine to select by click selectionbar.In illustrated example, the example of display model E-001.
In addition, unified model selectionbar 986 is also formed substantially identically with feature model selectionbar 983.At unified model selectionbar 986 display model numbering, model name, input model etc.In order to retrieve the model that will show and have search key input field 987.After search key input, pressing index button 988 is retrieved.Result for retrieval is presented at feature model selectionbar 986, is undertaken choosing determine to select by click selectionbar.The example of display model T-001 in illustrated example.
Input more than having carried out or select after, by click the Show Button 989, as shown in Figure 15, tendency chart is presented at the picture 90 of image display device 950.In the example of Figure 15, the generator selected by process signal selectionbar 981 is exported and carries out comparative display with the variation of the time of main steam flow.In addition, about the feature model E-001 selected or unified model T-001 and the new input variable PID152 added, according to often sorting out numbering, time series display is carried out.As shown in Figure 15, when new classification produces, the general section on tendency picture is emphasized with other color, notifies user thus.By clicking the return push-button 991 of Figure 15, the setting screen of Figure 14 can be returned.The initial picture of Figure 11 is back to when pressing the return push-button 999 of Figure 14.
Display frame as diagnostic result is routine and show Figure 15, other show the system diagram of the set of equipments becoming diagnosis object, when new classification produces, also can consider this position is significantly changed, when deserving position by clicking, the tendency of display shown in Figure 15 shows such display gimmick.
In addition, showing and comprise model information database 450 and the embodiment of diagnostic result database 480 at set of equipments diagnostic device 400, also can being respectively: the embodiment being set to other hardware not being contained in set of equipments diagnostic device 400.
Below, illustrate for power plant 100, based on the result of process diagnosis method of the present invention and device, be applied in the effect of exception/omen diagnosis of set of equipments.
When the diagnostic method of set of equipments of the present invention being applied to the exception/omen diagnosis of power plant, when due in using one of equipment exchange or maintenance and diagnostic model is revised, the diagnostic data accumulated till can being effectively used to this, and can diagnose.Its result, can the building of diagnostic model easy to implement again, by effectively utilizing actual achievement so far, can detect exception or omen tendency better.
In addition, because the tendency of two results of operations staff also being carried out to feature model and unified model shows, will become easy further based on visual supervision.And carry out comprehensive multiple diagnostic model and be set to stratum's type with unified model, the object of power plant is set to wider scope thereby, it is possible to easily form and carries out the model diagnosed.
Claims (7)
1. a diagnostic method for set of equipments, wherein,
The correlationship of input variable is kept to carry out the model after modelling,
According to the correlationship of described input variable, be multiple classification by inputted Data classification, and detect the exception of set of equipments according to the sorted generation not belonging to the normal classification sorted out,
The feature of the diagnostic method of described set of equipments is,
Create the described model adding or delete such change of input variable about the amendment according to described set of equipments, build new model by the change of the classification numbering that make use of this model,
When having added input variable to existing model, only build diagnostic model with the input variable added, number to generate based on the classification numbering obtained from existing model and the classification obtained from added described diagnostic model the model that new classification numbers.
2. the diagnostic method of set of equipments according to claim 1, is characterized in that,
When deleting input variable from existing model, to be normalized and the value of the input variable of deleting in the input variable inputted is set to fixed value, and the time series data of each input variable in utilizing the classification of this model to number carrys out the change of execution model.
3. the diagnostic method of set of equipments according to claim 1, is characterized in that,
When deleting input variable from existing model, the value being normalized the input variable of deleting in the input variable of rear and input is set to fixed value, and utilize the time series data of each input variable in the classification of this model numbering to carry out the change of execution model, and carry out delete processing after described additional process terminates.
4. a diagnostic method for set of equipments, wherein,
The correlationship of the input variable obtained from monitored object is carried out modelling, the Data classification inputing to model is become multiple classification, and detect the exception of set of equipments or the sign of omen according to the sorted generation not belonging to the normal classification sorted out,
The feature of the diagnostic method of described set of equipments is,
The correlationship of the 1st input variable is carried out modelling and kept as feature model, and according to the correlationship of described 1st input variable, inputted Data classification is become multiple classification, and the correlationship of the 2nd added input variable is also carried out modelling, inputted Data classification is become multiple classification, forms the unified model of described 2nd input variable after based on described feature model and modelling.
