Apparatus for noise control and method thereof

Abstract

An apparatus for controlling noise and a method thereof, including: a memory storing computer executable instructions; and at least one processor accessing the memory to execute the instructions, where the at least one processor may obtain virtual road noise and noise weights by applying an error input signal at a target point in time to a trained noise control model, target road noise is obtained by applying the virtual road noise and the virtual road noise generated at a time point different from the target time point to the main path, and target control noise is obtained by applying a noise weight and a noise weight obtained at a time point different from the target time point to the auxiliary path, and performing noise control on the error input signal based on the target road noise and the target control noise.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Korean Patent Application No. 10-2023-0087866, filed on Jul. 6, 2013, which is hereby incorporated by reference in its entirety for all purposes. Technical Field

[0003] The present disclosure relates to an apparatus for controlling noise and a method thereof, and more particularly, to a technology for controlling vehicle interior noise generated from road noise. Background Art

[0004] When a vehicle travels on a road, wheels of the vehicle generate road noise. The road noise generated from the outside may be transmitted to passengers of the vehicle.

[0005] The road noise generated from the outside can be reduced to a certain level by attaching a sound absorbing material or a sound insulating material to the vehicle. However, the scheme of reducing noise in this way increases the weight of the vehicle and increases the price. Therefore, a technology of generating a sound wave with a phase opposite to the road noise by the superposition principle to reduce the noise can be used.

[0006] An important factor in the technology of reducing noise by the superposition principle in a vehicle is the position of the acceleration sensor. The vibration measured from the acceleration sensor should have a high correlation with the road noise. However, when the correlation between the vibration measured from the acceleration sensor and the road noise is poor, there is a limit to the occurrence of divergence, so it is necessary to develop a technology for overcoming this limit.

[0007] The information included in this background of the disclosure is only for enhancement of understanding of the general background of the disclosure and should not be taken as an acknowledgment or any form of suggestion that this information forms the prior art already known to a person skilled in the art. Summary of the invention

[0008] Various aspects of the present disclosure are directed to providing an apparatus for controlling noise and a method thereof, the apparatus being configured to train a noise control model based on removing interior noise of a vehicle by a predetermined amount by applying estimated road noise measured from an acceleration sensor installed in a vehicle to a feedforward active noise control (ANC) model.

[0009] Another aspect of the present disclosure provides an apparatus for controlling noise and a method thereof, the apparatus being configured to perform noise control on an error input signal based on virtual road noise and noise weight obtained by applying the error input signal at a target time point to a trained noise control model.

[0010] Another aspect of the present disclosure provides a device for controlling noise and a method thereof, the device being configured to obtain a first weight and a second weight related to noise removal at a target time point based on an error input signal at a time point different from the target time point and an error output signal at a time point different from the target time point.

[0011] The technical problems to be solved by the present disclosure are not limited to the above-mentioned problems, and any other technical problems not mentioned herein will be clearly understood by those skilled in the art to which the present disclosure belongs from the following description.

[0012] According to one aspect of the present invention, a device for controlling noise includes: a memory storing computer-executable instructions; and at least one processor accessing the memory to execute the instructions, wherein the at least one processor can obtain virtual road noise and noise weight by applying an error input signal at a target time point to a trained noise control model, obtain target road noise by applying the virtual road noise and the virtual road noise generated at a time point different from the target time point to a main path, obtain target controlled noise by applying the noise weight and the noise weight obtained at a time point different from the target time point to an auxiliary path, and perform noise control on the error input signal based on the target road noise and the target controlled noise.

[0013] According to an exemplary embodiment of the present invention, at least one processor may obtain a first weight and a second weight related to noise removal at a target time point based on an error input signal at a time point different from the target time point and an error output signal at a time point different from the target time point.

[0014] According to an exemplary embodiment of the present disclosure, at least one processor may obtain an estimated error signal by applying estimated road noise measured from an acceleration sensor installed in a vehicle to a feedforward active noise control (ANC) model, remove interior noise of the vehicle based on the estimated road noise and estimated weights, and generate a training input and a training output based on removing the interior noise by a predetermined noise amount, the training input including the estimated error signal, and in the training output, the estimated road noise and the estimated weights are paired.

[0015] According to an exemplary embodiment of the present disclosure, at least one processor may train a noise control model based on a training input and a training output.

[0016] According to an exemplary embodiment of the present disclosure, at least one processor may train a noise control model based on a training input and a training output, wherein a road sign representing each of at least one road condition and an estimated error signal are paired.

[0017] According to an exemplary embodiment of the present disclosure, at least one processor is configured to generate a first virtual road noise by applying a first weight to the virtual road noise, generate a second virtual road noise by applying a second weight to the virtual road noise obtained at a time point different from a target time point, and obtain a target road noise by applying the first virtual road noise and the second virtual road noise to a main path.

[0018] According to an exemplary embodiment of the present disclosure, at least one processor is configured to generate a first target weight by applying a first weight to a noise weight, generate a second target weight by applying a second weight to a noise weight obtained at a time point different from a target time point, and obtain a target controlled noise by applying the first target weight, the second target weight, and virtual road noise to an auxiliary path.

[0019] According to an exemplary embodiment of the present disclosure, at least one processor may obtain a third target weight from an adaptive filter at a target time point, and obtain target controlled noise by applying the first target weight, the second target weight, the third target weight, and the virtual road noise to the auxiliary path.

[0020] According to an exemplary embodiment of the present disclosure, at least one processor may obtain an error output signal based on the target road noise and the target control noise, and set the error output signal as the error input signal at a time point after the target time point.

