CN111968613A - Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle - Google Patents

Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle Download PDF

Info

Publication number
CN111968613A
CN111968613A CN202010862334.5A CN202010862334A CN111968613A CN 111968613 A CN111968613 A CN 111968613A CN 202010862334 A CN202010862334 A CN 202010862334A CN 111968613 A CN111968613 A CN 111968613A
Authority
CN
China
Prior art keywords
noise
neural network
fuzzy
convolutional
convolution
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010862334.5A
Other languages
Chinese (zh)
Other versions
CN111968613B (en
Inventor
李涛
贺钰瑶
冯江华
桂卫华
王宁
罗竹辉
龙永红
胡云卿
李燕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University of Technology
Original Assignee
Hunan University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan University of Technology filed Critical Hunan University of Technology
Priority to CN202010862334.5A priority Critical patent/CN111968613B/en
Publication of CN111968613A publication Critical patent/CN111968613A/en
Application granted granted Critical
Publication of CN111968613B publication Critical patent/CN111968613B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10KSOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K11/00Methods 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
    • G10K11/16Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/175Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
    • G10K11/178Methods 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
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10KSOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K11/00Methods 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
    • G10K11/16Methods or devices for protecting against, or for damping, noise or other acoustic waves in general
    • G10K11/175Methods or devices for protecting against, or for damping, noise or other acoustic waves in general using interference effects; Masking sound
    • G10K11/178Methods 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
    • G10K11/1785Methods, e.g. algorithms; Devices
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10KSOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K2210/00Details of active noise control [ANC] covered by G10K11/178 but not provided for in any of its subgroups
    • G10K2210/10Applications
    • G10K2210/128Vehicles
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10KSOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K2210/00Details of active noise control [ANC] covered by G10K11/178 but not provided for in any of its subgroups
    • G10K2210/30Means
    • G10K2210/301Computational
    • G10K2210/3018Correlators, e.g. convolvers or coherence calculators
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10KSOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K2210/00Details of active noise control [ANC] covered by G10K11/178 but not provided for in any of its subgroups
    • G10K2210/30Means
    • G10K2210/301Computational
    • G10K2210/3029Fuzzy logic; Genetic algorithms
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10KSOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K2210/00Details of active noise control [ANC] covered by G10K11/178 but not provided for in any of its subgroups
    • G10K2210/30Means
    • G10K2210/301Computational
    • G10K2210/3038Neural networks

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Soundproofing, Sound Blocking, And Sound Damping (AREA)

Abstract

The invention discloses a convolution-fuzzy neural network method for actively controlling global spatial noise of a vehicle. The method includes providing a plurality of sub-passageways around a noise reduction zone of the vehicle; collecting noise residual signals of each secondary channel; a convolution-fuzzy neural network is adopted to perform off-line identification to obtain a secondary path model, meanwhile, the secondary path model is used as a self-adaptive active noise control algorithm of a secondary path to correct parameters of a controller on line, and finally, multi-directional noise cancellation signals are output. The invention uses the convolution-fuzzy neural network for identifying the inverse model of the object, provides a very effective method for identifying the nonlinear noise in the global space of the vehicle, and improves the identification precision of the secondary path by utilizing the nonlinear approximation capability of the convolution-fuzzy neural network to the function; an active feedback noise elimination system is adopted to establish a stable secondary path model; the problems of difficult control of global spatial noise and narrow frequency band of the vehicle are solved.