5. the diagnostic method of set of equipments according to claim 4, is characterized in that,
Described unified model comprises the determined new classification of combination by the classification by described 2nd input variable after the classification of described feature model and institute's modelling.
6. a diagnostic device for set of equipments, according to the measuring-signal obtained the control signal from the Monitor and Control device controlled monitored object or the process computer from the process signal of the described monitored object of input, detects the exception of described monitored object,
The feature of the diagnostic device of described set of equipments is to possess:
Feature model portion, the correlationship of the signal of input is carried out modelling to make feature model by it, the Data classification be input in feature model is become multiple classification by the correlationship according to described input signal, and detects the exception of set of equipments according to the sorted generation not belonging to the normal classification sorted out; And
Unified model portion, it possesses the unified model of the feature model at least comprising more than 1, the Data classification being input to unified model is become multiple classification by the correlationship according to described input signal, and detects the exception of set of equipments according to the sorted generation not belonging to the normal classification sorted out
The described feature model added of described input signal is created about the amendment according to described set of equipments, only build diagnostic model with the input signal added, number to generate new classification based on the classification numbering obtained from existing feature model with the classification obtained from added described diagnostic model to number, and then the model that will generate new classification numbering and obtain is stored in described unified model portion as unified model.
7. the diagnostic device of set of equipments according to claim 6, is characterized in that,
When deleting input variable from existing model, to be normalized and the value of the input variable of deleting in the input variable inputted is set to fixed value, and the time series data of each input variable in utilizing the classification of this model to number carrys out the change of execution model.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2011-157924 | 2011-07-19 | ||
| JP2011157924A JP5469131B2 (en) | 2011-07-19 | 2011-07-19 | Plant diagnostic method and apparatus. |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102890495A CN102890495A (en) | 2013-01-23 |
| CN102890495B true CN102890495B (en) | 2015-03-18 |
Family
ID=47534023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210245867.4A Expired - Fee Related CN102890495B (en) | 2011-07-19 | 2012-07-16 | Complete plant diagnosis methods and complete plant diagnosis apparatus |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP5469131B2 (en) |
| CN (1) | CN102890495B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016183839A (en) * | 2015-03-26 | 2016-10-20 | 一般財団法人電力中央研究所 | Pulverized coal firing boiler and power generation facility |
| CN105527842B (en) * | 2016-01-25 | 2018-04-24 | 东南大学 | A kind of reheat steam temperature neural Networks Internal Model Control method of compositive economy index |
| JP6747218B2 (en) * | 2016-09-28 | 2020-08-26 | 横河電機株式会社 | Plant simulation device and plant simulation method |
| JP6919186B2 (en) | 2016-12-14 | 2021-08-18 | オムロン株式会社 | Control system, control program and control method |
| JP6468313B2 (en) * | 2017-06-08 | 2019-02-13 | オムロン株式会社 | Control device, control program, and control method |
| EP3557354B1 (en) | 2016-12-14 | 2023-03-01 | Omron Corporation | Control device, control program, and control method |
| JP6920828B2 (en) * | 2017-02-17 | 2021-08-18 | 三菱パワー株式会社 | Plant diagnostic equipment and diagnostic methods |
| CN107703912A (en) * | 2017-09-13 | 2018-02-16 | 陕西千山航空电子有限责任公司 | A kind of method for diagnosing faults based on Aerial Electronic Equipment |
| JP6951202B2 (en) * | 2017-11-13 | 2021-10-20 | 株式会社日立製作所 | Data classification device |
| WO2019159883A1 (en) * | 2018-02-13 | 2019-08-22 | 三菱日立パワーシステムズ株式会社 | Model creation method, plant operation support method, model creating device, model, program, and recording medium having program recorded thereon |
| JP7161872B2 (en) * | 2018-06-28 | 2022-10-27 | 株式会社日立製作所 | Plant diagnostic system |
