CN107218846A - A kind of driving of a tank room noise Active Control Method and system - Google Patents
A kind of driving of a tank room noise Active Control Method and system Download PDFInfo
- Publication number
- CN107218846A CN107218846A CN201710523850.3A CN201710523850A CN107218846A CN 107218846 A CN107218846 A CN 107218846A CN 201710523850 A CN201710523850 A CN 201710523850A CN 107218846 A CN107218846 A CN 107218846A
- Authority
- CN
- China
- Prior art keywords
- noise
- signal
- error
- acoustic
- fuzzy
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000003044 adaptive effect Effects 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 18
- 238000011478 gradient descent method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000008878 coupling Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 5
- 238000005859 coupling reaction Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000007935 neutral effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005183 dynamical system Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F41—WEAPONS
- F41H—ARMOUR; ARMOURED TURRETS; ARMOURED OR ARMED VEHICLES; MEANS OF ATTACK OR DEFENCE, e.g. CAMOUFLAGE, IN GENERAL
- F41H7/00—Armoured or armed vehicles
- F41H7/02—Land vehicles with enclosing armour, e.g. tanks
- F41H7/03—Air-pressurised compartments for crew; Means for preventing admission of noxious substances, e.g. combustion gas from gun barrels, in crew compartments; Sealing arrangements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
- G10K11/00—Methods or devices for transmitting, conducting or directing sound in general; Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/16—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
- G10K11/175—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
- G10K11/178—Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound by electro-acoustically regenerating the original acoustic waves in anti-phase
Abstract
The invention discloses a kind of driving of a tank room noise Active Control Method and system, method includes referring to the multiple main noise source noises of microphone pick, is inputted as reference signal；Residual noise after the control of error microphone acquisition noise, is inputted as error signal；Fuzzy controller receives the adaptive FX RBF nets training algorithm of reference-input signal, error input signal based on fuzzy neural network and reference signal and error signal is analyzed, and it is superimposed to loudspeaker and main noise source noise x [n] to export anti-phase target acoustic signal y [n].Active noise controlling of the invention based on fuzzy neural network, has obvious noise reduction to below 2000Hz noise, wherein, the noise reduction to below 1000Hz low-frequency noises is especially pronounced.
Description
Technical field
The present invention relates to ship naval vessels field noise control technique, more particularly to a kind of driving of a tank room noise is actively controlled
Method and system processed.
Background technology
Modern war is increasingly focused on maneuver of tanks ability, needs to improve constantly the hair of tank during Tank Development
Motivation power, along with the raising of engine power, the noise in tank module is also increasing.Noise in cabin has a strong impact on
The ability to work and physical and mental health of tank crew, influences the fighting capacity of army.
The noise produced for the mechanical noise of the dynamical systems such as engine, transmission case, crawler belt with ground effects, engine
Noise that caused body oscillating is formed during work etc., focuses mostly in middle low-frequency range.Traditional noise control technique is such as
More effective to high-frequency noise using methods such as sound absorption, sound insulation, noise eliminations, existing Active Noise Control scheme can only typically be controlled
Below 200Hz noise, and only can carry out Noise measarement for arrowband.In order to preferably reduce Middle and low frequency noise to tank
The harm of occupant, improves military engagement ability, is badly in need of using active noise reduction scheme, has to the Middle and low frequency noise in driving cabin
Effect control.
In view of the above-mentioned problems, existing be badly in need of releasing a driving of a tank room noise Active Control Method and system, realize
Noise measarement in larger frequency bandwidth.
The content of the invention
In view of the problem of above-mentioned prior art is present, the present invention provides a kind of driving of a tank room noise Active Control Method
And system.
The present invention solves technical problem and adopted the following technical scheme that：A kind of driving of a tank room noise Active Control Method,
Including：With reference to the multiple main noise source noise x [n] of microphone pick, inputted as reference signal；Error microphone acquisition noise control
Residual noise e [n] after system, is inputted as error signal；Fuzzy controller receives reference-input signal x [n], error input letter
Number e [n], the adaptive FX-RBF nets training algorithm based on fuzzy neural network is analyzed reference signal and error signal,
And anti-phase target acoustic signal y [n] is exported to loudspeaker；And loudspeaker sends the target sound for offsetting main noise source noise
Signal y [n], it is superimposed with main noise source noise x [n].