Description

Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle
Technical Field
The invention relates to the technical field of vehicle noise control, in particular to a convolution-fuzzy neural network method for actively controlling vehicle global spatial noise.
Background
In recent years, with the continuous improvement of the manufacturing technology level of high-speed trains in China, the running speed of the trains is rapidly improved, the comfort requirement of rail transit vehicles is gradually improved to the same position after the rail transit vehicles meet the dynamic requirement, and the noise control level is one of key indexes for measuring the comfort of the vehicles.
In the field of urban rail transit, the tunnel space makes the subjective feeling of noise stronger. Complaints about train noise problems, whether by passengers or by subway operating units, are also emerging. Particularly, in cities with long subway opening time and aged lines and vehicles, the problems of wheel track and vehicle noise are more prominent.
The traditional noise control method for the rail transit vehicle mostly adopts a passive control method, namely, technical means such as sound absorption, sound insulation and vibration reduction are adopted to control noise, and the method has the advantages that the medium-high frequency noise reduction effect is visual and obvious, and the physical realization is convenient; the defects are that the noise diagnosis and positioning period is long, particularly for the designed and shaped vehicle system, the noise reduction process through structure and material optimization is very complicated, and the noise reduction effect of low-frequency noise is limited.
In the prior art, active noise control is also used, for example, a hybrid ANC apparatus is disclosed in the application No. 201610590884.X, so as to improve the anti-interference capability of the noise reduction apparatus. Compared with the traditional ANC device, the influence of external random noise on the noise reduction effect can be effectively eliminated, and the environmental adaptability of the equipment is enhanced. The patent with the application number of 201710523010.7 discloses an active noise control method based on a fuzzy neural network, which realizes active control of high, medium and low frequency noise in a cab of an armored vehicle, has an obvious noise reduction effect on noise below 2000Hz, and particularly has an obvious noise reduction effect on low frequency noise below 1000 Hz. The patent with application number 201810022206.2 collects more coherent noise signals through optimizing a multi-channel noise control algorithm, and then generates stable control signals, so that the noise reduction effect is realized, and multiple noise reduction modes are selectable according to different use scenes.
However, although the prior art basically achieves noise reduction, the following disadvantages still exist:
(1) only the noise reduction of local or specific areas of the vehicle is realized, and the global noise reduction problem of the vehicle cannot be solved.
(2) The effect achieved by the existing active noise control technology is almost narrow-band noise reduction, and mainly aims at performing targeted cancellation on single-band pure tones with relatively large contribution, so that the requirement of a wide band is difficult to achieve.
(3) The existing noise reduction control method such as FX-LMS algorithm mainly depends on a primary path sensor, and is suitable for noise reduction with clear noise source diagnosis and clear characteristics; when the sound source is not clear, large deviation can occur, the control effect is seriously influenced, and the method is particularly suitable for noise reduction of time-varying nonlinear noise.
(4) The existing secondary path is simple in modeling and poor in stability, and does not have self-learning and prediction capabilities.
In noise active control systems (ANC), the modeling of the secondary path presents the following problems:
first, in noisy active control systems, there is basically a problem of non-linearity, affecting the modeling accuracy. For designers, when the system is clear or simple, an accurate mathematical model is generally established by using a mathematical tool, but when the system is complicated or unknown and has little information, the accurate model is difficult to establish by using the general mathematical tool, and the stability of the system cannot be ensured.
Secondly, especially for the noise source of a large vehicle, the main lobe and the side lobe of the noise frequency in different areas are different, so that different control strategies are required for different secondary paths, and the modeling difficulty of the secondary paths is increased.
Furthermore, due to the complexity and high cost of the active noise control technology, the prior art only relates to a few advanced vehicle models in automotive engineering applications, although for applications such as pipe noise where plane sound wave propagation is dominant, a simpler control system consisting of a single secondary sound source and an error sensor can achieve a more desirable control effect. However, compared with a car in a narrow space, a car with a wider sound field space, such as a rail car, has more internal noise excitation sources, a multi-coupling model caused by train cascade is more complicated, and the difficulty in actively controlling the noise in a reverberation sound field is greater. For a system with complex cascade connection of trains, the single-stage sound source feedforward control active noise elimination system cannot meet the requirements.
In the patent, active noise control means that secondary sound with the same frequency, equal amplitude and opposite phase with noise at the position of a noise source is generated in real time in a specific space, and the secondary sound and the source noise are superposed and cancelled to realize noise reduction. It generally comprises two large parts: a controller portion and an acoustic vibration portion. The controller mainly processes the reference signal and the error signal, outputs a driving signal and drives the secondary sound source. The acoustic vibrations mainly comprise secondary acoustic sources (electro-acoustic devices, actuators), position sensors and error sensors. The active noise control can be further classified into a feedforward control method, a feedback control method, a hybrid control method, and the like.
The secondary path refers to the physical path from the electroacoustic device to the error sensor, and typically includes the acoustic field, the electroacoustic sensing device, the electronic circuitry, etc.; identification of the secondary path is modeling of the secondary path.
Disclosure of Invention
In order to overcome at least one defect in the prior art, the invention provides a convolution-fuzzy neural network method for actively controlling the global spatial noise of the vehicle.
Providing a plurality of sub-passageways around a noise reduction zone of a vehicle; collecting noise residual signals of each secondary channel; and (3) performing off-line identification by adopting a convolution-fuzzy neural network to obtain a secondary path model, meanwhile, using the model as a self-adaptive active noise control algorithm of a secondary path, correcting the parameters of the controller on line, and finally outputting a multi-azimuth noise cancellation signal.
The scheme is suitable for noise reduction in a wider space, such as a vehicle global space; the defects of large noise excitation sources in an open space and large control difficulty caused by multiple vehicle cascade coupling can be overcome, and the noise reduction effect is good.
And furthermore, the convolution-fuzzy neural network comprises a convolution network, a fuzzy layer and a full connection layer, fuzzy reasoning is carried out on the sample characteristic vectors passing through the convolution network in the fuzzy layer, training is carried out on the full connection layer, the weight value is extracted for updating, and modeling and noise reduction are carried out on the collected noise residual signals. The convolution network deeply extracts the signal characteristics and reduces the dimension, thereby obviously reducing the number of network parameters and improving the calculation speed. The fuzzy neural network combines the advantages of a fuzzy system and the neural network, and has good capability of processing uncertain or inaccurate information and excellent data training and self-adapting capability of the neural network.
Further, the learning of the convolution-fuzzy neural network in the process of online correcting the parameters of the controller by adopting the convolution-fuzzy neural network to firstly carry out off-line identification to obtain a secondary path model and simultaneously using the self-adaptive active noise control algorithm of the secondary path comprises the following steps:
s1, initializing a controller based on a convolution-fuzzy neural network algorithm;