[0021] According to an exemplary embodiment of the present disclosure, at least one processor may obtain an error output signal by subtracting the target control noise from the target road noise.

[0022] According to another aspect of the present disclosure, a method for controlling noise includes: obtaining virtual road noise and noise weight by applying an error input signal at a target time point to a trained noise control model; obtaining target road noise by applying virtual road noise and virtual road noise generated at a time point different from the target time point to a main path, obtaining target control noise by applying noise weight and noise weight obtained at a time point different from the target time point to a secondary path, and performing noise control on the error input signal based on the target road noise and the target control noise.

[0023] According to an exemplary embodiment of the present disclosure, the method may further include obtaining a first weight and a second weight related to noise removal at a target time point based on an error input signal at a time point different from the target time point and an error output signal at a time point different from the target time point.

[0024] According to an exemplary embodiment of the present disclosure, obtaining road noise and weights may include: obtaining an estimated error signal by applying estimated road noise measured from an acceleration sensor installed in a vehicle to a feedforward active noise control (ANC) model; removing the interior noise of the vehicle based on the estimated road noise and estimated weights based on removing the interior noise by a predetermined noise amount, and generating a training input and a training output, the training input including the estimated error signal, and in the training output, the estimated road noise is paired with the estimated weights.

[0025] According to an exemplary embodiment of the present disclosure, the method may further include training the noise control model based on the training input and the training output.

[0026] According to an exemplary embodiment of the present disclosure, the method may further include training the noise control model based on a training input and a training output, wherein a road sign representing each of the at least one road condition is paired with the estimated error signal.

[0027] According to an exemplary embodiment of the present disclosure, obtaining the target road noise may include: generating a first virtual road noise by applying a first weight to the virtual road noise; generating a second virtual road noise by applying a second weight to the virtual road noise obtained at a time point different from the target time point; and obtaining the target road noise by applying the first virtual road noise and the second virtual road noise to the main path.

[0028] According to an exemplary embodiment of the present disclosure, obtaining the target controlled noise may include: generating a first target weight by applying a first weight to a noise weight; generating a second target weight by applying a second weight to a noise weight obtained at a time point different from a target time point; and obtaining the target controlled noise by applying the first target weight, the second target weight, and virtual road noise to an auxiliary path.

[0029] According to an exemplary embodiment of the present disclosure, obtaining the target controlled noise may include: obtaining a third target weight from an adaptive filter at a target time point; and obtaining the target controlled noise by applying the first target weight, the second target weight, the third target weight, and the virtual road noise to the auxiliary path.

[0030] According to an exemplary embodiment of the present disclosure, the method may further include obtaining an error output signal based on the target road noise and the target control noise, and setting the error output signal as the error input signal at a time point after the target time point.

[0031] According to an exemplary embodiment of the present disclosure, obtaining the error output signal may include obtaining the error output signal by subtracting the target control noise from the target road noise.

[0032] The methods and apparatus of the present disclosure have other features and advantages that will be apparent from or set forth in more detail in the accompanying drawings and the following detailed description incorporated herein, which together serve to explain certain principles of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a block diagram illustrating an apparatus for controlling noise according to an exemplary embodiment of the present disclosure;

[0034] Figure 2 is a flow chart illustrating a method for controlling noise according to an exemplary embodiment of the present disclosure;

[0035] Figure 3 is a diagram illustrating an example of training a noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure;

[0036] Figure 4 is a flowchart illustrating an example of training a noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure;

[0037] Figure 5 is a diagram illustrating an example of controlling noise based on a trained noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure;

[0038] Figure 6 is a flowchart illustrating an example of controlling noise based on a trained noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure; and

[0039] Figure 7 is a block diagram illustrating a computing system for executing a method of controlling noise according to an exemplary embodiment of the present disclosure.

[0040] It will be appreciated that the drawings are not necessarily drawn to scale, and that the drawings present somewhat simplified representations of various features illustrating the basic principles of the present disclosure. The specific design features of the present disclosure as included herein (including, for example, specific dimensions, orientations, locations, and shapes) will be determined in part by the specific intended application and use environment.

[0041] In the drawings, reference numbers refer to the same or equivalent parts of the present disclosure throughout the several figures of the drawing. DETAILED DESCRIPTION

[0042] Reference will now be made in detail to various embodiments of the present disclosure, examples of which are shown in the accompanying drawings and described below. Although the present disclosure will be described in conjunction with exemplary embodiments of the present disclosure, it should be understood that this specification is not intended to limit the present disclosure to those exemplary embodiments of the present disclosure. On the other hand, the present disclosure is intended to cover not only the exemplary embodiments of the present disclosure, but also various replacements, modifications, equivalents and other embodiments that may be included in the spirit and scope of the present disclosure as defined by the appended claims.

[0043] Hereinafter, various exemplary embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. It should be noted that when a reference numeral is added to a component of each drawing, the same reference numeral is marked even if the same or equivalent components are shown in other drawings. In addition, when describing the exemplary embodiments of the present disclosure, when it is determined that the relevant known configuration or function interferes with the understanding of the exemplary embodiments of the present disclosure, the detailed description of the relevant known configuration or function will be omitted. Various embodiments of the present disclosure may be described with reference to the drawings. Therefore, a person of ordinary skill in the art will recognize that different modifications, equivalents and / or substitutions may be made to the different embodiments described herein without departing from the scope and spirit of the present disclosure. With respect to the description of the drawings, similar elements may be marked with similar reference numerals.

[0044] When describing the components of the present disclosure, terms such as first, second, A, B, (a), (b) etc. can be used in this article. These terms are only used to distinguish an element from other elements, and the nature, order, sequence and quantity of the element are not limited by these terms. In addition, unless otherwise defined, all terms (including technical or scientific terms) used in this article include the same meaning as the meaning generally understood by the technicians in the field to which the present disclosure belongs. The terms defined in the commonly used dictionary should be interpreted as having the meaning consistent with the context of the relevant technology, and should not be interpreted as ideal or too formal meanings, unless clearly defined in the specification of the present disclosure. For example, the terms used in this article, such as "first", "second", etc., can refer to various elements of various embodiments of the present disclosure, but are not limited to these elements. For example, "first user equipment" and "second user equipment" indicate different user equipment, regardless of order or priority. For example, without departing from the scope of the present disclosure, the first element can be referred to as the second element, and similarly, the second element can be referred to as the first element.

[0045] In the exemplary embodiments of the present disclosure included herein, the expressions “having”, “may have”, “including” and “comprising” or “may include” and “may include” used herein indicate the presence of corresponding features (e.g., elements such as values, functions, operations or components), but do not exclude the presence of additional features.

[0046] It will be understood that when an element (e.g., a first element) is referred to as being “operably or communicatively coupled / coupled to” or “connected to” another element (e.g., a second element), it may be directly coupled / coupled to or connected to another element (e.g., the second element) or may be present an intervening element (e.g., a third element). Conversely, when an element (e.g., a first element) is referred to as being “directly coupled / coupled to” or “directly connected to” another element (e.g., the second element), it will be understood that there are no intervening elements (e.g., a third element).

[0047] As used herein, the expression “configured to” may be used as, for example, an expression “suitable for,” “having the ability to,” “designed to,” “adapted to,” “made to,” or “able to,” depending on the circumstances.

[0048] The term "configured to" must not only mean "specifically designed to" in hardware. On the contrary, the statement "the device is configured to" may mean that the device is "capable of" operating with another device or other components. CPU, for example, "a processor configured to perform A, B, and C" may mean a dedicated processor (e.g., an embedded processor) for performing the corresponding operations or a general-purpose processor (e.g., a central processing unit (CPU) or an application processor) that can perform the corresponding operations by executing one or more software programs stored in a memory device. The terms used in this disclosure are used to describe the specific embodiments of the present disclosure and are not intended to limit the scope of the present disclosure. Unless otherwise specified, terms in the singular may include plural forms. All terms used herein, including technical or scientific terms, may include the same meanings commonly understood by those skilled in the art. It should be further understood that, unless so defined herein, in various embodiments of the present disclosure, the terms defined in the dictionary and commonly used should also be interpreted as being customary in the relevant art and not having an idealized or overly formal meaning. In some cases, even when the terms are defined in the exemplary embodiments of the present disclosure, they cannot be interpreted as excluding the embodiments of the present disclosure.

[0049] In the exemplary embodiments of the present disclosure included herein, the expressions "A or B", "at least one of A or / and B", or "one or more of A or / and B", etc. used herein may include any and all combinations of one or more of the relevant listed items. For example, the term "A or B", "at least one of A and B", or "at least one of A or B" may refer to all of the case (1) including at least one A, the case (2) including at least one B, and the case (3) including both at least one A and at least one B. In addition, as used herein, each of phrases such as "A or B", "at least one of A and B", "at least one of A or B", "A, B or C", "at least one of A, B and C", and "at least one of A, B or C" may include any or all possible combinations of the items enumerated together in the corresponding one phrase. Phrases such as "at least one of A, B, C, and any combination thereof" may include A or B or C or a combination thereof, such as AB or ABC.

[0050] In the following, reference will be made to Figures 1 to 7 Various exemplary embodiments of the present disclosure are described in detail.

[0051] Figure 1 is a block diagram illustrating an apparatus for controlling noise according to an exemplary embodiment of the present disclosure.

[0052] The apparatus 100 for controlling noise according to various exemplary embodiments of the present disclosure may include a processor 110 and a memory 120 for storing instructions 122. For example, the apparatus 100 for controlling noise may train a noise control model, and may perform noise control in a vehicle without an acceleration sensor based on the trained noise control model.

[0053] In conjunction with the training of the noise control model, the apparatus 100 for controlling noise may apply the estimated road noise measured from an acceleration sensor installed in the vehicle to a feedforward active noise control (ANC) model to obtain an estimated error signal and an estimated weight.

[0054] In this case, the feedforward ANC model may be a model different from the noise control model to be trained by the apparatus 100 for controlling noise. The apparatus 100 for controlling noise may remove the interior noise of the vehicle based on the estimated road noise and the estimated weight. The process of the apparatus 100 for controlling noise removing the interior noise of the vehicle may indicate the process of training the noise control model by the apparatus 100 for controlling noise.

[0055] For example, when removing the interior noise with a predetermined noise amount, the apparatus 100 for controlling noise may select an estimated road noise and an estimated weight that satisfy it from a plurality of estimated road noises and estimated weights. The apparatus 100 for controlling noise may use the selected estimated error signal as a training input and train a noise control model, which determines a training output in which the selected estimated road noise and the selected estimated weight are paired.

[0056] For reference, the process of training the noise control model in the apparatus 100 for controlling noise may be performed in the development stage before the mass production of the vehicle, but the embodiment is not limited thereto. For example, the apparatus 100 for controlling noise may additionally train the noise control model after the mass production of the vehicle. However, in the exemplary embodiment of the present disclosure, for the sake of convenience of description, the process of training the noise control model is mainly described as a process performed in the vehicle development stage. In addition, the following will refer to Figure 3 and Figure 4 A detailed description of training the noise control model is given.

[0057] Regarding performing noise control, the apparatus 100 for controlling noise may perform noise control in a vehicle without an acceleration sensor based on a trained noise control model.

[0058] For example, the apparatus 100 for controlling noise may obtain virtual road noise and noise weight by applying the error input signal at the target time point to the trained noise control model. As described above, the estimated road noise may be noise measured from an acceleration sensor provided in the vehicle. Alternatively, the virtual road noise may be virtual noise obtained from a trained noise control model. When there is no acceleration sensor in the vehicle, the apparatus 100 for controlling noise may obtain virtual road noise from a trained noise control model instead of estimating the road noise. The apparatus 100 for controlling noise may perform noise control on the error input signal by applying the virtual road noise and noise weight to the primary path and the secondary path, respectively. This will be described below. Figure 5 and Figure 6 A detailed description of performing noise control is described.

[0059] The processor 110 may execute software and may be configured to control at least one other component (e.g., hardware or software component) connected to the processor 110. The processor 110 may also perform various data processing or determinations. For example, the processor 110 may store virtual road noise, noise weight, target road noise, target control noise, and error input signal in the memory 120. The processor 110 may provide a user with a driving environment in which road noise (e.g., virtual road noise instead of estimated road noise) is removed by target control noise through a method for controlling noise described later.

[0060] For reference, the processor 110 may perform all operations performed by the apparatus 100 for controlling noise. Therefore, in an exemplary embodiment of the present disclosure, for convenience of description, operations performed by the apparatus 100 for controlling noise are mainly referred to as operations performed by the processor 110.

[0061] In addition, in the exemplary embodiment of the present disclosure, for the convenience of description, the processor 110 is mainly referred to as a single processor, but the embodiment is not limited thereto. For example, the apparatus 100 for controlling noise may include at least one processor. Each processor is configured to perform all operations related to the noise control operation.

[0062] The memory 120 may temporarily and / or permanently store various data and / or information required to perform noise control. For example, the memory 120 may store at least one of virtual road noise, noise weight, target road noise, target control noise, error input signal, or a combination thereof.

[0063] Figure 2 is a flowchart illustrating a method for controlling noise according to an exemplary embodiment of the present disclosure.

[0064] In operation S210, a device for controlling noise (eg, Figure 1 The apparatus 100 for controlling noise can obtain virtual road noise and noise weight by applying the error input signal to the trained noise control model at the target time point. For example, the target time point may indicate the time point at which the apparatus for controlling noise performs noise control. Although described later, in the exemplary embodiment of the present disclosure, it is mainly described that the target time point is the (n+1)th time point.

[0065] The error input signal may include a difference between the target road noise and the target control noise at a time point before the target time point (e.g., the nth time point). For example, the device for controlling noise may distinguish the target road noise from the target control noise at a time point before the target time point, and set the error input signal at the target time point. The device for controlling noise may perform noise control on the error input signal by applying the error input signal to a trained noise control model. In more detail, the device for controlling noise may perform noise control on a virtual road noise obtained by applying the error input signal to the trained noise control model.

[0066] The virtual road noise, which is noise generated by a trained noise control model, may represent noise virtually generated corresponding to noise caused by a vehicle traveling on a road (e.g., noise caused by friction between a real road surface and tires). For example, when an acceleration sensor is provided in a vehicle, the device for controlling noise may obtain actual road noise (e.g., estimated road noise) by vibration measured from the vehicle acceleration sensor. On the contrary, when the vehicle does not have any acceleration sensor, the device for controlling noise may obtain virtual road noise by using a trained noise control model. That is, the virtual road noise, which is noise different from the actual road noise, may be noise virtually generated by performing noise control (e.g., by a trained noise control model) when no acceleration sensor is present in the vehicle.

[0067] The noise weight (which is a weight generated by the trained noise control model) may represent a parameter related to the virtual road noise. As will be described later, the device for controlling noise may obtain a target control noise by applying the noise weight to the auxiliary path. When there is no acceleration sensor in the vehicle, the device for controlling noise may perform noise control based on the target control noise obtained by the noise weight.

[0068] In operation S220, the apparatus for controlling noise may obtain a target road noise by applying the virtual road noise and the virtual road noise generated at a time point different from the target time point to the main path.

[0069] The main path may represent a path in which noise is distorted by applying phenomena such as reflection, interference, and superposition of sound waves to virtual road noise. For example, virtual road noise, which is noise generated by a trained noise control model, is virtual noise representing noise generated between a vehicle tire and a vehicle suspension, and cannot be directly transmitted to a driver of the vehicle. In other words, the driver of the vehicle may only hear the noise generated by the tire reflected from the interior of the vehicle, the steering wheel, or surrounding objects. Therefore, the device for controlling noise may apply virtual road noise to the main path to obtain a target road noise audible to the driver of the vehicle.

[0070] The apparatus for controlling noise may apply the virtual road noise at the target time point and the virtual road noise at a time point different from the target time point to the main path to obtain the target road noise. Figure 5 For reference, in the exemplary embodiment of the present disclosure, for the convenience of description, the time point different from the target time point and before the target time point is mainly described. However, the time point different from the target time point is not limited thereto, and may be a time point after the target time point.

[0071] In operation S230, the apparatus for controlling noise may obtain a target controlled noise by applying the noise weight and the noise weight obtained at a time point different from the target time point to the auxiliary path.

[0072] The secondary path may represent a path in which noise is distorted by applying phenomena such as reflection, interference, and superposition of anti-phase noise (e.g., anti-phase noise of virtual road noise) output from a vehicle speaker. For example, a device for controlling noise may be configured to generate anti-phase noise of virtual road noise by using virtual road noise and noise weights. The device for controlling noise may output anti-phase noise through a vehicle speaker. However, the anti-phase noise output by the vehicle speaker is noise that cannot be directly transmitted to the driver of the vehicle. In other words, the driver of the vehicle may only hear the noise generated by the speaker and reflected by the interior of the vehicle, the steering wheel, or surrounding objects. Therefore, the device for controlling noise may apply noise weights to the secondary path to obtain a target control noise audible to the driver of the vehicle.

[0073] The target controlled noise may represent the inverted noise of the virtual road noise. However, the target controlled noise is not limited thereto and may represent a plurality of noises (e.g., modified virtual road noise) for controlling the virtual road noise. For reference, in an exemplary embodiment of the present disclosure, for ease of description, the target controlled noise is mainly referred to as the inverted noise of the virtual road noise, that is, the noise to which the noise weight is applied to the virtual road noise.

[0074] The apparatus for controlling noise may apply the noise weight at the target time point and the noise weight at a time point different from the target time point to the auxiliary path to obtain the target controlled noise. Figure 5 Describe the details.

[0075] In operation S240 , the apparatus for controlling noise may perform noise control on the error input signal based on the target road noise and the target control noise.

[0076] For example, the device for controlling noise may obtain virtual road noise by applying an error input signal to a noise control model, the error input signal being the difference between a target road noise at a time point before a target time point and a target control noise at a time point before the target time point. The device for controlling noise may obtain the target control noise through an auxiliary path to control the obtained virtual road noise. The device for controlling noise may be configured to control noise in the vehicle according to the error input signal at a target time point based on the target control noise.

[0077] Figure 3 is a diagram illustrating an example of training a noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure.

[0078] In operation S300, a device for controlling noise (eg, Figure 1 The apparatus 100 for controlling noise may be configured to measure the estimated road noise (e.g., Figure 3 ) is applied to the feed-forward ANC model to obtain an estimated error signal (e.g., Figure 3 is shown as e(n)).

[0079] The apparatus for controlling noise may apply the estimated road noise to the main path based on the signal measured from the acceleration sensor, and apply the estimated weight (e.g., Figure 3 The device for controlling noise may obtain an estimated error signal by applying the estimated road noise and the estimated weight to the primary path and the secondary path, respectively. For reference, the value obtained by applying the estimated road noise to the primary path (e.g., Figure 3 d(n)) and the value obtained by applying the estimated weights to the secondary path (e.g., Figure 3 As shown in , it is the difference between y(n)) to obtain the estimated error signal.

[0080] The device for controlling noise may remove the interior noise of the vehicle based on the estimated road noise and the estimated weight. In other words, the estimated road noise measured from the acceleration sensor may be generated as the interior noise of the vehicle. The device for controlling noise may remove the interior noise of the vehicle using the anti-phase noise based on the estimated road noise and the estimated weight.

[0081] In operation S310, the apparatus for controlling noise may be configured to generate a training input and a training output based on removing the internal noise with a predetermined noise amount, the training input including the estimated error signal, and in the training output, the estimated road noise is paired with the estimated weight. For reference, in an exemplary embodiment of the present disclosure, for ease of description, it is mainly described that the predetermined noise is 3 dB, but the embodiment is not limited thereto.

[0082] In operation S320, the apparatus for controlling noise may train a noise control model based on a training input and a training output. In more detail, the apparatus for controlling noise may train a noise control model based on a training input and a training output, wherein in the training input, a road sign representing each road condition in at least one road condition is paired with an estimated error signal.

[0083] As an exemplary embodiment of the present disclosure, the noise control model may include a neural network. The neural network may include multiple layers, each layer including multiple nodes. The node may include a node value determined based on an activation function. A node of any layer may be connected to a node of another layer (e.g., another node) via a link (e.g., a connection edge) including a connection weight. The node value of the node may be propagated to other nodes via the link. In the inference operation of the neural network, the node value may be propagated forward from the previous layer to the next layer.

[0084] For example, in the noise control model, the forward propagation operation may represent an operation of propagating node values ​​based on input data in a direction from an input layer to an output layer of the noise control model. That is, the node value of the corresponding node may be propagated (e.g., forward propagated) to a node of a next layer connected to the node (e.g., a next node) through a connection edge. For example, a node may receive a value weighted by a connection weight from a previous node (e.g., a plurality of nodes) connected through a connection edge.

[0085] For example, the nodes of the input layer may include 129 nodes. The training input may represent an input in which a road sign representing each of at least one road condition is paired with an estimated error signal. Road signs may include signs on highways, general roads, unpaved roads, roads including child protection areas, national highways, and bridges. Road signs may be represented in one dimension. In other words, road signs may be applied to one node of the input layer. On the other hand, the estimated error signal may include 128 different frequency components, wherein the noise is transformed by a fast Fourier transform (FFT). In other words, the estimated error signal may be applied to 128 nodes of the input layer.

[0086] For example, the nodes of the output layer may include 256 nodes. The training output may represent an output of an estimated road noise paired with an estimated weight. The estimated road noise may include 128 different frequency components, where the noise is transformed by a fast Fourier transform. In addition, the estimated weight may include weights of 128 different frequency components, where the noise is transformed by a fast Fourier transform. In other words, the estimated road noise and the estimated weight may be output from the 256 nodes of the output layer.

[0087] The node value of the node may be determined based on applying the activation function to the sum of weighted values ​​received from previous nodes (e.g., a weighted sum). The parameters of the neural network may include the connection weights described above as an example. The parameters of the neural network may be updated so that the objective function value described later changes in a target direction (e.g., a direction in which loss is minimized).

[0088] The trained noise control model may refer to a model trained by machine learning, and in detail, may be a trained machine learning model that outputs a training output (e.g., road noise and a weight for road noise) from a training input (error signal).

[0089] The machine learning model (eg, a trained noise control model) may be generated by machine learning. For example, the learning algorithm may include supervised learning, unsupervised learning, semi-supervised learning, or enhanced learning, but the implementation is not limited to the above examples.

[0090] The machine learning model may include multiple artificial neural network layers. In detail, the trained noise control model may include a shared layer and multiple classifier layers (e.g., task-specific layers) connected to the shared layer, the shared layer including at least one convolution operation. The artificial neural network may include at least one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q network, or a combination thereof, but the implementation is not limited to the above examples.

[0091] In supervised learning, the above-mentioned machine learning model can be trained based on training data including a pair of training inputs and training outputs mapped to the corresponding training inputs. For example, the machine learning model can be trained to output training outputs from training inputs. During learning, the machine learning model can be configured to generate a temporary output in response to the training input, and can be trained to minimize the loss between the temporary output and the training output (e.g., the training target). During the learning process, the parameters of the machine learning model (e.g., the connection weights between nodes / layers in a neural network) can be updated according to the loss. For example, such learning can be performed in the device for controlling noise itself in which the machine learning model is executed, or can be performed by a separate server. The fully trained machine learning model (e.g., a trained noise control model) can be stored in a memory (e.g., Figure 1 in the memory 120).

[0092] Figure 4 is a flowchart illustrating an example of training a noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure.

[0093] In operation S410, a device for controlling noise (eg, Figure 1 The device 100 for controlling noise can be set for the vehicle to travel in various road environments. For example, the device for controlling noise can be set for the vehicle to travel on a highway, a general road, an unpaved road, a road including a child protection area, a national highway, and a bridge.

[0094] In operation S420, the apparatus for controlling noise may obtain estimated road noise by setting an acceleration sensor at an optimal position in the vehicle. For example, the acceleration sensor may be set at an optimal position in the vehicle based on the condition that the vehicle is traveling on a highway, a general road, an unpaved road, a road including a child protection area, a national highway, and a bridge.

[0095] In operation S430, the apparatus for controlling noise may apply the estimated road noise obtained from the acceleration sensor to the feedforward ANC model. The apparatus for controlling noise may be configured to generate anti-phase noise with respect to the estimated road noise by applying the estimated road noise to the feedforward ANC model.

[0096] In operation S440, the apparatus for controlling noise may remove the estimated road noise by outputting the generated reverse phase noise through a speaker provided in the vehicle.

[0097] In operation S450, the apparatus for controlling noise may measure the change of the estimated road noise controlled by the anti-phase noise (e.g., the removal of the estimated road noise). In the instant case, the apparatus for controlling noise may be configured to determine whether the effect of removing the estimated road noise is greater than or equal to the predetermined noise (e.g., 3dB). When the effect of removing the estimated road noise is less than or equal to the predetermined noise, the apparatus for controlling noise may perform operation S430 again.

[0098] In operation S460, when the effect of removing the estimated road noise is greater than or equal to the predetermined noise, the apparatus for controlling noise may be configured to generate a training input and a training output, in which a road sign representing each of the at least one road condition is paired with the estimated error signal, and in which the estimated road noise is paired with the estimated weight. In the instant case, the training input and the training output may represent a training set of noises satisfying the effect of removing the estimated road noise being greater than or equal to the predetermined noise.

[0099] In operation S470, the apparatus for controlling noise may train a noise control model based on the generated training input and training output. For example, the apparatus for controlling noise may train the noise control model by applying the estimated error signal to the noise control model for each of at least one road condition to output estimated road noise and estimated weights. The apparatus for controlling noise may perform noise control by obtaining virtual road noise without estimating road noise based on the trained noise control model.

[0100] Figure 5is a diagram illustrating an example of controlling noise based on a trained noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure.

[0101] Devices for controlling noise (e.g. Figure 1 The apparatus 100 for controlling noise may be configured to generate a signal at a target time point (e.g., at a time point) through the headrest microphone 500. Figure 5 The error input signal is measured at the (n+1)th time point (shown in FIG. Figure 5 The error input signal at the target time point may represent the difference between the target road noise at a previous time point different from the target time point (e.g., the nth time point) and the target control noise at a previous time point different from the target time point of the target road noise. The apparatus for controlling noise may apply the measured error input signal to the noise control model 510 to obtain the virtual road noise (e.g., at Figure 5 ) and the noise weights (e.g., Figure 5 is shown as w(n+1)).

[0102] The apparatus for controlling noise may perform noise control by applying the first weight and the second weight to each of the virtual road noise and the noise weight, respectively.

[0103] The first weight may be based on an error input signal at a time point different from the target time point and an error output signal at a time point different from the target time point, indicating a weight related to noise removal at the target time point. Similarly, the second weight may be based on an error input signal at a time point different from the target time point and an error output signal at a time point different from the target time point, indicating a weight opposite to noise removal at the target time point. The first weight and the second weight may be expressed as the following equation 1.

[0104] [Equation 1]

[0105]

[0106] Wherein α may represent a first weight, and β may represent a second weight. In addition, e(n) may represent an error input signal at a time point different from a target time point, and e′(n) may represent an error output signal at a time point different from the target time point.

[0107] The first weight may be a weight related to how much noise removal is performed, and may be a weight indicating the predictive performance of the trained noise control model. For example, the first weight may include a value close to 1' due to the difference between e'(n) and e(n) (e.g., when noise removal is not good). Conversely, the first weight may include a value close to 0 (zero)' due to the difference between e'(n) and e(n) (e.g., when noise removal is successful). When the predictive performance of the noise control model is good, the first weight may include a value close to 0 (zero)' because e'(n) is close to 0 (zero)'.

[0108] The apparatus for controlling noise may apply virtual road noise to the main path 520 to obtain a target road noise (e.g., Figure 5 For example, the apparatus for controlling noise may obtain the target road noise by applying the first virtual road noise and the second virtual road noise to the main path 520 .

[0109] For example, the apparatus for controlling noise may be configured to generate a first virtual road noise by applying a first weight to the virtual road noise, and generate a second virtual road noise by applying a second weight to the virtual road noise obtained at a time point different from the target time point. The value applied to the main path 520 by the first virtual road noise and the second virtual road noise may be expressed as the following equation 2.

[0110] [Equation 2]

[0111] x′(n+1)=αx(n+1)+βx(n)

[0112] Wherein αx(n+1) may represent a first virtual road noise obtained by applying a first weight to the virtual road noise, and βx(n) may represent a second virtual road noise obtained by applying a second weight to a virtual road noise obtained at a time point different from a target time point. In addition, x′(n+1) may indicate a value applied to the main path 520 as a result of summing the first virtual road noise and the second virtual road noise.

[0113] The apparatus for controlling noise may obtain target road noise by applying x′(n+1) to the main path 520. For example, the target road noise may be expressed as Equation 3 below.

[0114] [Equation 3]

[0115] d(n+1) = main path h{αx(n+1)+βx(n)}

[0116] Where αx(n+1)+βx(n) may represent a value applied to the main path 520 , and d(n+1) may represent a target road noise.

[0117] Considering various reflection environments of the vehicle (e.g., environments where sound waves overlap), the device for controlling noise may apply x'(n+1) to the main path 520 to obtain the target road noise. In other words, the target road noise may be noise audible to the driver of the vehicle because the noise generated from the tires is reflected by the interior of the vehicle, the steering wheel, or surrounding objects. For reference, in an exemplary embodiment of the present disclosure, x'(n+1) may be applied to the main path 520 and the target road noise may be transmitted to the driver of the vehicle through the vehicle speaker.

[0118] When noise removal is successful (e.g., when α in Equation 1 is close to 0 (zero)), x′(n+1) may be close to the value of virtual road noise obtained at a time point different from the target time point. In other words, when noise removal is successful, x′(n+1) as a value applied to the main path 520 may represent virtual road noise obtained at a time point different from the target time point, rather than virtual road noise at the target time point.

[0119] In contrast, when noise removal is unsuccessful (e.g., when α in Equation 1 is close to 1'), x'(n+1) may be close to the virtual road noise value at the target time point. In other words, when noise removal is unsuccessful, x'(n+1) as a value applied to the main path 520 may represent a virtual road noise obtained at a time point different from the target time point, rather than the virtual road noise at the target time point.

[0120] The apparatus for controlling noise may apply the first target weight and the second target weight to the auxiliary path 530 to obtain a target controlled noise (e.g., Figure 5 For example, the apparatus for controlling noise may be configured to generate a first target weight by applying a first weight to a noise weight. In addition, the apparatus for controlling noise may be configured to generate a second target weight by applying a second weight to a noise weight obtained at a time point different from the target time point.

[0121] However, the method of obtaining the target controlled noise is not limited thereto. For example, the device for controlling noise may obtain the target controlled noise by applying the first target weight, the second target weight, the third target weight, and the modified virtual road noise (e.g., x′(n+1) in Equation 2) to the auxiliary path 530. The value applied to the auxiliary path 530 by the first target weight, the second target weight, and the third target weight may be expressed as the following Equation 4.

[0122] [Equation 4]

[0123] w′(n+1)=αw(n+1)+βw(n)+γW LMS (n+1)

[0124] Wherein αw(n+1) may represent a first target weight obtained by applying a first weight to a noise weight, βw(n) may represent a second target weight obtained by applying a second weight to a noise weight obtained at a time point different from a target time point, and γW LMS (n+1) may denote a third target weight updated by the LMS 540, and w'(n+1) may denote a value applied to the auxiliary path 530, which is a result of adding the first target weight to the third target weight.

[0125] For example, LMS 540 is an adaptive filter and may represent a filter updated to minimize the loss of the error output signal. For reference, γ, which is a third target weight of a parameter of LMS 540, may represent a parameter used by tuning the mixed value. In the exemplary embodiment of the present disclosure, for ease of description, γ is mainly described as a parameter with a value between 0.15 and 0.30.

[0126] The apparatus for controlling noise may obtain target controlled noise by applying x'(n+1) and w'(n+1) to the auxiliary path 530. The value applied to the auxiliary path 530 may be expressed as Equation 5 below.

[0127] [Equation 5]

[0128] {αx(n+1)+βx(n)}×{αw(n+1)+βw(n)+γW LMS (n+1)}

[0129] Where αx(n+1)+βx(n) is the result of adding the first virtual road noise and the second virtual road noise, which can represent x′(n+1) applied to the main path 520, and αw(n+1)+βw(n)+γW LMS (n+1) may represent w′(n+1) which is a result of adding the first target weight, the second target weight, and the third target weight.