Optionally, the fuzzy controller includes acoustic mode extractor, using the acoustic mode extractor for needing
The amplitude of the main noise source to be controlled, energy, phase, frequency, the acoustic properties of direction and statistical property, from it is a series of not
At least one is extracted in related reference acoustic mode and refers to acoustic mode.
Optionally, the fuzzy controller is based on multiple uncorrelated reference acoustic modes above and carries out fuzzy controls, and defeated
Go out noise control mode.
Optionally, the noise control mode include but is not limited to noise source quantity, it is the position of the main noise source, described
The acoustic properties of the type of main noise source, the main noise source.
Optionally, the adaptive FX-RBF nets training algorithm includes：Reference noise is believed based on FuzzycMeans Clustering
Number collection is divided；The material calculation of each iteration is adaptively reduced based on approximate gradient descent method, and is dynamically adjusted most
The learning rate of small mean square deviation algorithm.
Optionally, the adaptive FX-RBF nets training algorithm also includes：Amplitude and phase to time lag signal are divided
Exported after analysis, reconstruct inverting target acoustical signal to loudspeaker.
Optionally, it is described to include the step of divided based on FuzzycMeans Clustering to reference noise signal data set：
Using Gaussian function as the basic function of algorithm, it is determined that being adapted to the optimal cluster number c and optimal weight of actual noise situation
After factor m, the center vector of hidden layer is learnt, until center vector no longer changes or less than predetermined threshold value, and calculated
Gaussian function variance；The material calculation that each iteration is adaptively reduced based on approximate gradient descent method, and dynamically adjust most
The step of learning rate of small mean square deviation algorithm, includes：Based on approximate gradient descent method, formula α (t+1)=α (t)-β is utilized
Δ E adaptively reduces the material calculation of each iteration, and dynamically adjusts the learning rate of lms algorithm；Then initialize
Hidden layer recycles formula to each weights of output layerWeights are counted
Calculate, until output error [y0(n)-y (n)] no longer change or during less than some default threshold value, stop study, otherwise continue weight
Multiple above learning procedure；α is learning rate in formula, and Δ E is the error before and after training, and β is adaptive adjusting step, and w is implicit
Layer arrives the weights of output layer, y0(n) it is target output value, y (n) is real output value.
Optionally, the reference microphone is located at the top of crew department and operating desk；The error microphone, which is located at, to be driven
Cabin seat is at human ear；The loudspeaker is located at the top of crew department and seat tops；The fuzzy controller, which is located at, to be driven
Member's under-seat.
The present invention solves technical problem and adopted the following technical scheme that：A kind of driving of a tank room noise active control system,
Including：With reference to microphone, coupled with fuzzy controller, it is defeated as reference signal for gathering multiple main noise source noise x [n]
Enter；Error microphone, couples with fuzzy controller, for the residual noise e [n] after acquisition noise control, is used as error signal
Input；Fuzzy controller, is coupled with the reference microphone, error microphone and loudspeaker, for receiving reference-input signal x
[n], error input signal e [n], the adaptive FX-RBF nets training algorithm based on fuzzy neural network is to reference signal and error
Signal is analyzed, and exports anti-phase target acoustic signal y [n] to loudspeaker；And loudspeaker, with the fuzzy controller coupling
Connect, it is superimposed with main noise source noise x [n] for sending the target acoustic signal y [n] for offsetting main noise source noise.
Optionally, the fuzzy controller includes acoustic mode extractor, using the acoustic mode extractor for needing
The amplitude of the main noise source to be controlled, energy, phase, frequency, the acoustic properties of direction and statistical property, from it is a series of not
At least one is extracted in related reference acoustic mode and refers to acoustic mode；The fuzzy controller is based on multiple uncorrelated above
Fuzzy control, and output noise control model are carried out with reference to acoustic mode；The noise control mode includes but is not limited to noise
Source quantity, the position of the main noise source, the type of the main noise source, the acoustic properties of the main noise source；The reference
Microphone is located at the top of crew department and operating desk；The error microphone is located at flight deck seat at human ear；It is described to raise
Sound device is located at the top of crew department and seat tops；The fuzzy controller is located at below pilot set.
The present invention has the advantages that：
1. inputted using multiple reference signals of the function applied to polymorphic type sound source will be extracted with reference to acoustic mode extractor
In, by Adaptive adjusting algorithm extract the optimization of function, can effectively ensure the degree of accuracy of extracted acoustic mode；
2. the active noise control system based on fuzzy neural network, has obvious noise reduction to below 2000Hz noise
Effect, wherein, the noise reduction to below 1000Hz low-frequency noises is especially pronounced；
3. carrying out automatically adjusting for learning rate based on adaptive FX-RBF nets training algorithm, the same of the stability of a system is being ensured
When, improve algorithm the convergence speed and study precision；
4. carrying out the reconstruct of reverse target acoustic signal based on adaptive FX-RBF algorithms, anti-noise sound source Time Delay is being solved
While, effectively increase noise reduction.
Brief description of the drawings
Fig. 1 is a kind of embodiment schematic diagram of driving of a tank room noise Active Control Method of the invention；
Fig. 2 is schematic diagram in a kind of driving of a tank room of the present invention；
Fig. 3 is the fundamental diagram of acoustic mode extractor provided in an embodiment of the present invention；
Fig. 4 is fuzzy controller illustraton of model provided in an embodiment of the present invention；
Fig. 5 show the specific schematic diagram of the application driving of a tank room noise active control system.
Embodiment
Technical scheme is further elaborated with reference to embodiment and accompanying drawing.
Some vocabulary have such as been used to censure specific components among specification and claim.Those skilled in the art should
It is understood that hardware manufacturer may call same component with different nouns.This specification and claims are not with name
The difference of title is used as the mode for distinguishing component, but is used as the criterion of differentiation with the difference of component functionally.Such as logical
The "comprising" of piece specification and claim mentioned in is an open language, therefore should be construed to " include but do not limit
In "." substantially " refer in receivable error range, those skilled in the art can solve described in the range of certain error
Technical problem, basically reaches the technique effect.In addition, " coupling " one word is herein comprising any direct and indirect electric property coupling
Means.Therefore, if a first device is coupled to a second device described in text, representing the first device can directly electrical coupling
The second device is connected to, or the second device is electrically coupled to indirectly by other devices or coupling means.Specification
Subsequent descriptions for implement the application better embodiment, so it is described description be for the purpose of the rule for illustrating the application,
It is not limited to scope of the present application.The protection domain of the application is worked as to be defined depending on the appended claims person of defining.
Embodiment 1
Present embodiments provide a kind of driving of a tank room noise Active Control Method.It is shown in Figure 1 be the application in
Step includes in the specific embodiment of driving of a tank room noise Active Control Method, the present embodiment：
Step S1-1：With reference to the multiple main noise source noise x [n] of microphone pick, inputted as reference signal；
Step S1-2：Residual noise e [n] after the control of error microphone acquisition noise, is inputted as error signal；
Step S2：Fuzzy controller receives reference-input signal x [n]=x [n], error input signal e [n], based on fuzzy
Adaptive-filtering RBF (Filter-x Radial Basis Function, hereinafter referred to as FX-RBF) net training of neutral net
Algorithm is analyzed reference signal and error signal, and exports anti-phase target acoustic signal y [n] to loudspeaker；And
Step S3：Loudspeaker sends the target acoustic signal y [n] for offsetting main noise source noise, with main noise source noise x
[n] is superimposed.
Wherein, it is located at reference to microphone at the top of crew department and operating desk；It is close that error microphone is located at flight deck seat
At human ear；Loudspeaker is located at the top of crew department and seat tops；Fuzzy controller is located at below pilot set, such as Fig. 2 institutes
Show.
Wherein, fuzzy controller includes acoustic mode extractor, as shown in figure 3, Fig. 3 is sound provided in an embodiment of the present invention
Learn the fundamental diagram of pattern extractor.
Using acoustic mode extractor for the amplitude of main noise source for needing to control, energy, phase, frequency, direction and
The acoustic properties of statistical property, extraction at least one refers to acoustic mode from a series of incoherent reference acoustic modes.Mould
Fuzzy controllers are based on multiple uncorrelated reference acoustic modes above and carry out fuzzy controls, and output noise control model, noise control
Molding formula includes but is not limited to noise source quantity, the position of main noise source, the type of main noise source, the acoustics category of main noise source
Property.
Set in fuzzy controller and refer to acoustic mode extractor, function will be extracted using with reference to acoustic mode extractorApplied to described multiple reference signals input x [n], then to passing through extraction algorithmIt is defeated after processing
Go out with reference to acoustic mode s [n]；Then estimation function α is applied to output reference model s using with reference to acoustic mode extractor
[n], after to compared estimate α (s [n]) extract the adaptive adjustment of function.
Fig. 4 is fuzzy controller illustraton of model provided in an embodiment of the present invention.The driving of a tank room noise that the present invention is provided
Active Control Method mainly includes：Based on sound system unintentional nonlinearity characteristic, neutral net is introduced into fuzzy control, mould is constituted
Neutral net is pasted, according to input and output sample, by using the learning method of neutral net, Automated Design and adjustment fuzzy system
Self study and adaptation function, improve the degree of accuracy and the noise reduction of active noise controlling；Wherein x (n) makes an uproar for system reference
Acoustical signal, e (n) is residual noise signal, and y (n) is controller output signal.
As illustrated, the type of processing unit is divided into three classes in neutral net：Input layer, output layer, hidden layer；
Input layer：Noise source signal and data outside receiving；Input layer signal in the present invention is " addition delay link
Reference signal input vector "；
Output layer：Realize the output of system result；In the present invention, be " by optimal noise control mode export to
Loudspeaker, drives it to send corresponding target acoustic signal "；
Hidden layer：Line translation is entered to input vector, between input and output layer, the processing do not observed by its exterior
Unit；In the present invention, it is " the reference signal input vector of low-dimensional to be converted into higher dimensional space, realizes that the linear of sound system is asked
Inscribe the linear separability in higher dimensional space ".
Adaptive FX-RBF net training algorithms include：Reference noise signal data set is carried out based on FuzzycMeans Clustering
Divide；The material calculation of each iteration is adaptively reduced based on approximate gradient descent method, and dynamically adjusts lms algorithm
Learning rate.
It is above-mentioned to include the step of divided based on FuzzycMeans Clustering to reference noise signal data set：
Using Gaussian function as the basic function of algorithm, it is determined that be adapted to actual noise situation optimal cluster number c and
After optimal weight factor m, the center vector of hidden layer is learnt, until center vector no longer changes or less than default threshold
Value, and calculate Gaussian function variance.
The above-mentioned material calculation that each iteration is adaptively reduced based on approximate gradient descent method, and dynamically adjust lowest mean square
The step of learning rate of difference algorithm, includes：
Based on approximate gradient descent method, the meter of each iteration is adaptively reduced using formula α (t+1)=α (t)-β Δs E
Step-length is calculated, and dynamically adjusts the learning rate of lms algorithm, more efficient accelerates convergence of algorithm speed；
Then initialization hidden layer recycles formula to each weights of output layer
Weights are calculated, until output error [y0(n)-y (n)] no longer change or during less than some default threshold value, stop learning
Practise, otherwise continue to repeat above learning procedure；Algorithm is improved by dynamic adaptive regularized learning algorithm speed in learning process
Convergence rate, so as to improve study precision.
α is learning rate in formula, and Δ E is the error before and after training, and β is adaptive adjusting step, and w is hidden layer to output
The weights of layer, y0(n) it is target output value, y (n) is real output value.
Wherein, the adaptive FX-RBF nets training algorithm also includes：Amplitude and phase to time lag signal are analyzed,
Exported after reconstruct inverting target acoustical signal to loudspeaker, the time lag signal refers to that reference signal x (t) waits to eliminate the noise propagating to
In the path of point, the signal y (t) produced due to time delay；The relation of time lag signal and reference signal：Y (t)=x (t)-x
(t-t0), wherein, x (t) is reference signal, and y (t) is time lag signal, t0For lag time.
Embodiment 2
In order that present invention description is more clearly and detailed, while being easy to technical staff to understand, the present embodiment provides a kind of smooth
Active noise control system in gram driver's cabin, it is shown in Figure 5 for the application driving of a tank room noise active control system
Specific schematic diagram.
A kind of driving of a tank room noise active control system, including：
With reference to microphone, coupled with fuzzy controller, for gathering multiple main noise source noise x [n], be used as reference signal
Input；
Error microphone, couples with fuzzy controller, for the residual noise e [n] after acquisition noise control, is used as error
Signal is inputted；
Fuzzy controller, with being coupled with reference to microphone, speed probe, error microphone and loudspeaker, for receiving ginseng
Input signal x [n]=x [n], error input signal e [n] are examined, the adaptive FX-RBF net training based on fuzzy neural network is calculated
Method is analyzed reference signal and error signal, and exports anti-phase target acoustic signal y [n] to loudspeaker；And
Loudspeaker, is coupled with fuzzy controller, for sending the target acoustic signal y [n] for offsetting main noise source noise,
It is superimposed with main noise source noise x [n].
Wherein, above-mentioned reference microphone and error microphone are microphone.
Fuzzy controller includes acoustic mode extractor, using acoustic mode extractor for needing the main noise source of control
Amplitude, energy, phase, frequency, the acoustic properties of direction and statistical property, from a series of incoherent reference acoustic modes
Extract at least one and refer to acoustic mode.
Fuzzy controller is based on multiple uncorrelated reference acoustic modes above and carries out fuzzy controls, and output noise control mould
Formula.Noise control mode includes but is not limited to noise source quantity, the position of main noise source, the type of main noise source, main noise source
Acoustic properties.
Wherein, it is located at reference to microphone at the top of crew department and operating desk；It is close that error microphone is located at flight deck seat
At human ear；Loudspeaker is located at the top of crew department and seat tops；Fuzzy controller is located at below pilot set.
In summary, the present invention is provided a kind of driving of a tank room noise Active Control Method and system, with existing skill
Art is compared, and is had the advantages that：
1. the active noise control system based on fuzzy neural network, has obvious noise reduction to below 2000Hz noise
Effect, wherein, the noise reduction to below 1000Hz low-frequency noises is especially pronounced；Made an uproar in driving of a tank room provided by the present invention
Sound active control system, can realize the active control of driving of a tank Shi Nei senior middle schools low-frequency noise；
2. inputted using multiple reference signals of the function applied to polymorphic type sound source will be extracted with reference to acoustic mode extractor
In, by Adaptive adjusting algorithm extract the optimization of function, can effectively ensure the degree of accuracy of extracted acoustic mode；
3. carrying out automatically adjusting for learning rate based on adaptive FX-RBF nets training algorithm, the same of the stability of a system is being ensured
When, improve algorithm the convergence speed and study precision；
4. directly being controlled time lag noise based on adaptive FX-RBF algorithms, efficiently solve anti-noise sound source time lag and ask
Topic, and improve noise reduction.
For ease of description, the quality of embodiment is not only represented for the sequencing of above example.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. a kind of driving of a tank room noise Active Control Method, it is characterised in that including：
With reference to the multiple main noise source noise x [n] of microphone pick, inputted as reference signal；
Residual noise e [n] after the control of error microphone acquisition noise, is inputted as error signal；
Fuzzy controller receives reference-input signal x [n], error input signal e [n], based on the adaptive of fuzzy neural network
FX-RBF nets training algorithm is analyzed reference signal and error signal, and exports anti-phase target acoustic signal y [n] to raising one's voice
Device；And
Loudspeaker sends the target acoustic signal y [n] for offsetting main noise source noise, superimposed with main noise source noise x [n].
2. driving of a tank room noise Active Control Method according to claim 1, it is characterised in that the fuzzy control
Device includes acoustic mode extractor, the amplitude of the main noise source controlled using the acoustic mode extractor for needs,
Energy, phase, frequency, the acoustic properties of direction and statistical property, extracted from a series of incoherent reference acoustic modes to
Few one kind refers to acoustic mode.
3. driving of a tank room noise Active Control Method according to claim 2, it is characterised in that the fuzzy control
Device is based on multiple uncorrelated reference acoustic modes above and carries out fuzzy controls, and output noise control model.
4. driving of a tank room noise Active Control Method according to claim 3, it is characterised in that the Noise measarement
Pattern includes but is not limited to noise source quantity, the position of the main noise source, the type of the main noise source, the main noise source
Acoustic properties.
5. driving of a tank room noise Active Control Method according to claim 1, it is characterised in that described adaptive
FX-RBF net training algorithms include：Reference noise signal data set is divided based on FuzzycMeans Clustering；Based on approximate
Gradient descent method adaptively reduces the material calculation of each iteration, and dynamically adjusts the learning rate of lms algorithm.
6. driving of a tank room noise Active Control Method according to claim 1, it is characterised in that described adaptive
FX-RBF net training algorithms also include：Amplitude and phase to time lag signal are analyzed, defeated after reconstruct inverting target acoustical signal
Go out to loudspeaker.
7. driving of a tank room noise Active Control Method according to claim 5, it is characterised in that described based on fuzzy
The step of c- mean clusters are divided to reference noise signal data set includes：
Using Gaussian function as the basic function of algorithm, it is determined that being adapted to the optimal cluster number c of actual noise situation and optimal
After weight factor m, the center vector of hidden layer is learnt, until center vector no longer changes or less than predetermined threshold value, and
Calculate Gaussian function variance；
The material calculation that each iteration is adaptively reduced based on approximate gradient descent method, and dynamically adjustment Minimum Mean Square Error is calculated
The step of learning rate of method, includes：
Based on approximate gradient descent method, walked using formula α (t+1)=α (the t)-β Δs E calculating for adaptively reducing each iteration
It is long, and dynamically adjust the learning rate of lms algorithm；
Then initialization hidden layer recycles formula to each weights of output layer
Weights are calculated, until output error [y0(n)-y (n)] no longer change or during less than some default threshold value, stop learning
Practise, otherwise continue to repeat above learning procedure；
α is learning rate in formula, and Δ E is the error before and after training, and β is adaptive adjusting step, and w is that hidden layer arrives output layer
Weights, y0(n) it is target output value, y (n) is real output value.
8. the driving of a tank room noise Active Control Method according to claim any one of 1-7, it is characterised in that described
It is located at reference to microphone at the top of crew department and operating desk；The error microphone is located at flight deck seat at human ear；Institute
Loudspeaker is stated positioned at crew department top and seat tops；The fuzzy controller is located at below pilot set.
9. a kind of driving of a tank room noise active control system, it is characterised in that including：
With reference to microphone, coupled with fuzzy controller, it is defeated as reference signal for gathering multiple main noise source noise x [n]
Enter；
Error microphone, couples with fuzzy controller, for the residual noise e [n] after acquisition noise control, is used as error signal
Input；
Fuzzy controller, is coupled with the reference microphone, error microphone and loudspeaker, for receiving reference-input signal x
[n], error input signal e [n], the adaptive FX-RBF nets training algorithm based on fuzzy neural network is to reference signal and error
Signal is analyzed, and exports anti-phase target acoustic signal y [n] to loudspeaker；And
Loudspeaker, is coupled with the fuzzy controller, for sending the target acoustic signal y [n] for offsetting main noise source noise,
It is superimposed with main noise source noise x [n].
10. driving of a tank room noise active control system according to claim 9, it is characterised in that the Fuzzy Control
Device processed includes acoustic mode extractor, utilizes the acoustic mode extractor shaking for the main noise source of needs control
Width, energy, phase, frequency, the acoustic properties of direction and statistical property, are extracted from a series of incoherent reference acoustic modes
At least one refers to acoustic mode；The fuzzy controller is based on multiple uncorrelated reference acoustic modes above and carries out Fuzzy Controls
System, and output noise control model；The noise control mode includes but is not limited to noise source quantity, the position of the main noise source
Put, the type of the main noise source, the acoustic properties of the main noise source；The reference microphone be located at crew department at the top of and
Operating desk；The error microphone is located at flight deck seat at human ear；The loudspeaker is located at the top of crew department and seat
At the top of chair；The fuzzy controller is located at below pilot set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710523850.3A CN107218846A (en) | 2017-06-30 | 2017-06-30 | A kind of driving of a tank room noise Active Control Method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710523850.3A CN107218846A (en) | 2017-06-30 | 2017-06-30 | A kind of driving of a tank room noise Active Control Method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107218846A true CN107218846A (en) | 2017-09-29 |
Family
ID=59951580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710523850.3A Pending CN107218846A (en) | 2017-06-30 | 2017-06-30 | A kind of driving of a tank room noise Active Control Method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107218846A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111833840A (en) * | 2019-04-17 | 2020-10-27 | 北京地平线机器人技术研发有限公司 | Noise reduction method and device, system, electronic equipment and storage medium |
| CN112652289A (en) * | 2020-12-11 | 2021-04-13 | 西安艾科特声学科技有限公司 | Fire fighting truck cab local space active noise control system and method |
| CN113488015A (en) * | 2021-06-23 | 2021-10-08 | 武汉理工大学 | Active control system and control method for mixing structural sound and air sound of excavator cab |
| CN113539229A (en) * | 2021-07-30 | 2021-10-22 | 北京安声浩朗科技有限公司 | Noise reduction parameter determination method and device, active noise reduction method and device |
| CN113539228A (en) * | 2021-07-30 | 2021-10-22 | 北京安声浩朗科技有限公司 | Noise reduction parameter determination method and device, active noise reduction method and device |
| WO2022037308A1 (en) * | 2020-08-21 | 2022-02-24 | 中车株洲电力机车有限公司 | Active noise reduction method for rail transit vehicle and cab |
| CN114162261A (en) * | 2021-11-16 | 2022-03-11 | 舟山中远海运重工有限公司 | Ship noise control method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020117579A1 (en) * | 2000-12-29 | 2002-08-29 | Kotoulas Antonios N. | Neural net controller for noise and vibration reduction |
| US20120288110A1 (en) * | 2011-05-11 | 2012-11-15 | Daniel Cherkassky | Device, System and Method of Noise Control |
| CN103646252A (en) * | 2013-12-05 | 2014-03-19 | 江苏大学 | Optimized fuzzy learning vector quantization apple classification method |
| CN104616667A (en) * | 2014-12-02 | 2015-05-13 | 清华大学 | Active noise reduction method for automobile |
| CN104778951A (en) * | 2015-04-07 | 2015-07-15 | 华为技术有限公司 | Speech enhancement method and device |
| CN104794482A (en) * | 2015-03-24 | 2015-07-22 | 江南大学 | Inter-class maximization clustering algorithm based on improved kernel fuzzy C mean value |
| CN106128449A (en) * | 2016-08-16 | 2016-11-16 | 青岛歌尔声学科技有限公司 | A kind of automobile active denoising method |
| CN106778826A (en) * | 2016-11-25 | 2017-05-31 | 南昌航空大学 | Based on the hereditary Hybrid Clustering Algorithm with preferred Fuzzy C average of self adaptation cellular |
-
2017
- 2017-06-30 CN CN201710523850.3A patent/CN107218846A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020117579A1 (en) * | 2000-12-29 | 2002-08-29 | Kotoulas Antonios N. | Neural net controller for noise and vibration reduction |
| US20120288110A1 (en) * | 2011-05-11 | 2012-11-15 | Daniel Cherkassky | Device, System and Method of Noise Control |
| CN103646252A (en) * | 2013-12-05 | 2014-03-19 | 江苏大学 | Optimized fuzzy learning vector quantization apple classification method |
| CN104616667A (en) * | 2014-12-02 | 2015-05-13 | 清华大学 | Active noise reduction method for automobile |
| CN104794482A (en) * | 2015-03-24 | 2015-07-22 | 江南大学 | Inter-class maximization clustering algorithm based on improved kernel fuzzy C mean value |
| CN104778951A (en) * | 2015-04-07 | 2015-07-15 | 华为技术有限公司 | Speech enhancement method and device |
| CN106128449A (en) * | 2016-08-16 | 2016-11-16 | 青岛歌尔声学科技有限公司 | A kind of automobile active denoising method |
| CN106778826A (en) * | 2016-11-25 | 2017-05-31 | 南昌航空大学 | Based on the hereditary Hybrid Clustering Algorithm with preferred Fuzzy C average of self adaptation cellular |
Non-Patent Citations (6)
| Title |
|---|
| 刘士荣, 俞金寿: "过程建模和控制中的神经网络与模糊逻辑融合技术的现状与发展趋势", 宁波大学学报(理工版), no. 01 * |
| 张宇献;李松;董晓;: "基于特征聚类数据划分的多神经网络模型", 信息与控制, no. 06 * |
| 张运陶;杨晓丽;: "自适应径向基神经网络及其应用", 计算机与应用化学, no. 01 * |
| 李传光, 姜丽飞, 李长青: "RBF网络在履带车辆舱室内有源降噪的实验研究", 北京理工大学学报, no. 04, pages 1 - 3 * |
| 苏小红;侯秋香;马培军;王亚东;: "RBF神经网络的混合学习算法", 哈尔滨工业大学学报, no. 09 * |
| 陈燕, 李桃迎: "Matlab神经网络与应用", 大连海事大学出版社, pages: 253 - 256 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111833840A (en) * | 2019-04-17 | 2020-10-27 | 北京地平线机器人技术研发有限公司 | Noise reduction method and device, system, electronic equipment and storage medium |
| WO2022037308A1 (en) * | 2020-08-21 | 2022-02-24 | 中车株洲电力机车有限公司 | Active noise reduction method for rail transit vehicle and cab |
| CN112652289A (en) * | 2020-12-11 | 2021-04-13 | 西安艾科特声学科技有限公司 | Fire fighting truck cab local space active noise control system and method |
| CN113488015A (en) * | 2021-06-23 | 2021-10-08 | 武汉理工大学 | Active control system and control method for mixing structural sound and air sound of excavator cab |
| CN113488015B (en) * | 2021-06-23 | 2024-03-15 | 武汉理工大学 | Active control system and control method for mixing structural sound and air sound of cab of excavator |
| CN113539229A (en) * | 2021-07-30 | 2021-10-22 | 北京安声浩朗科技有限公司 | Noise reduction parameter determination method and device, active noise reduction method and device |
| CN113539228A (en) * | 2021-07-30 | 2021-10-22 | 北京安声浩朗科技有限公司 | Noise reduction parameter determination method and device, active noise reduction method and device |
| CN113539228B (en) * | 2021-07-30 | 2023-10-31 | 北京安声浩朗科技有限公司 | Noise reduction parameter determining method and device, active noise reduction method and device |
| CN113539229B (en) * | 2021-07-30 | 2023-10-31 | 北京安声浩朗科技有限公司 | Noise reduction parameter determining method and device, active noise reduction method and device |
| CN114162261A (en) * | 2021-11-16 | 2022-03-11 | 舟山中远海运重工有限公司 | Ship noise control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107230472A (en) | Noise initiative control method and system in a kind of helicopter cockpit | |
| CN107218846A (en) | A kind of driving of a tank room noise Active Control Method and system | |
| CN107240392A (en) | A kind of armored vehicle cabin room noise Active Control Method and system | |
| CN107230473A (en) | Noise initiative control method and system in a kind of submarine cabin | |
| CN207149250U (en) | Active noise control system in a kind of helicopter cockpit | |
| CN107240391A (en) | A kind of active noise controlling method based on fuzzy neural network, system and panzer helmet of driver | |
| Cheer et al. | Active noise control of a diesel generator in a luxury yacht | |
| CN207925130U (en) | Active noise control system in a kind of submarine cabin | |
| CN109747575A (en) | A kind of multi-mode in-vehicle sound quality optimization system based on order optimization | |
| CN108189724B (en) | Automobile feedback control active noise reduction neck pillow | |
| CN105931650B (en) | A kind of self-adaptation noise reduction method based on audio feature extraction | |
| CN107248408A (en) | A kind of active noise controlling method based on fuzzy neural network, system and helicopter pilot's helmet | |
| Buck et al. | Performance evaluation of an active headrest considering non-stationary broadband disturbances and head movement | |
| US20150358727A1 (en) | Active buffeting control in an automobile | |
| CN109346052B (en) | Device and method for optimizing sound quality in vehicle by utilizing active noise reduction | |
| US20170278504A1 (en) | Actively controlled quiet headspace | |
| CN110972007A (en) | Active earphone noise reduction method suitable for ship high-noise scene | |
| EP0789900A1 (en) | Reduction of computational burden of adaptively updating control filter(s) in active systems | |
| CN110503937B (en) | Sound quality optimization system and method | |
| Ferrari et al. | Investigation of an engine order noise cancellation system in a super sports car | |
| EP3844741A1 (en) | Systems and methods for noise-cancellation with shaping and weighting filters | |
| CN111951775A (en) | In-vehicle sound quality optimization system and optimization method | |
| CN106990800A (en) | A kind of narrowband self-adaption method based on preposition across band filter group structure | |
| Foo et al. | Active noise cancellation headset | |
| Macchi et al. | A feedback multi-tone algorithm for the control of helicopter gearbox noise in an active headrest |
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 |