s2, calculating input and output of each layer of the controller based on the convolution-fuzzy neural network algorithm;
s3, calculating the input and output of the convolutional-fuzzy neural network recognizer;
and S4, correcting the parameters of the controller.
Further, step S2 is specifically:
through a series of convolutions and pooling exchanges in a convolutional network:
Figure BDA0002647343120000031
wherein ,zg(n) the g-th convolutional layer output unit; omegatg(n) weights for all input units connected to the g-th output unit, bg(n) is the bias of the g convolutional layer output unit;
the relu function is selected as an activation function to obtain the output of a convolution network with a higher level as the input of a fuzzy layer:
og(n)=max(0,zg(n))
the fuzzy layer divides and converts the characteristic matrix obtained after convolution and pooling into proper membership function values according to the fuzzy degree and the membership function:
Figure BDA0002647343120000041
in the formula ,
Figure BDA0002647343120000042
respectively the center and the width of the membership function, g is an input number, and i is a fuzzy set number;
then fuzzy calculation is carried out to obtain the product of the membership value and the continuous product:
Figure BDA0002647343120000043
and finally, obtaining an output value at a full connection layer:
Figure BDA0002647343120000044
wherein ,
Figure BDA0002647343120000045
are fuzzy parameters.
Furthermore, the convolution network comprises a convolution layer and a pooling layer, and the multi-dimensional data of the noise signal is processed by convolution and pooling to form a higher-level sample characteristic matrix; and adding a pooling layer after at least every two convolution layers. The accuracy and the identification efficiency of the noise sample identification are maintained, and the size of the signal data is reduced.
Further, in step S1, the residual noise signal obtained by the error sensor is used as an input signal to enter the convolutional-fuzzy neural network identifier, and the trained network coefficient is used as an initial value of the control coefficient after the off-line identification of the secondary path model.
Furthermore, the output after off-line identification and the error signals e (n) together correct the parameters of the controller on line until the error signals e (n) reach the minimum value, and finally, multi-azimuth noise cancellation signals are output to obtain the best noise reduction effect.
In the scheme, the self-adaption and self-learning capabilities of the neural network are utilized, the convolution-fuzzy neural network is adopted to distinguish the object model off line, and then control is achieved. The network parameters obtained by off-line training are used as initial values of on-line learning, so that the on-line learning process of the network can be accelerated, and the network output approaches to the system output.
Further, the error signal e (n) is obtained by:
establishing an adaptive secondary path reversible model, x (n) collecting the incoming noise signal for the error sensor, and generating the expected signal through the secondary path
d(n)=x(n)*h(n)
(x denotes convolution), where h (n) is the secondary path transfer function.
Meanwhile, x (n) is input into a controller based on a convolution-fuzzy neural network algorithm, and a controller noise signal y (n) is output, and y (n) passes through an inverse function h of a secondary path-1(n) multiplying the sum by a correction value p (t.) to produce a noise cancellation signal
s(n)=y(n)*h-1(n)+p(.)
The correction value p is used for correcting the noise signal acquired by the original error sensor after the position sensor acquires the deflection displacement of the noise reduction target; sound pressure of residual noise signal x (n) acquired by error sensor:
Figure BDA0002647343120000051
in the formula :
Figure BDA0002647343120000052
is wave number, p0Static pressure of atmosphere, c0At sonic speed, the sound source intensity q is 4 π x2ux,uxThe vibration speed is adopted;
estimating and calculating the sound pressure value of the controlled area according to the deflection displacement d acquired by the position sensor:
Figure BDA0002647343120000053
a correction value obtained by correcting the original noise signal by the position information obtained by the position sensor
Figure BDA0002647343120000054
The system error signal is
e(n)=d(n)-s(n)。
Further, in step S4, the mean square of the error is taken as a performance function, and the controller parameter is corrected:
the full link layer output is y (n) ═ y1(n),y2(n)…,yi(n)]Y (n) is multiplied by the inverse function of the secondary path to obtain s (n), and the root mean square error of the system is
Figure BDA0002647343120000055
Calculating whether a minimization condition is met:
Figure BDA0002647343120000056
and (3) coefficient correction:
Figure BDA0002647343120000057
Figure BDA0002647343120000058
Figure BDA0002647343120000059
Figure BDA00026473431200000510
wherein α and β are learning rates.
Further, an error sensor acquires a residual noise signal, and noise signal characteristic depth extraction is carried out through the convolution layer; the pooling layer then performs dimension reduction on the extracted features; the fuzzy layer carries out fuzzy reasoning calculation on the signals after the dimensionality reduction; error minimization calculation; correcting parameters of the controller; judging whether the error value meets the minimization; if the error value meets the minimization condition, outputting a controller noise signal through a secondary path inverse function; if not, returning the fuzzy initialization of the data again; if the noise reduction target signal in the target area has deflection displacement, performing final supplementary correction on the controller noise signal through a correction value, and outputting a noise cancellation signal; if not, directly outputting the controller noise signal as a final noise cancellation signal.
Compared with the prior art, the invention has the beneficial effects that:
the noise control effect of the scheme is good. In particular, the amount of the solvent to be used,
(1) the active feedback control reduces the positioning limitation and the number limitation of the primary path error sensors, does not depend on reference signals, and avoids the problems of sound source positioning, collection and feedback in the primary path picking process.
(2) And an active feedback noise elimination system is adopted, a virtual reference signal is constructed, and a stable active noise reduction model based on a secondary path is established.
(3) Aiming at the global space of the vehicle, a plurality of error sensors and secondary sound sources are designed, the number, the angles, the positions and the installation modes of the error sensors and the secondary sound sources are reasonably and optimally set, and the noise control of the global space of the vehicle is realized.
(4) The position information of the noise reduction target is adopted as the supplementary correction of the noise signal of the controller, so that the noise reduction target has higher pertinence and better noise reduction effect.
(5) The convolution-fuzzy neural network algorithm is creatively used for identifying the secondary path model of ANC off line, and a very novel and effective tool is provided for identifying the nonlinear system; the scheme skillfully combines the convolution network and the fuzzy network, enhances the noise mapping processing capacity of the nonlinear system, improves the identification precision of the secondary path and simultaneously enlarges the noise frequency control bandwidth.
The scheme is particularly suitable for noise reduction of vehicles with wide sound field spaces, is also suitable for noise reduction of other spaces, and has important application value.
Drawings
Fig. 1 is a schematic diagram of an embodiment of an active noise control device.
FIG. 2 is a diagram of an embodiment secondary path inverse model architecture.
FIG. 3 is a diagram illustrating a convolutional-fuzzy neural network according to an embodiment.
FIG. 4 is a flowchart illustrating the control of the convolutional-fuzzy neural network according to an embodiment.
FIG. 5 is a schematic cross-sectional view of an embodiment sub-passage arrangement.
Fig. 6 is a schematic structural view of a sub-passage annular slide rail and a device mounting base according to an embodiment.
Fig. 7 is a schematic diagram of an embodiment active noise control device arrangement power supply.
FIG. 8 is a schematic diagram of an embodiment subpassage arrangement.
In the figure: the device comprises a vehicle body 1, a slide rail mechanism 2, a transverse slide rail 21, a longitudinal slide rail 22, a device mounting base 3, a nut 4, a bayonet 5, a power supply 6, an alternating current power supply line 7, an a1-an error sensor, a b1-bn loudspeaker and a c1-cn position sensor.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent; for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; "connected" herein may be either a direct connection or an indirect connection; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted. The specific meaning of the above terms in the present invention can be understood in specific cases to those skilled in the art. The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
The embodiment provides a convolution-fuzzy neural network method for actively controlling global spatial noise of a vehicle, which comprises the steps of arranging a plurality of secondary passages around a noise reduction area of the vehicle; the secondary path comprises an error sensor, a position sensor and a secondary sound source; and collecting residual noise signals of each secondary path, calculating an optimal solution of a filter coefficient, filtering the virtual reference signal by the optimal solution to obtain output signals of each secondary sound source, and thus obtaining a secondary path inverse model. A convolution-fuzzy neural network algorithm is used as a self-adaptive active noise control algorithm, off-line identification is carried out to obtain a secondary path model, a noise offset signal is output through the secondary path model, a position signal acquired by a position sensor corrects a noise signal output by a controller, and the precision of a noise reduction signal is improved.
In the specific implementation process, the error sensor collects background noise in a space field, collects data such as noise distribution and characteristics, calculates and analyzes the sound field, runs a processing control algorithm according to a signal processing result, calculates and generates a secondary sound source, destructively interferes with a noise source, and reduces noise. The error sensors are arranged according to the physical form of the neural network, noise signals in the noise-reduced area are collected in real time, and the reverse sound wave signals are adjusted in real time according to the noise reduction effect.
As shown in fig. 1, the noise controller controls the active noise elimination system by using feedback of a multi-stage sound source, the error sensor acquires a noise signal x (n) and transmits the noise signal x (n) to the reversible model of the secondary path, and parameters of the controller are continuously modified on line according to an error between a vector s (n) of an output signal of the secondary sound source and a vector d (n) of the output signal of the secondary path, so that the error signal e (n) is minimized, an optimal control quantity is generated, and the active noise elimination system is enabled to achieve an optimal noise elimination state. The error sensors are arranged in a neural network type structure, so that more noise signals can be acquired under the condition that the I/O interface is limited. Meanwhile, the noise reduction target position information acquired by the position sensor is used for tracking and correcting the noise signal output by the controller in real time, so that the noise reduction signal precision is improved.
As shown in FIG. 2, an adaptive secondary path reversible model is established, x (n) collects the incoming noise signal for the error sensor, and the desired signal is generated through the secondary path
d(n)=x(n)*h(n)
(x denotes convolution), where h (n) is the secondary path transfer function.
Meanwhile, x (n) is input into a controller based on a convolution-fuzzy neural network algorithm, a controller noise signal y (n) is output, and the y (n) is multiplied by a secondary path inverse function and then added with a correction value p (the.) to generate a noise cancellation signal
s(n)=y(n)*h-1(n)+p(.)
The correction value p is used for correcting the noise signal acquired by the original error sensor after the position sensor acquires the deflection displacement of the noise reduction target; sound pressure of residual noise signal x (n) acquired by error sensor:
Figure BDA0002647343120000081
in the formula :
Figure BDA0002647343120000082
is wave number, p0Static pressure of atmosphere, c0At the speed of sound, the intensity of the sound sourceq=4πx2ux,uxThe vibration speed is adopted;
estimating the sound pressure value of the noise reduction target in the controlled area according to the deflection displacement d acquired by the position sensor:
Figure BDA0002647343120000083
a correction value obtained by correcting the original noise signal by the position information obtained by the position sensor
Figure BDA0002647343120000084
The system error signal is
e(n)=d(n)-s(n)
In order to eliminate the influence of the secondary channel, the noise signal x (n) collected by the error sensor is firstly identified by a convolution-fuzzy neural network identifier (C-FNNI) off line, and then a new noise signal x' (n) is obtained and is corrected on line with the noise signal e (n) until the error signal e (n) reaches the minimum value.
The specific implementation mode adopts a convolution-fuzzy neural network algorithm as a self-adaptive active noise control algorithm in a secondary path inverse model, and the convolution-fuzzy neural network algorithm and the fuzzy neural network algorithm are jointly formed. The convolution network has translation invariance and can well adapt to the position change of a noise sample; and the method has the characteristic of weight sharing, obviously reduces the number of network parameters and improves the calculation speed. The fuzzy neural network is formed by combining a fuzzy system and a neural network, fuzzification processing and reasoning in the fuzzy system are represented by the neural network, input and output nodes of the neural network are used for representing input and output signals of the fuzzy system, and implicit nodes in the neural network are used for representing membership functions and fuzzy rules. The combination of the two enhances the nonlinear noise mapping processing capability, effectively solves the problem of fuzzy uncertainty of noise signals, improves the identification precision of noise samples, and simultaneously enlarges the noise frequency control bandwidth.
The embodiment simultaneously uses the convolution-fuzzy neural network for identifying the inverse model of the object, provides a novel and effective tool for identifying the nonlinear system, carries out off-line identification by utilizing the powerful nonlinear approximation capability of the neural network to the function to obtain the model of the secondary path, and finally outputs a multi-directional noise cancellation signal.
As shown in fig. 3, the convolutional-fuzzy neural network is composed of three parts, namely, a convolutional network, a fuzzy layer and a full connection layer, wherein the convolutional network comprises convolution and pooling, the fuzzy layer simulates human reasoning ability based on fuzzy concepts to carry out reasoning, and finally, the full connection layer outputs results. In the figure, the network input is a noise signal x (n) ═ x acquired by the error sensor1(n),x2(n)…,xt(n)](where t is the number of inputs) and the net output is yi(n)=[y1(n),y2(n)…,yi(n)]。
The convolution-fuzzy neural network carries out off-line identification to obtain a secondary path model, and meanwhile, the learning of the convolution-fuzzy neural network in the process of online correcting the parameters of the controller by the self-adaptive active noise control algorithm as the secondary path comprises the following steps:
s1, initializing a controller based on a convolution-fuzzy neural network algorithm;
s2, calculating input and output of each layer of the controller based on the convolution-fuzzy neural network algorithm;
first in the convolutional network (convolutional and pooling layers) through a series of convolutional and pooling exchanges:
Figure BDA0002647343120000091
wherein ,zg(n) the g-th convolutional layer output unit; omegatg(n) weights for all input units connected to the g-th output unit, bg(n) is the bias of the g convolutional layer output unit;
the relu function is selected as an activation function to obtain the output of a convolution network with a higher level as the input of a fuzzy layer:
og(n)=max(0,zg(n))
compared with the traditional convolution network, the number of convolution layers is increased in the network, more convolutions are allowed, and the depth extraction is carried out on the input signal characteristics; that is, the convolutional layer extracts the characteristics of the original data and trains and adjusts the parameters of the convolutional layer through convolution calculation. And the pooling layer then performs dimension reduction on the features extracted from the convolutional layer, compresses the number of data and network parameters, and reduces overfitting. The number of convolution layers and the training times are increased, and the extracted features, parameters and operations are increased; in order to save hardware computation resources, 2n (n is 1,2,3 … n is a positive integer) layers are specially set to be convolution layers, and then 1 layer of pooling layers are periodically inserted, so that the size of data can be reduced while the accuracy and the identification efficiency of noise sample identification are maintained.