| WO2020031722A1 (en) * | 2018-08-10 | 2020-02-13 | 住友重機械工業株式会社 | Abnormality monitoring device, abnormality monitoring method, and abnormality monitoring program |
| US20230046190A1 (en) * | 2020-03-30 | 2023-02-16 | Mitsubishi Electric Corporation | Diagnosis system, diagnosis method, and recording medium |
| JP2024067066A (en) * | 2022-11-04 | 2024-05-17 | 株式会社日立製作所 | Industrial plant related system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101361029A (en) * | 2005-11-17 | 2009-02-04 | 霍尼韦尔国际公司 | Apparatus and method for identifying informative data in a process control environment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10207507A (en) * | 1997-01-23 | 1998-08-07 | Hitachi Ltd | Plant simulator |
| JP4676149B2 (en) * | 2004-03-10 | 2011-04-27 | 株式会社日立製作所 | Data classification device |
| JP5076785B2 (en) * | 2007-09-28 | 2012-11-21 | 富士電機株式会社 | Plant operation planning device and program thereof |
| JP5097739B2 (en) * | 2009-03-31 | 2012-12-12 | 株式会社日立製作所 | Plant abnormality diagnosis apparatus and abnormality diagnosis method |
| JP5150590B2 (en) * | 2009-09-25 | 2013-02-20 | 株式会社日立製作所 | Abnormality diagnosis apparatus and abnormality diagnosis method |
-
2011
- 2011-07-19 JP JP2011157924A patent/JP5469131B2/en active Active
-
2012
- 2012-07-16 CN CN201210245867.4A patent/CN102890495B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101361029A (en) * | 2005-11-17 | 2009-02-04 | 霍尼韦尔国际公司 | Apparatus and method for identifying informative data in a process control environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102890495A (en) | 2013-01-23 |
| JP5469131B2 (en) | 2014-04-09 |
| JP2013025461A (en) | 2013-02-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102890495B (en) | Complete plant diagnosis methods and complete plant diagnosis apparatus | |
| CN109272243B (en) | Carbon asset management method and system | |
| CN102460529B (en) | Device abnormality monitoring method and system | |
| CN107741008A (en) | A kind of monitoring boiler method and system based on Internet of Things | |
| CN102809928B (en) | Control optimizing method for energy consumption of thermal equipment of industrial enterprise | |
| CN106302739A (en) | A kind of Industrial Boiler monitoring and analysis aid decision cloud platform system | |
| CN206195827U (en) | Industrial boiler monitoring and analysis aid decision cloud platform system | |
| CN107291830A (en) | A kind of creation method of equipment knowledge base | |
| CN109886471A (en) | Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm | |
| Jagtap et al. | Markov-based performance evaluation and availability optimization of the boiler–furnace system in coal-fired thermal power plant using PSO | |
| CN104090560B (en) | Device monitoring power supply integrated environment evaluation indexes | |
| CN104200397B (en) | A kind of nuclear power station DCS system input design file and variable information data base consistency(-tance) method of calibration | |
| Wang | Thermo-economic evaluation, optimization and synthesis of large-scale coal-fired power plants | |
| CN117390529A (en) | Multi-factor traceable data center information management method | |
| Ma et al. | Economic operation evaluation of active distribution network based on fuzzy Borda method | |
| CN112016821A (en) | CS (circuit switched) architecture-based intelligent power plant standardized management system and method | |
| KR20160091942A (en) | Method, system, and computer program product for analyzing production and/or process-engineering processes and/or process steps in a plant | |
| CN113722656B (en) | Real-time health evaluation method and system for thermal generator set | |
| Dev et al. | System modeling and analysis of a combined cycle power plant | |
| CN102592004B (en) | System and method for on-line analysis and diagnosis of whole-process energy-consuming conditions of integrated iron and steel works | |
| Chen et al. | Application of deep learning modelling of the optimal operation conditions of auxiliary equipment of combined cycle gas turbine power station | |
| CN102830662B (en) | Monitoring system and method of flow industrial pipe network system | |
| CN102497135A (en) | Rule-engine-based method for monitoring photovoltaic power station | |
| CN117114335A (en) | Intelligent management system and method for building energy consumption | |
| CN106408214A (en) | Equivalent conversion evaluation method for full-life-cycle environmental cost of project |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150318 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |