CN107783071A - Sensor fault monitoring method and device - Google Patents
Sensor fault monitoring method and device Download PDFInfo
- Publication number
- CN107783071A CN107783071A CN201710992641.3A CN201710992641A CN107783071A CN 107783071 A CN107783071 A CN 107783071A CN 201710992641 A CN201710992641 A CN 201710992641A CN 107783071 A CN107783071 A CN 107783071A
- Authority
- CN
- China
- Prior art keywords
- capacitance voltage
- forecast model
- sensor
- value
- statcom
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of Resistance Or Impedance (AREA)
Abstract
The embodiment of the present invention provides a kind of sensor fault monitoring method and device, by the output current and capacitance voltage detected value that obtain STATCOM device, output current is inputted into forecast model, the capacitance voltage predicted value of capacitance voltage sensor is calculated, and judge whether capacitance voltage sensor breaks down according to residual error between capacitance voltage detected value and capacitance voltage predicted value, if, then by for controlling the feed back input value of each control strategy of STATCOM device to switch to capacitance voltage predicted value, to control STATCOM device to run.Above-mentioned technical proposal is by establishing Transducer fault detection and decision mechanism, after sensor fault, the output of capacitance voltage predicted value is taken instead of feed back input of the detected value of capacitance voltage sensor as closed-loop system, realize soft closed loop faults-tolerant control, faults-tolerant control can be realized in the capacitance voltage sensor failure of STATCOM device, with good accuracy and real-time, the security incident caused by sensor fault is effectively prevented.
Description
Technical field
The present invention relates to field of computer technology, in particular to a kind of sensor fault monitoring method and device.
Background technology
In recent years, based on H bridge structures STATCOM (Static Synchronous Compensator,
STATCOM) because of its modularization, be easily installed, extend the advantages that facilitating, obtained extensively in fields such as reactive-load compensation, harmonic wave controls
General application.As large capacity STATCOM device in the continuous input of power network, its reliability has become the weight of electric power netting safe running
Want condition.It is an extremely complex non-linear more closed-loop systems yet with STATCOM systems, there are multiple detections in system
Link (for example, sensor), the feed back input for closed-loop system.The influence of STATCOM system contexts is limited by, these
In the case that sensor is chronically at high temperature, strong electromagnetic, easily break down.And once break down, if locating not in time
Reason, the feedback signal that fault sensor transmits can spread rapidly in closed-loop control system, gently then cause system harmonicses increase, set
Standby damage, it is heavy then trigger security incident, bring casualties.
The content of the invention
In order to overcome above-mentioned deficiency of the prior art, it is an object of the invention to provide a kind of sensor fault monitoring side
Method and device, faults-tolerant control can be realized in the capacitance voltage sensor failure of STATCOM device, there is good standard
True property and real-time, effectively prevent the security incident caused by sensor fault.
To achieve these goals, the technical scheme that present pre-ferred embodiments use is as follows：
Present pre-ferred embodiments provide a kind of sensor fault monitoring method, applied to computer equipment, the calculating
Machine equipment is stored with the forecast model of the target capabilities parameter of capacitance voltage sensor, includes in the forecast model
Function prediction relation between the output current and capacitance voltage of STATCOM device, methods described include：
Obtain the output current and capacitance voltage detected value of STATCOM device；
The output current is inputted into the forecast model, the capacitance voltage that capacitance voltage sensor is calculated is pre-
Measured value；
The capacitance voltage is judged according to residual error between the capacitance voltage detected value and the capacitance voltage predicted value
Whether sensor breaks down；
If breaking down, the feed back input value of each control strategy for controlling the STATCOM device is switched
For the capacitance voltage predicted value, to control the STATCOM device to run, wherein, the control strategy includes PWM control plans
Omit, capacitor voltage balance control strategy in capacitive coupling voltage balancing control strategy and phase.
In present pre-ferred embodiments, in each control strategy by for controlling the STATCOM device
Feed back input value switches to the capacitance voltage predicted value, after controlling the STATCOM device to run, methods described bag
Include：
Whether the failure for detecting the capacitance voltage sensor excludes, if so, then by the feed back input of each control strategy
Value switches to the capacitance voltage detected value of capacitance voltage sensor.
In present pre-ferred embodiments, after the output current of STATCOM device and capacitance voltage detected value is obtained,
Methods described also includes：
Establish the forecast model；
It is described to establish the forecast model, including：
The historical data of the STATCOM device is obtained, the historical data includes the output current number of STATCOM device
According to capacitance voltage data；
The multinuclear least square branch established according to the historical data between STATCOM device output current and capacitance voltage
Vector machine forecast model is held, to obtain the forecast model.
It is described that STATCOM device output current and electricity are established according to the historical data in present pre-ferred embodiments
Hold the multinuclear least square method supporting vector machine forecast model between voltage, including：
Training for training the multinuclear least square method supporting vector machine forecast model is obtained according to the historical data
Sample set, the mode input variable of the training sample set is output current, and the model output variable of the training sample set is
Capacitance voltage；
According to the training sample set Training Support Vector Machines；
According to default kernel function, by the SVMs from low-dimensional mode input space reflection to high-dimensional feature space
In, establish linear function；
The training error of the linear function, the linear letter after being adjusted are adjusted according to structural risk minimization
Number；
The linear function is handled using method of Lagrange multipliers, obtained for predicting capacitance voltage predicted value
Function prediction expression formula, to obtain the forecast model.
It is described according to the capacitance voltage detected value and the capacitance voltage predicted value in present pre-ferred embodiments
Between residual error judge whether the capacitance voltage sensor breaks down, including：
Judge whether the residual error is less than or equal to predetermined threshold value；
If it is not, then judge the capacitance voltage sensor failure.
Present pre-ferred embodiments also provide a kind of sensor fault supervising device, applied to computer equipment, the meter
The forecast model that machine equipment is stored with the target capabilities parameter of capacitance voltage sensor is calculated, is included in the forecast model
Function prediction relation between the output current and capacitance voltage of STATCOM device, described device include：
Acquisition module, for obtaining the output current and capacitance voltage detected value of STATCOM device；
Input module, for the output current to be inputted into the forecast model, capacitance voltage sensing is calculated
The capacitance voltage predicted value of device；
Judge module, for being judged according to residual error between the capacitance voltage detected value and the capacitance voltage predicted value
Whether the capacitance voltage sensor breaks down；
Handover module, for when breaking down, by the anti-of each control strategy for controlling the STATCOM device
Feedback input value switches to the capacitance voltage predicted value, to control the STATCOM device to run, wherein, the control strategy
Including capacitor voltage balance control strategy in PWM control strategies, capacitive coupling voltage balancing control strategy and phase.
In terms of existing technologies, the invention has the advantages that：
The embodiment of the present invention provides a kind of sensor fault monitoring method and device, by obtaining the defeated of STATCOM device
Go out electric current and capacitance voltage detected value, then input output current into forecast model, capacitance voltage sensor is calculated
Capacitance voltage predicted value, and institute is judged according to residual error between the capacitance voltage detected value and the capacitance voltage predicted value
State whether capacitance voltage sensor breaks down, if breaking down, by each control for controlling the STATCOM device
The feed back input value of strategy switches to the capacitance voltage predicted value, to control the STATCOM device to run.Set based on above-mentioned
Meter, by establishing Transducer fault detection and decision mechanism, after sensor fault, the capacitance voltage predicted value is taken to export
Instead of feed back input of the detected value of capacitance voltage sensor as closed-loop system, soft closed loop faults-tolerant control, Ke Yi are realized
Faults-tolerant control is realized during the capacitance voltage sensor failure of STATCOM device, there is good accuracy and real-time, have
Effect prevents the security incident caused by sensor fault.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by embodiment it is required use it is attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 is the block diagram for the computer equipment that present pre-ferred embodiments provide；
Fig. 2 is a kind of schematic flow sheet for the sensor fault monitoring method that present pre-ferred embodiments provide；
Fig. 3 is another schematic flow sheet for the sensor fault monitoring method that present pre-ferred embodiments provide；
Fig. 4 is a kind of functional block diagram for the sensor fault supervising device that present pre-ferred embodiments provide；
Fig. 5 is another functional block diagram for the sensor fault supervising device that present pre-ferred embodiments provide；
Fig. 6 is another functional block diagram for the sensor fault supervising device that present pre-ferred embodiments provide.
Icon：100- computer equipments；110- memories；120- processors；130- communication units；140- storage controls
Device；150- display units；200- sensor fault supervising devices；209- forecast models establish module；210- acquisition modules；220-
Input module；230- judge modules；240- handover modules；250- detection modules.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.Generally herein
The component of the embodiment of the present invention described and illustrated in place's accompanying drawing can be configured to arrange and design with a variety of.Therefore,
The detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit the model of claimed invention below
Enclose, but be merely representative of the selected embodiment of the present invention.Based on the embodiment in the present invention, those of ordinary skill in the art are not having
There is the every other embodiment made and obtained under the premise of creative work, belong to the scope of protection of the invention.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent accompanying drawing in individual accompanying drawing.Meanwhile the present invention's
In description, term " first ", " second " etc. are only used for distinguishing description, and it is not intended that instruction or hint relative importance.
Referring to Fig. 1, Fig. 1 is the block diagram for the computer equipment 100 that present pre-ferred embodiments provide.In this hair
In bright embodiment, the computer equipment 100 may be, but not limited to, PC (Personal Computer, PC), pen
Remember this computer, tablet personal computer, personal digital assistant (Personal Digital Assistant, PDA), mobile internet surfing equipment
(Mobile Internet Device, MID) etc..The operating system of the computer equipment 100 may be, but not limited to,
Windows systems, linux system, OSX systems etc..Preferably, in the present embodiment, the operation system of the computer equipment 100
System can be Windows systems.
As shown in figure 1, the computer equipment 100 can include memory 110, processor 120, communication unit 130, deposit
Store up controller 140 and display unit 150.The memory 110, processor 120, communication unit 130, storage control 140
And display unit 150 is directly or indirectly electrically connected between each other, to realize the transmission of data or interaction.For example, these
Element can be realized by one or more communication bus or signal wire be electrically connected between each other.Biography is stored with memory 110
Sensor failure monitoring device 200, the sensor fault supervising device 200 include it is at least one can be with software or firmware
(Firmware) form is stored in the software function module in the memory 110, and the processor 120 is stored by running
Software program and module in memory 110, such as the sensor fault supervising device 200 in the embodiment of the present invention, so as to
Various function application and data processing are performed, that is, realizes the sensor fault monitoring method in the embodiment of the present invention.
Wherein, the memory 110 may include high speed random access memory, may also include nonvolatile memory, such as one
Or multiple magnetic storage devices, flash memory or other non-volatile solid state memories.In some instances, memory 110 can
Further comprise that relative to the remotely located remote memory of processor 120, these remote memories network connection can be passed through
To the computer equipment 100.The example of above-mentioned network can include but is not limited to internet, intranet, LAN, shifting
Dynamic communication network and combinations thereof.Wherein, memory 110 is used for storage program, the processor 120 after execute instruction is received,
Perform described program.Further, various input/output devices are coupled to processor 120 and memory by communication unit 130
110, software program and module in above-mentioned memory 110 may also include operating system, and it may include various to be used to manage system
The component software of system task (such as memory management, storage device control, power management etc.) and/or driving, and can with it is various hard
Part or component software mutually communicate, so as to provide the running environment of other software component.
The processor 120 can be a kind of IC chip, have the disposal ability of signal.Above-mentioned processor
120 can be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit
(Network Processor, NP) etc..It can also be digital signal processor (DSP), application specific integrated circuit (ASIC), scene
Programmable gate array (FPGA) either other PLDs, discrete gate or transistor logic, discrete hardware group
Part.It can realize or perform disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor can be with
It is microprocessor or the processor 120 can also be any conventional processor etc..
The display unit 150 can between the computer equipment 100 and user simultaneously provide one output and it is defeated
Enter interface.Specifically, the display unit 150 shows that video or image export to user, and the content of these video frequency outputs can
Including word, figure, video and its any combination.Some output results correspond to some user interface objects.For example,
In the present embodiment, the display unit 150 is displayed for the simulation parameter configuration interface for configuring simulation parameter.This
Outside, the display unit 150 can also receive the input of user, such as the gesture operation such as the click of user, slip, so as to user
Input of the interface object to these users responds.Detection user input technology can be based on resistance-type, condenser type or
Other any possible touch control detection technologies of person.Alternatively, the instantiation of the display unit 150 can include but and unlimited
In liquid crystal display or light emitting polymer displays.
It is appreciated that the structure shown in Fig. 1 is only to illustrate, the computer equipment 100 can also include than shown in Fig. 1
More either less components have the configuration different from shown in Fig. 1.Each component shown in Fig. 1 can use hardware,
Software or its combination are realized.
Because traditional capacitance voltage sensor fault faults-tolerant control strategy is still the thinking that follows switching device failure,
Trouble point is isolated after failure and bypasses malfunctioning module, then carries out corresponding control strategy adjustment.Sent out through the application
A person of good sense studies for a long period of time discovery, and after switching device failure, power model can lose the ability of normal work, it is therefore necessary to carry out
Fault Isolation and bypass.And sensor fault simply monitors obtained signal and deviation occurs, power model where it is that possess
Normal work ability.After failure occurs, each power model voltage fluctuation of capacitor is larger, capacitive coupling voltage not releveling,
In addition to it can influence STATCOM system outlet sides, capacitive faults can also be caused for a long time by going down, or even charging too high causes electricity
Hold blast.Therefore, for power model capacitance voltage sensor fault detection and faults-tolerant control be extremely necessary.
In view of the above problems, present inventor proposes following examples to solve or improve above mentioned problem.It is right below
The embodiment of the present invention elaborates.In the case where not conflicting, the feature in following embodiment and embodiment can be mutual
Combination.
Referring to Fig. 2, Fig. 2 is the schematic flow sheet for the sensor fault monitoring method that present pre-ferred embodiments provide.
It should be noted that method provided in an embodiment of the present invention is not using Fig. 2 and particular order as described below as limitation.Methods described
Idiographic flow it is as follows：
Step S210, obtain the output current and capacitance voltage detected value of STATCOM device.
In the present embodiment, STATCOM (Static Synchronous Compensator, STATCOM) is in parallel
In power network, the reactive current source controllable equivalent to one, its reactive current can rapidly follow the change of reactive load electric current
Change and change, reactive power needed for automatic compensation network system, dynamic passive compensation is realized to power system reactive power.
Specifically, the output current of the STATCOM device is that capacitance voltage detected value can be each mutually each power model
Capacitance voltage detected value.
Step S220, the output current is inputted into forecast model, the electric capacity of capacitance voltage sensor is calculated
Voltage prediction value.
Specifically, in the present embodiment, the target capabilities of capacitance voltage sensor are stored with the computer equipment 100
The forecast model of parameter, the function between the output current of STATCOM device and capacitance voltage is included in the forecast model
Projected relationship, the target capabilities parameter are the output current and capacitance voltage of STATCOM device.
Input into the forecast model by the output current, according to the function prediction relation, then can calculate
Obtain the capacitance voltage predicted value of the capacitance voltage sensor.
In the present embodiment, the computer equipment 100 can pre-establish the forecast model.Alternatively, obtain first
The historical data of the STATCOM device, the historical data include the output current data and capacitance voltage of STATCOM device
Data, the multinuclear least square then established according to the historical data between STATCOM device output current and capacitance voltage
SVM prediction model, to obtain the forecast model.
More specifically, obtained first according to the historical data for training the multinuclear least square method supporting vector machine
The training sample set of forecast model, the mode input variable of the training sample set is output current, the training sample set
Model output variable is capacitance voltage.Then, according to the training sample set Training Support Vector Machines, further according to default core letter
Number, by the SVMs from low-dimensional mode input space reflection into high-dimensional feature space, establish linear function, then so
Afterwards, according to the training error of the structural risk minimization adjustment linear function, the linear function after being adjusted, finally
The linear function is handled using method of Lagrange multipliers, obtains the function prediction for predicting capacitance voltage predicted value
Expression formula, to obtain the forecast model.
In the present embodiment, the forecast model can use pre- based on multinuclear least square method supporting vector machine (MLS-SVM)
Survey model.Specifically, the A phases output voltage of the STATCOM device can be：
ua=U cos (ω t)
The A phase currents of the STATCOM device can be
ia=I cos (ω t+ θ)
The transient current calculation formula for so flowing through electric capacity is：
In above formula：D is the chain link output voltage dutycycle, and M is modulation ratio and modulation ratio M can be 0.87.
According to above-mentioned calculation formula, the historical data of the STATCOM device can be utilized, it is defeated to establish STATCOM device
The regressive prediction model gone out between electric current and capacitance voltage, after failure occurs, utilize this model and actual STATCOM device
Output current draws the predicted value of capacitance voltage.
In the present embodiment, the basic thought of the prediction of MLS-SVM models is on the basis of LS-SVM forecast models, is utilized
Multiple kernel functions are calculated, and so as to reduce sensitiveness of the forecast model to training sample, improve its robustness.
First, training sample set is givenWherein, ici∈ R are mode input data, i.e., to STATCOM device
Output current, ui∈ R are model output data, i.e. capacitance voltage value, and l is the quantity of training sample.The recurrence of given sample set
Nonlinear function estimation problem in original sample space can be converted into above-mentioned calculating formula by problem using a Nonlinear Mapping
High-dimensional feature space in linear function estimation problem.
Wherein,W is that weight coefficient is vectorial (complexity of representative model),By sample from former space RpIt is mapped to high-dimensional feature space Rh, b is offset constant.
Then, according to structural risk minimization, by the way that the first power of error is converted into quadratic power, LS-SVM original
Beginning optimization problem is：
In above formula, C ∈ R+It is penalty factor (flatness and training error that are used for Tuning function).
Then, this constrained optimization problem is converted into unconstrained optimization problem with Lagrangian method：
In above formula, αi(i=1,2 ..., l) is Lagrange multiplier, αi>Sample point corresponding to 0 is supporting vector.
Then, from KKT (Karush-Kuhn-Tucker) condition：
ξ is eliminated from above formulaiAnd w, and define the kernel function for meeting Mercer theoremsThen optimize
Problem, which is converted into, solves following system of linear equations：
Factor alpha in above formula is obtained with least square methodiWith deviation b, you can newly entered sample ic Function Estimation prediction
Expression formula：
Understood to realize the classification to a new samples data (namely system output current) by above formula, it is only necessary to calculate each
The kernel function of individual training sample and new samples, it is not necessary to look for specificThe kernel function can be but not limited to z ranks
Polynomial kernel function, gaussian radial basis function (RBF) or multilayer perceptron kernel function etc..
For Multiple Kernel Learning, orderFinally give the Nonlinear Classification model based on MLS-SVM：
Step S230, according to judging residual error between the capacitance voltage detected value and the capacitance voltage predicted value
Whether capacitance voltage sensor breaks down.
Specifically, it may determine that whether the residual error is less than or equal to predetermined threshold value first, if it is not, then judging the electricity
Hold voltage sensor to break down.If so, then judging that the capacitance voltage sensor does not break down, now plan is controlled according to original
The STATCOM device is slightly controlled to continue to run with.
Step S240, it is if breaking down, the feedback of each control strategy for controlling the STATCOM device is defeated
Enter value and switch to the capacitance voltage predicted value, to control the STATCOM device to run.
Specifically, in the present embodiment, the control strategy includes PWM control strategies, capacitive coupling voltage balancing control
Capacitor voltage balance control strategy in strategy and phase.If it is determined that the capacitance voltage sensor failure, then then will
Capacitance voltage in PWM control strategies, capacitive coupling voltage balancing control strategy and phase for controlling the STATCOM device
The feed back input value of balance control strategy switches to the capacitance voltage predicted value, is simultaneously emitted by warning message, reminds relevant people
Member excludes the failure, makes STATCOM device continue to keep the normal operation in certain time (for example, ten minutes).
Based on above-mentioned design, by establishing Transducer fault detection and decision mechanism, after sensor fault, take described
The output of capacitance voltage predicted value realizes soft closed loop instead of feed back input of the detected value of capacitance voltage sensor as closed-loop system
Faults-tolerant control, faults-tolerant control can be realized in the capacitance voltage sensor failure of STATCOM device, there is good standard
True property and real-time, effectively prevent the security incident caused by sensor fault.
Further, referring to Fig. 3, methods described can also include：
Whether step S250, the failure for detecting the capacitance voltage sensor exclude, if so, then by each control strategy
Feed back input value switches to the capacitance voltage detected value of capacitance voltage sensor.
In the present embodiment, if the failure of the capacitance voltage sensor has excluded, then then recover former control strategy operation.
It is understood that the specific implementation of former control strategy is referred to prior art or actual design demand, this implementation
This is not repeated in example.
Further, referring to Fig. 4, present pre-ferred embodiments also provide a kind of sensor fault supervising device 200, institute
The software function module that device is installed in the memory 110 and performed including one or more by the processor 120 is stated,
Described device includes：
Acquisition module 210, for obtaining the output current and capacitance voltage detected value of STATCOM device.
Input module 220, for the output current to be inputted into the forecast model, capacitance voltage biography is calculated
The capacitance voltage predicted value of sensor.
Judge module 230, for according to residual error between the capacitance voltage detected value and the capacitance voltage predicted value
Judge whether the capacitance voltage sensor breaks down.
Handover module 240, for when breaking down, by each control strategy for controlling the STATCOM device
Feed back input value switch to the capacitance voltage predicted value, to control the STATCOM device to run, wherein, the control
Strategy includes capacitor voltage balance control strategy in PWM control strategies, capacitive coupling voltage balancing control strategy and phase.
Further, referring to Fig. 5, described device can also include：
Whether detection module 250, the failure for detecting the capacitance voltage sensor exclude, if so, then by each control
The feed back input value of system strategy switches to the capacitance voltage detected value of capacitance voltage sensor.
Further, referring to Fig. 6, described device can also include：
Forecast model establishes module 209, for establishing the forecast model.
The forecast model establishes module 209, is additionally operable to obtain the historical data of the STATCOM device, the history
Data include the output current data and capacitance voltage data of STATCOM device；STATCOM dresses are established according to the historical data
The multinuclear least square method supporting vector machine forecast model between output current and capacitance voltage is put, to obtain the forecast model.
Alternatively, the forecast model establishes module 209, can be also used for：
Training for training the multinuclear least square method supporting vector machine forecast model is obtained according to the historical data
Sample set, the mode input variable of the training sample set is output current, and the model output variable of the training sample set is
Capacitance voltage；According to the training sample set Training Support Vector Machines；According to default kernel function, by the SVMs from
Low-dimensional mode input space reflection establishes linear function into high-dimensional feature space；Adjusted according to structural risk minimization
The training error of the linear function, the linear function after being adjusted；Using method of Lagrange multipliers to the linear function
Handled, obtain the function prediction expression formula for predicting capacitance voltage predicted value, to obtain the forecast model.
Further, the judge module 230, can be also used for；It is default to judge whether the residual error is less than or equal to
Threshold value；If it is not, then judge the capacitance voltage sensor failure.
The concrete operation method of each functional module in the present embodiment can refer to corresponding steps in above method embodiment
It is described in detail, it is no longer repeated herein.
In summary, the embodiment of the present invention provides a kind of sensor fault monitoring method and device, by obtaining STATCOM
The output current and capacitance voltage detected value of device, then input output current into forecast model, and electric capacity electricity is calculated
The capacitance voltage predicted value of pressure sensor, and according to residual between the capacitance voltage detected value and the capacitance voltage predicted value
Difference judges whether the capacitance voltage sensor breaks down, if breaking down, by for controlling the STATCOM device
The feed back input value of each control strategy switches to the capacitance voltage predicted value, to control the STATCOM device to run.Base
In above-mentioned design, by establishing Transducer fault detection and decision mechanism, after sensor fault, take the capacitance voltage pre-
Measured value output replaces feed back input of the detected value of capacitance voltage sensor as closed-loop system, realizes soft closed loop faults-tolerant control,
Faults-tolerant control can be realized in the capacitance voltage sensor failure of STATCOM device, there is good accuracy and reality
Shi Xing, effectively prevent the security incident caused by sensor fault.
In several embodiments that the embodiment of the present invention is provided, it should be understood that disclosed apparatus and method, also may be used
To realize by another way.Apparatus and method embodiment described above is only schematical, for example, in accompanying drawing
Flow chart and block diagram show that the system of multiple embodiments according to the present invention, the possibility of method and computer program product are realized
Architectural framework, function and operation.At this point, each square frame in flow chart or block diagram can represent module, a program
A part for section or code, a part for the module, program segment or code include one or more and are used to realize defined patrol
Collect the executable instruction of function.It should also be noted that at some as the function of in the implementation replaced, being marked in square frame
Can be with different from the order marked in accompanying drawing generation.For example, two continuous square frames can essentially be held substantially in parallel
OK, they can also be performed in the opposite order sometimes, and this is depending on involved function.It is also noted that block diagram and/or
The combination of each square frame and block diagram in flow chart and/or the square frame in flow chart, function or dynamic as defined in performing can be used
The special hardware based system made is realized, or can be realized with the combination of specialized hardware and computer instruction.
In addition, each functional module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are make it that a computing device (can be personal
Computer, electronic equipment, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
It should be noted that herein, term " including ", " including " or its any other variant are intended to non-row
His property includes, so that process, method, article or equipment including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or equipment institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence " including one ... ", it is not excluded that including institute
State in process, method, article or the equipment of key element and other identical element also be present.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Any reference in claim should not be considered as to the involved claim of limitation.
Claims (10)
1. a kind of sensor fault monitoring method, applied to computer equipment, it is characterised in that the computer equipment is stored with
The forecast model of the target capabilities parameter of capacitance voltage sensor, the output of STATCOM device is included in the forecast model
Function prediction relation between electric current and capacitance voltage, methods described include：
Obtain the output current and capacitance voltage detected value of STATCOM device；
The output current is inputted into the forecast model, the capacitance voltage prediction of capacitance voltage sensor is calculated
Value；
The capacitance voltage sensing is judged according to residual error between the capacitance voltage detected value and the capacitance voltage predicted value
Whether device breaks down；
If breaking down, by for controlling the feed back input value of each control strategy of the STATCOM device to switch to institute
State capacitance voltage predicted value, to control the STATCOM device to run, wherein, the control strategy include PWM control strategies,
Capacitor voltage balance control strategy in capacitive coupling voltage balancing control strategy and phase.
2. sensor fault monitoring method according to claim 1, it is characterised in that it is described will be used to controlling it is described
The feed back input value of each control strategy of STATCOM device switches to the capacitance voltage predicted value, with described in control
After STATCOM device operation, methods described includes：
Whether the failure for detecting the capacitance voltage sensor excludes, if so, then cutting the feed back input value of each control strategy
It is changed to the capacitance voltage detected value of capacitance voltage sensor.
3. sensor fault monitoring method according to claim 1, it is characterised in that obtaining the defeated of STATCOM device
Go out after electric current and capacitance voltage detected value, methods described also includes：
Establish the forecast model；
It is described to establish the forecast model, including：
Obtain the historical data of the STATCOM device, the historical data include STATCOM device output current data and
Capacitance voltage data；
The multinuclear least square established according to the historical data between STATCOM device output current and capacitance voltage support to
Amount machine forecast model, to obtain the forecast model.
4. sensor fault monitoring method according to claim 3, it is characterised in that described to be built according to the historical data
Vertical multinuclear least square method supporting vector machine forecast model between STATCOM device output current and capacitance voltage, including：
Training sample for training the multinuclear least square method supporting vector machine forecast model is obtained according to the historical data
Collection, the mode input variable of the training sample set is output current, and the model output variable of the training sample set is electric capacity
Voltage；
According to the training sample set Training Support Vector Machines；
According to default kernel function, by the SVMs from low-dimensional mode input space reflection into high-dimensional feature space,
Establish linear function；
The training error of the linear function, the linear function after being adjusted are adjusted according to structural risk minimization；
The linear function is handled using method of Lagrange multipliers, obtains the function for predicting capacitance voltage predicted value
Prediction expression, to obtain the forecast model.
5. sensor fault monitoring method according to claim 1, it is characterised in that described to be examined according to the capacitance voltage
Residual error judges whether the capacitance voltage sensor breaks down between measured value and the capacitance voltage predicted value, including：
Judge whether the residual error is less than or equal to predetermined threshold value；
If it is not, then judge the capacitance voltage sensor failure.
6. a kind of sensor fault supervising device, applied to computer equipment, it is characterised in that the computer equipment is stored with
The forecast model of the target capabilities parameter of capacitance voltage sensor, the output of STATCOM device is included in the forecast model
Function prediction relation between electric current and capacitance voltage, described device include：
Acquisition module, for obtaining the output current and capacitance voltage detected value of STATCOM device；
Input module, for the output current to be inputted into the forecast model, capacitance voltage sensor is calculated
Capacitance voltage predicted value；
Judge module, described in being judged according to residual error between the capacitance voltage detected value and the capacitance voltage predicted value
Whether capacitance voltage sensor breaks down；
Handover module, it is for when breaking down, the feedback of each control strategy for controlling the STATCOM device is defeated
Enter value and switch to the capacitance voltage predicted value, to control the STATCOM device to run, wherein, the control strategy includes
Capacitor voltage balance control strategy in PWM control strategies, capacitive coupling voltage balancing control strategy and phase.
7. sensor fault supervising device according to claim 6, it is characterised in that described device includes：
Whether detection module, the failure for detecting the capacitance voltage sensor exclude, if so, then by each control strategy
Feed back input value switches to the capacitance voltage detected value of capacitance voltage sensor.
8. sensor fault supervising device according to claim 6, it is characterised in that described device also includes：
Forecast model establishes module, for establishing the forecast model；
The forecast model establishes module, is additionally operable to obtain the historical data of the STATCOM device, and the historical data includes
The output current data and capacitance voltage data of STATCOM device；
The multinuclear least square established according to the historical data between STATCOM device output current and capacitance voltage support to
Amount machine forecast model, to obtain the forecast model.
9. sensor fault supervising device according to claim 8, it is characterised in that the forecast model establishes module,
It is additionally operable to：
Training sample for training the multinuclear least square method supporting vector machine forecast model is obtained according to the historical data
Collection, the mode input variable of the training sample set is output current, and the model output variable of the training sample set is electric capacity
Voltage；
According to the training sample set Training Support Vector Machines；
According to default kernel function, by the SVMs from low-dimensional mode input space reflection into high-dimensional feature space,
Establish linear function；
The training error of the linear function, the linear function after being adjusted are adjusted according to structural risk minimization；
The linear function is handled using method of Lagrange multipliers, obtains the function for predicting capacitance voltage predicted value
Prediction expression, to obtain the forecast model.
10. sensor fault supervising device according to claim 6, it is characterised in that the judge module, be additionally operable to；
Judge whether the residual error is less than or equal to predetermined threshold value；
If it is not, then judge the capacitance voltage sensor failure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710992641.3A CN107783071A (en) | 2017-10-23 | 2017-10-23 | Sensor fault monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710992641.3A CN107783071A (en) | 2017-10-23 | 2017-10-23 | Sensor fault monitoring method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107783071A true CN107783071A (en) | 2018-03-09 |
Family
ID=61435061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710992641.3A Pending CN107783071A (en) | 2017-10-23 | 2017-10-23 | Sensor fault monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107783071A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490266A (en) * | 2019-08-23 | 2019-11-22 | 北京邮电大学 | A kind of sensing data uploads, Transducer-fault Detecting Method and device |
| CN111090071A (en) * | 2018-10-24 | 2020-05-01 | 株洲中车时代电气股份有限公司 | Method, system, device and storage medium for diagnosing sensor fault in converter |
| CN111564024A (en) * | 2020-05-25 | 2020-08-21 | 安徽复盛信息科技有限公司 | Automatic protection method and system based on dangerous gas monitoring alarm |
| CN115420325A (en) * | 2022-11-04 | 2022-12-02 | 深圳海润新能源科技有限公司 | Method for checking abnormal sensor of energy storage device, terminal equipment and storage medium |
| CN116579762A (en) * | 2023-04-14 | 2023-08-11 | 广州林旺空调工程有限公司 | Intelligent operation and maintenance platform for cooling tower |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324034A (en) * | 2011-05-25 | 2012-01-18 | 北京理工大学 | Sensor-fault diagnosing method based on online prediction of least-squares support-vector machine |
| CN102663412A (en) * | 2012-02-27 | 2012-09-12 | 浙江大学 | Power equipment current-carrying fault trend prediction method based on least squares support vector machine |
| CN103488869A (en) * | 2013-08-23 | 2014-01-01 | 上海交通大学 | Wind power generation short-term load forecast method of least squares support vector machine |
| CN104182630A (en) * | 2014-08-20 | 2014-12-03 | 国家电网公司 | Residual battery capacity detection method based on simplified least square support vector machine |
| US20150338847A1 (en) * | 2014-05-20 | 2015-11-26 | Samsung Electronics Co., Ltd. | Method and apparatus for discovering equipment causing product defect in manufacturing process |
| CN105631550A (en) * | 2015-12-29 | 2016-06-01 | 吉林大学 | Short-term wind power combined prediction method |
-
2017
- 2017-10-23 CN CN201710992641.3A patent/CN107783071A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324034A (en) * | 2011-05-25 | 2012-01-18 | 北京理工大学 | Sensor-fault diagnosing method based on online prediction of least-squares support-vector machine |
| CN102663412A (en) * | 2012-02-27 | 2012-09-12 | 浙江大学 | Power equipment current-carrying fault trend prediction method based on least squares support vector machine |
| CN103488869A (en) * | 2013-08-23 | 2014-01-01 | 上海交通大学 | Wind power generation short-term load forecast method of least squares support vector machine |
| US20150338847A1 (en) * | 2014-05-20 | 2015-11-26 | Samsung Electronics Co., Ltd. | Method and apparatus for discovering equipment causing product defect in manufacturing process |
| CN104182630A (en) * | 2014-08-20 | 2014-12-03 | 国家电网公司 | Residual battery capacity detection method based on simplified least square support vector machine |
| CN105631550A (en) * | 2015-12-29 | 2016-06-01 | 吉林大学 | Short-term wind power combined prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 任磊等: "电力电子电路功率器件故障特征参数提取技术综述", 《中国电机工程学报》 * |
| 戴志雄等: "STATCOM直流侧电容对谐波含量的影响", 《微计算机信息》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111090071A (en) * | 2018-10-24 | 2020-05-01 | 株洲中车时代电气股份有限公司 | Method, system, device and storage medium for diagnosing sensor fault in converter |
| CN111090071B (en) * | 2018-10-24 | 2021-07-30 | 株洲中车时代电气股份有限公司 | Method, system, device and storage medium for diagnosing sensor fault in converter |
| CN110490266A (en) * | 2019-08-23 | 2019-11-22 | 北京邮电大学 | A kind of sensing data uploads, Transducer-fault Detecting Method and device |
| CN111564024A (en) * | 2020-05-25 | 2020-08-21 | 安徽复盛信息科技有限公司 | Automatic protection method and system based on dangerous gas monitoring alarm |
| CN115420325A (en) * | 2022-11-04 | 2022-12-02 | 深圳海润新能源科技有限公司 | Method for checking abnormal sensor of energy storage device, terminal equipment and storage medium |
| CN116579762A (en) * | 2023-04-14 | 2023-08-11 | 广州林旺空调工程有限公司 | Intelligent operation and maintenance platform for cooling tower |
| CN116579762B (en) * | 2023-04-14 | 2023-10-20 | 广州林旺空调工程有限公司 | Intelligent operation and maintenance platform for cooling tower |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107783071A (en) | Sensor fault monitoring method and device | |
| CN107462148B (en) | A kind of door state detection method and device | |
| US7693608B2 (en) | Systems and methods for alarm filtering and management within a real-time data acquisition and monitoring environment | |
| AU2007275224B2 (en) | Systems and methods for alarm filtering and management within a real-time data acquisition and monitoring environment | |
| Zarrabian et al. | Reinforcement learning approach for congestion management and cascading failure prevention with experimental application | |
| WO2012103244A2 (en) | Systems and methods for automated model-based real-time simulation of a microgrid for market-based electric power system optimization | |
| CA2657038C (en) | Systems and methods for real-time advanced visualization for predicting the health, reliability and performance of an electrical power system | |
| WO2012103246A2 (en) | Systems and methods for real-time dc microgrid power analytics for mission-critical power systems | |
| US20170160328A1 (en) | Distributed iot based sensor analytics for power line diagnosis | |
| CN107516303A (en) | Multi-object tracking method and system | |
| Wang et al. | Unscented Kalman filter based interval state estimation of cyber physical energy system for detection of dynamic attack | |
| CN109582109A (en) | Data center's control method and system | |
| CN111967738B (en) | Risk early warning method, system and medium of power grid information energy fusion system | |
| Suganyadevi et al. | Assessment of voltage stability margin by comparing various support vector regression models | |
| CN107608748A (en) | Application program management-control method, device, storage medium and terminal device | |
| CN110445176A (en) | A kind of distributed photovoltaic power prediction and data interaction system | |
| CN109193670A (en) | A kind of protective device and method of self-powered circuit | |
| Zhang et al. | Sensor/actuator faults detection for networked control systems via predictive control | |
| CN105676631A (en) | Intelligent rotating speed control system and method for generator set | |
| Changchao et al. | Research on the frequency synchronization control strategy for power system | |
| CN117288255A (en) | Line state monitoring method, device, computer equipment and storage medium | |
| CN110276852A (en) | Unmanned plane method for inspecting and device | |
| Lekshmi et al. | Online static security assessment module using radial basis neural network trained with particle swarm optimization | |
| CN109683040A (en) | Reliability checking method, device and the equipment of flexible direct current transmission converter valve | |
| Yuan et al. | Design of an intelligent decision model for power grid fault location and isolation based on topology analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180309 |
|
| RJ01 | Rejection of invention patent application after publication |