Secondly, the fuzzy layer divides and converts the characteristic matrix obtained after convolution and pooling into proper membership function values according to the fuzzy degree and the membership function:
Figure BDA0002647343120000101
in the formula ,
Figure BDA0002647343120000102
respectively the center and the width of the membership function, g is an input number, and i is a fuzzy set number;
then fuzzy calculation is carried out to obtain the product of the membership value and the continuous product:
Figure BDA0002647343120000103
and finally, obtaining an output value at a full connection layer:
Figure BDA0002647343120000104
wherein ,
Figure BDA0002647343120000105
are fuzzy parameters.
S3, calculating the input and the output of a convolutional-fuzzy neural network identifier (C-FNNI), which are different from a controller algorithm, and calculating the weight and the offset in a convolutional network in the identifier algorithm; the center and width of membership function of the fuzzy layer and the fuzzy coefficient are fixed values. These parameters are the result of the offline recognition.
S4, taking the mean square of the error as a performance function, and correcting the parameters of the controller;
the full link layer output is y (n) ═ y1(n),y2(n)…,yi(n)]Y (n) is multiplied by the inverse function of the secondary path to obtain s (n), and the root mean square error of the system is
Figure BDA0002647343120000106
Calculating whether a minimization condition is met:
Figure BDA0002647343120000107
and (3) coefficient correction:
Figure BDA0002647343120000108
Figure BDA0002647343120000109
Figure BDA00026473431200001010
Figure BDA00026473431200001011
wherein α and β are learning rates.
S5, repeating the steps S2-S4 until the error minimization is met.
As shown in fig. 4, the flow of the convolutional-fuzzy neural network control algorithm of the present embodiment is as follows, including: an error sensor acquires a residual noise signal, and signal feature depth extraction is carried out through a convolution layer; the pooling layer reduces the dimension of the extracted features; fuzzy reasoning calculation of a fuzzy layer; error minimization calculation; correcting parameters of the controller; judging whether the error value meets the minimization; if the error value meets the minimization condition, outputting a controller noise signal through a secondary path inverse function; if not, returning the fuzzy initialization of the data again; if the noise reduction target signal in the target area has deflection displacement, performing final supplementary correction on the controller noise signal through a correction value, and outputting a noise cancellation signal; if not, directly outputting the controller noise signal as a final noise cancellation signal.
As a specific embodiment, the control method of the present embodiment may be implemented by using the following active noise control device. The apparatus includes a secondary path and a noise controller; the secondary path includes a plurality of error sensors for acquiring residual noise signals, a position sensor for acquiring position information of a noise reduction target in the target area, and a plurality of secondary sound sources for canceling noise. The error sensor acquires a residual noise signal and transmits the residual noise signal to the controller to provide an input signal, the controller sends a cancellation noise signal to the secondary sound source to output cancellation noise, and meanwhile, the position sensor acquires position information to be used as supplementary correction of the noise signal of the controller and tracks and adjusts the signal output by the controller in real time. It is understood that the noise controller may be a controller having a general arithmetic function.
In order to improve the active noise control level of the global space of the vehicle, the error sensor adopts an array type microphone. Noise signals of different positions and angles in the global space of the vehicle are collected through a plurality of microphones, and the error sensors acquire residual noise signals at different positions and form a neural network structure for determining the output of the secondary sound source.
As shown in fig. 5, a plurality of error sensors and a plurality of secondary sound sources are arranged along a transverse section of the train by a slide rail mechanism. When the number of the loudspeakers of the secondary sound source is odd, the loudspeakers are uniformly distributed on the annular track; and when the number of the loudspeakers is even, the loudspeakers are symmetrically arranged on the annular track. The number of the loudspeakers of the secondary sound sources and the angular positions are arranged, so that the secondary sound sources are further prevented from interfering with each other and being suppressed. When the number of the loudspeakers is set to be 4, the loudspeakers can be symmetrically arranged on a slide rail mechanism on the same transverse interface of the train from top to bottom and from left to right. As in fig. 1, the speaker b1, the speaker b2, the speaker b3, and the speaker b4 are symmetrically disposed.
As a specific implementation, the secondary path sensor in this embodiment further includes a position sensor. As shown in fig. 1, the error sensor a1 and the error sensor an are arranged symmetrically to each other, and the position sensor c1 and the position sensor cn are arranged symmetrically to each other. The position sensor functions to acquire position information of the noise reduction target in the target area, such as whether there is a passenger, and particularly whether there is a displacement of the head of the passenger. This information is the real-time adjustment controller output noise signal. The position sensor of the present embodiment may be a common infrared sensor or the like.
As shown in fig. 6, the slide rail mechanism 2 includes an endless track along a transverse section of the train body 1, and a device mounting base 3 attached to the endless track, and the error sensor, the position sensor, and the secondary sound source are mounted on the slide rail mechanism 2 through the device mounting base 3. And the annular track is adopted, so that the installation and adjustment of the error sensor, the position sensor and the secondary sound source are easy.
As shown in fig. 7, the slide rail mechanism 2 is provided with a stopper device for stopping the device mounting base 3. Specifically, each of the energizing members is connected to the power source 6 through an ac power supply line 7, and the ac power supply line 7 may be provided along the inside of the slide rail mechanism 2. The limiting device is fixed on the sliding rail mechanism 2 through the nut 4, and the screw rod is installed on the outer side of the sliding rail mechanism 2 through a hole in the bottom to correspond to the nut 4 on the installation base according to installation needs, so that the limiting device is prevented from moving.
Contain bayonet 5 on the device mount pad 3, but compatible installation error sensor, position sensor and secondary sound source fix different devices respectively through the inside screens of different shapes of bayonet to utilize nut 4 to be fixed in slide rail mechanism 2 with the mount pad on, avoided fixing device complicated and easy not hard up.
As shown in fig. 8, the slide rail mechanisms 2 are arranged along the transverse section of the train in a surrounding manner, and a plurality of groups are arranged in the length direction of the train; the plurality of error sensors, the plurality of position sensors and the plurality of secondary sound sources are arranged on a plurality of transverse sections of the train through a sliding rail mechanism. The accuracy of noise signal acquisition is ensured by arranging the position and the angle of the error sensor; tracking noise position information and performing supplementary correction through the arrangement of the position and the angle of the position sensor; by arranging the positions and angles of the secondary sound sources, the interference and suppression of the plurality of secondary sound sources with each other are avoided.
The embodiment is based on a secondary channel off-line identification control strategy, applies the self nonlinear approximation capability and self-learning and self-adapting capability of the neural network, and utilizes the convolution-fuzzy neural network to firstly carry out off-line identification on an object model and then realize control. The specific implementation mode overcomes the defects of large noise excitation sources in an open space and large control difficulty caused by multiple times of vehicle cascade coupling, is particularly suitable for noise reduction in a vehicle global space, and has a good noise reduction effect.
The positional relationships depicted in the drawings are for illustration purposes only and should not be construed as limiting the present patent. The above-described embodiments of the present invention are merely examples provided for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.

Claims (10)

1. A convolution-fuzzy neural network method for actively controlling global spatial noise of a vehicle is characterized in that a plurality of secondary passages are arranged around a noise reduction area of the vehicle; collecting noise residual signals of each secondary channel; a convolution-fuzzy neural network is adopted to perform off-line identification to obtain a secondary path model, meanwhile, the secondary path model is used as a self-adaptive active noise control algorithm of a secondary path to correct parameters of a controller on line, and finally, multi-directional noise cancellation signals are output.
2. The convolutional-fuzzy neural network method for actively controlling the global spatial noise of the vehicle as claimed in claim 1, wherein the convolutional-fuzzy neural network comprises a convolutional network, a fuzzy layer and a fully connected layer, the convolutional network comprises a convolutional layer and a pooling layer, the sample feature vector after passing through the convolutional network is subjected to fuzzy inference in the fuzzy layer and is trained in the fully connected layer, parameters are updated, and finally a controller noise signal is output.
3. The convolutional-fuzzy neural network method for actively controlling the global spatial noise of the vehicle as claimed in claim 2, wherein the convolutional-fuzzy neural network learning in the process of online modifying the parameters of the controller by using the adaptive active noise control algorithm of the convolutional-fuzzy neural network as the secondary path comprises the following steps:
s1, initializing a controller based on a convolution-fuzzy neural network algorithm;
s2, calculating input and output of each layer of the controller based on the convolution-fuzzy neural network algorithm;
s3, calculating the input and output of the convolutional-fuzzy neural network recognizer;
and S4, correcting the parameters of the controller.
4. The convolutional-fuzzy neural network method for actively controlling global spatial noise of a vehicle as claimed in claim 3, wherein the step S2 is specifically:
through a series of convolutions and pooling exchanges in a convolutional network:
Figure FDA0002647343110000011
wherein ,zg(n) the g-th convolutional layer output unit; omegatg(n) Weights for all input units connected to the g-th output unit, bg(n) is the bias of the g convolutional layer output unit;
the relu function is selected as an activation function to obtain the output of a convolution network with a higher level as the input of a fuzzy layer:
og(n)=max(0,zg(n))
the fuzzy layer divides and converts the characteristic matrix obtained after convolution and pooling into proper membership function values according to the fuzzy degree and the membership function:
Figure FDA0002647343110000012
in the formula ,
Figure FDA0002647343110000013
respectively the center and the width of the membership function, g is an input number, and i is a fuzzy set number;
then fuzzy calculation is carried out to obtain the product of the membership value and the continuous product:
Figure FDA0002647343110000021
and finally, obtaining an output value at a full connection layer:
Figure FDA0002647343110000022
wherein ,
Figure FDA0002647343110000023
are fuzzy parameters.
5. The convolutional-fuzzy neural network method for actively controlling global spatial noise of a vehicle as claimed in claim 2, wherein a pooling layer is added after at least two convolutional layers, and the noise data is characterized and reduced in dimension.
6. The convolutional-fuzzy neural network method for actively controlling global spatial noise of a vehicle as claimed in claim 3, wherein in step S1, the residual noise signal obtained by the error sensor is used as the input signal to enter the convolutional-fuzzy neural network identifier, and the trained network coefficients are used as the initial values of the controller coefficients after the off-line identification of the secondary path model.
7. The convolutional-fuzzy neural network method for actively controlling global spatial noise of a vehicle as claimed in claim 3, wherein the controller parameters are modified online with the error signals e (n) after off-line training until the error signals e (n) reach the minimum value, and finally multi-directional noise cancellation signals are outputted to obtain the best noise reduction effect.
8. The convolutional-fuzzy neural network method for actively controlling the global spatial noise of the vehicle as claimed in any one of claims 1 to 7, wherein said error signal e (n) is obtained by:
establishing an adaptive secondary path reversible model, x (n) collecting the incoming noise signal for the error sensor, and generating the expected signal through the secondary path
d(n)=x(n)*h(n)
(xvi denotes convolution), where h (n) is the secondary path transfer function;
meanwhile, x (n) is input into a controller based on a convolution-fuzzy neural network algorithm, and a controller noise signal y (n) is output, and y (n) passes through an inverse function h of a secondary path-1(n) multiplying and adding the correction value p (.)
s(n)=y(n)*h-1(n)+p(.)
The correction value p is used for correcting the noise signal acquired by the original error sensor after the position sensor tracks and reduces the noise and takes the deflection displacement; i.e. the sound pressure of the residual noise signal x (n) acquired by the error sensor
Figure FDA0002647343110000024
in the formula :
Figure FDA0002647343110000025
is wave number, p0Static pressure of atmosphere, c0At sonic speed, the sound source intensity q is 4 π x2ux,uxIn order to obtain the vibration speed, the vibration speed is set,
estimating the sound pressure value of the noise reduction target in the controlled area according to the deflection displacement d acquired by the position sensor
Figure FDA0002647343110000031
The correction value obtained by correcting the original noise signal by the position information obtained by the position sensor is
Figure FDA0002647343110000032
The system error signal is
e(n)=d(n)-s(n)。
9. The convolutional-fuzzy neural network method for actively controlling global spatial noise of a vehicle as claimed in any one of claims 1 to 7, wherein in said step S4, the mean square of the error is taken as the performance function, and the controller parameters are modified:
the full link layer output is y (n) ═ y1(n),y2(n)…,yi(n)]And y (n) is obtained by convolution calculation with the secondary path inverse function, and then the root mean square error of the control system is
Figure FDA0002647343110000033
Calculating whether a minimization condition is met:
Figure FDA0002647343110000034
and (3) coefficient correction:
Figure FDA0002647343110000035
Figure FDA0002647343110000036
Figure FDA0002647343110000037
Figure FDA0002647343110000038
wherein α and β are learning rates.
10. The convolutional-fuzzy neural network method for actively controlling the global spatial noise of the vehicle as claimed in any one of claims 1 to 7, wherein an error sensor acquires a residual noise signal, and the depth extraction of the noise signal feature is performed through a convolutional layer; the pooling layer then performs dimension reduction on the extracted features; the fuzzy layer carries out fuzzy reasoning calculation on the signals after the dimensionality reduction; error minimization calculation; correcting parameters of the controller; judging whether the error value meets the minimization; if the error value meets the minimization condition, outputting a controller noise signal through a secondary path inverse function; if not, returning the fuzzy initialization of the data again; if the noise reduction target signal in the target area has deflection displacement, performing final supplementary correction on the controller noise signal through a correction value, and outputting a noise cancellation signal; if not, directly outputting the controller noise signal as a final noise cancellation signal.
CN202010862334.5A 2020-08-24 2020-08-24 Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle Active CN111968613B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010862334.5A CN111968613B (en) 2020-08-24 2020-08-24 Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010862334.5A CN111968613B (en) 2020-08-24 2020-08-24 Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle

Publications (2)

Publication Number Publication Date
CN111968613A true CN111968613A (en) 2020-11-20
CN111968613B CN111968613B (en) 2023-09-19

Family

ID=73390215

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010862334.5A Active CN111968613B (en) 2020-08-24 2020-08-24 Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle

Country Status (1)

Country Link
CN (1) CN111968613B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112562623A (en) * 2020-11-24 2021-03-26 南京航空航天大学 Method for determining optimal position of active noise control loudspeaker
CN112580263A (en) * 2020-12-24 2021-03-30 湖南工业大学 Turbofan engine residual service life prediction method based on space-time feature fusion
WO2021084404A1 (en) * 2019-10-27 2021-05-06 Silentium Ltd. Apparatus, system and method of active noise control (anc) based on heating, ventilation and air conditioning (hvac) configuration
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
WO2023040025A1 (en) * 2021-09-15 2023-03-23 江南大学 Feedback-type active noise control system and method based on secondary channel online identification
CN115862581A (en) * 2023-02-10 2023-03-28 杭州兆华电子股份有限公司 Secondary elimination method and system for repeated pattern noise
US11688381B2 (en) 2021-09-15 2023-06-27 Jiangnan University Feedback active noise control system and strategy with online secondary-path modeling
US11935513B2 (en) 2019-10-27 2024-03-19 Silentium Ltd. Apparatus, system, and method of Active Acoustic Control (AAC)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06202672A (en) * 1993-01-06 1994-07-22 Nissan Motor Co Ltd Active control unit
US6137886A (en) * 1994-07-18 2000-10-24 Cooper Tire & Rubber Company Active vibration control method and apparatus
CN107240392A (en) * 2017-06-30 2017-10-10 邢优胜 A kind of armored vehicle cabin room noise Active Control Method and system
CN108538304A (en) * 2018-03-09 2018-09-14 华侨大学 Active Control System for Noise Cancelling in Passenger Compartment of Vehicle
CN109473120A (en) * 2018-11-14 2019-03-15 辽宁工程技术大学 A kind of abnormal sound signal recognition method based on convolutional neural networks
CN110598709A (en) * 2019-08-12 2019-12-20 北京智芯原动科技有限公司 Convolutional neural network training method and license plate recognition method and device
EP3614374A1 (en) * 2018-08-22 2020-02-26 recalm GmbH Noise reduction system and method for active compensation of noise
CN111091805A (en) * 2019-11-15 2020-05-01 佳禾智能科技股份有限公司 Feedback type noise reduction method based on neural network
CN111145715A (en) * 2019-12-27 2020-05-12 汉得利(常州)电子股份有限公司 Active noise control system and control method for fan
US10741162B1 (en) * 2019-07-02 2020-08-11 Harman International Industries, Incorporated Stored secondary path accuracy verification for vehicle-based active noise control systems

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06202672A (en) * 1993-01-06 1994-07-22 Nissan Motor Co Ltd Active control unit
US6137886A (en) * 1994-07-18 2000-10-24 Cooper Tire & Rubber Company Active vibration control method and apparatus
CN107240392A (en) * 2017-06-30 2017-10-10 邢优胜 A kind of armored vehicle cabin room noise Active Control Method and system
CN108538304A (en) * 2018-03-09 2018-09-14 华侨大学 Active Control System for Noise Cancelling in Passenger Compartment of Vehicle
EP3614374A1 (en) * 2018-08-22 2020-02-26 recalm GmbH Noise reduction system and method for active compensation of noise
CN109473120A (en) * 2018-11-14 2019-03-15 辽宁工程技术大学 A kind of abnormal sound signal recognition method based on convolutional neural networks
US10741162B1 (en) * 2019-07-02 2020-08-11 Harman International Industries, Incorporated Stored secondary path accuracy verification for vehicle-based active noise control systems
CN110598709A (en) * 2019-08-12 2019-12-20 北京智芯原动科技有限公司 Convolutional neural network training method and license plate recognition method and device
CN111091805A (en) * 2019-11-15 2020-05-01 佳禾智能科技股份有限公司 Feedback type noise reduction method based on neural network
CN111145715A (en) * 2019-12-27 2020-05-12 汉得利(常州)电子股份有限公司 Active noise control system and control method for fan

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ASSAF HOOGI: "Adaptive estimation of active controur parameters using convolutional neural networks and texture analysis" *
丁福臣: "车内噪声主动控制系统的研究及应用" *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021084404A1 (en) * 2019-10-27 2021-05-06 Silentium Ltd. Apparatus, system and method of active noise control (anc) based on heating, ventilation and air conditioning (hvac) configuration
US11034211B2 (en) 2019-10-27 2021-06-15 Silentium Ltd. Apparatus, system and method of active noise control (ANC) based on heating, ventilation and air conditioning (HVAC) configuration
US11935513B2 (en) 2019-10-27 2024-03-19 Silentium Ltd. Apparatus, system, and method of Active Acoustic Control (AAC)
CN112562623A (en) * 2020-11-24 2021-03-26 南京航空航天大学 Method for determining optimal position of active noise control loudspeaker
CN112580263A (en) * 2020-12-24 2021-03-30 湖南工业大学 Turbofan engine residual service life prediction method based on space-time feature fusion
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
WO2023040025A1 (en) * 2021-09-15 2023-03-23 江南大学 Feedback-type active noise control system and method based on secondary channel online identification
US11688381B2 (en) 2021-09-15 2023-06-27 Jiangnan University Feedback active noise control system and strategy with online secondary-path modeling
CN115862581A (en) * 2023-02-10 2023-03-28 杭州兆华电子股份有限公司 Secondary elimination method and system for repeated pattern noise

Also Published As

Publication number Publication date
CN111968613B (en) 2023-09-19

Similar Documents

Publication Publication Date Title
CN111968613A (en) Convolution-fuzzy neural network method for actively controlling global spatial noise of vehicle
CN111968614B (en) Active noise control device of vehicle global space based on convolution-fuzzy network
CN109747575B (en) Multi-mode in-vehicle sound quality optimization system based on order optimization
CN104821166A (en) Active noise control method based on particle swarm optimization algorithm
CN107791970A (en) Automobile active denoising method based on heuristic dynamic programming
CN107240392A (en) A kind of armored vehicle cabin room noise Active Control Method and system
CN109379652B (en) Earphone active noise control secondary channel off-line identification method
CN112017626A (en) Active noise reduction method for rail transit vehicle and cab
CN115171639A (en) Vehicle noise reduction method and system
CN116312448A (en) Reference sensing optimization method of road noise active control system
CN114582312B (en) Active control method and system for anti-interference adaptive road noise in vehicle
Botto et al. Intelligent active noise control applied to a laboratory railway coach model
Yang et al. Adaptive nonlinear ANC system based on time-domain signal reconstruction technology
CN114464157A (en) Active noise reduction method and device for vehicle and storage medium
Abouel-Seoud Active control analysis of passenger vehicle interior noise produced from tyre/road interaction
Mylonas et al. An extrapolation-based virtual sensing technique of improving the control performance of the FxLMS algorithm in a maritime environment
CN110908287B (en) Method for making active feed-forward control strategy for vibration sound radiation of aluminum profile of railway vehicle body
De Brett Implications of nonlinear suspension behaviour for feedforward control of road noise in cars
Pi et al. Experimental Performance Analysis of Multi-Channel Active Control System for Road Noise in Vehicles Using FXLMS Algorithm
Kuo et al. An integrated audio and active noise control system
CN111951776B (en) Active noise control method and device of train traction system based on fractional order variable step length
Chen et al. Objective evaluation of interior sound quality in passenger cars using artificial neural networks
CN116013238A (en) Active noise reduction algorithm of sensor without secondary path based on convolution-fuzzy neural network
JP3617079B2 (en) Active noise control device and active vibration control device
CN115482803A (en) Intelligent system parameter calibration method and system applied to in-vehicle road noise control

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
GR01 Patent grant
GR01 Patent grant