[0130] In other words, the apparatus for controlling noise can be configured to calculate the value of {αx(n+1)+βx(n)}×{αw(n+1)+βw(n)+γW based on the first target weight, the second target weight, the third target weight, and the virtual road noise. LMS (n+1)} is applied to the auxiliary path 530 to obtain the target control noise. For example, the target control noise can be expressed as the following equation 6.

[0131] [Equation 6]

[0132] y(n+1)=auxiliary path{{αx(n+1)+βx(n)}×{αw(n+1)+βw(n)+γWLMS (n+1)}}

[0133] Among them {αx(n+1)+βx(n)}×{αw(n+1)+βw(n)+γW LMS y(n+1)} may represent a value applied to the auxiliary path 530, and y(n+1) may represent a target control noise.

[0134] The target controlled noise may be an inverted noise of the virtual road noise, and may represent an inverted noise of the virtual road noise to which a target weight is applied. In addition, in order to remove the target road noise (e.g., noise generated by the interior of the vehicle, the steering wheel, or the surrounding objects reflecting from the tires, and which can be audibly heard by the driver of the vehicle), the device for controlling noise may output the target controlled noise through a speaker of the vehicle.

[0135] The apparatus for controlling noise may obtain an error output signal based on the target road noise and the target control noise. For example, the apparatus for controlling noise may obtain the error output signal by subtracting the target control noise from the target road noise. When the target road noise is similar to the target control noise (e.g., when the noise heard in the ears of the driver of the vehicle is similar to the anti-phase noise signal reproduced inversely through the speaker), the error output signal may include a value close to 0 (zero).

[0136] The apparatus for controlling noise may set the error output signal as the error input signal at a time point after the target time point. The error input signal at the time point after the target time point may be expressed as the following Equation 7.

[0137] [Equation 7]

[0138] e(n+2)=e′(n+1)=|d(n+1)-y(n+1)|

[0139] Wherein |d(n+1)-y(n+1)| may represent the absolute value of the difference between the target road noise and the target control noise, e′(n+1) may represent the error output signal at the target time point (e.g., the (n+1)th time point), and e(n+2) may represent the error input signal at the time point after the target time point (e.g., the (n+2)th time point). The apparatus for controlling noise may perform noise control according to the target road noise and the target control noise at the time point after the target time point by applying the error input signal at the time point after the target time point to the trained noise control model.

[0140] Figure 6 is a flowchart illustrating an example of controlling noise based on a trained noise control model in an apparatus for controlling noise according to an exemplary embodiment of the present disclosure.

[0141] In operation S610, a device for controlling noise (eg, Figure 1 The apparatus 100 for controlling noise may measure an error input signal through a microphone located near a headrest inside the vehicle. The error input signal may be the difference between a target road noise at a time point before the target time point and a target control noise at a time point before the target time point.

[0142] In operation S620, the apparatus for controlling noise may apply the error input signal to the trained noise control model. By applying the error input signal to the trained noise control model, the apparatus for controlling noise may perform noise control without obtaining road noise through an acceleration sensor of the vehicle.

[0143] In operation S630, the apparatus for controlling noise may obtain virtual road noise and noise weight by applying the error input signal to the trained noise control model. The apparatus for controlling noise may obtain target road noise by applying the virtual road noise to the main path. The vehicle driver may audibly identify the noise of the vehicle through the target road noise. Differently, the apparatus for controlling noise may obtain the target controlled noise by applying the result of applying the noise weight to the virtual road noise to the auxiliary path. The driver of the vehicle may audibly identify the removal of the vehicle noise from the target controlled noise through the target controlled noise output from the vehicle speaker.

[0144] In operation S640, the apparatus for controlling noise may obtain an error output signal. The apparatus for controlling noise may obtain the error output signal based on the difference between the target road noise and the target control noise. The error output signal may be set to the error input signal at a time point after the target time point.

[0145] In operation S650, the apparatus for controlling noise may apply the error output signal to the LMS to update the LMS so that the loss of the error output signal is minimized. In addition, the apparatus for controlling noise may obtain a third target weight (e.g., Figure 5 Equation 3).

[0146] Figure 7 is a block diagram illustrating a computing system that executes a method for controlling noise according to an exemplary embodiment of the present disclosure.

[0147] See also Figure 7 The computing system 1000 executing the method for controlling noise may include at least one processor 1100 , a memory 1300 , a user interface input device 1400 , a user interface output device 1500 , a storage device 1600 , and a network interface 1700 connected via a bus 1200 .

[0148] The processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in the memory 1300 and / or the storage device 1600. The memory 1300 and the storage device 1600 may include various volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) and a random access memory (RAM).

[0149] Therefore, the process of the method or algorithm described in conjunction with the exemplary embodiments of the present disclosure may be directly implemented by hardware, software modules, or a combination thereof executed by the processor 1100. The software module may reside in a storage medium (i.e., the memory 1300 and / or the storage device 1600), such as a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a solid state drive (SSD), a detachable disk, or a CD-ROM.

[0150] An exemplary storage medium is coupled to the processor 1100, and the processor 1100 can read information from the storage medium and can write information in the storage medium. In another approach, the storage medium can be integrated with the processor 1100. The processor and the storage medium can reside in an application specific integrated circuit (ASIC). The ASIC can reside in a user terminal. In another approach, the processor and the storage medium can reside in a user terminal as separate components.

[0151] Although embodiments of the present disclosure have been described for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the disclosure.

[0152] The above exemplary embodiments can be implemented by hardware elements, software elements and / or their combinations. For example, the devices and components shown in the exemplary embodiments of the present disclosure can be implemented in one or more general-purpose computers or special-purpose computers (such as processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable gate arrays (FPGAs), programmable logic units (PLUs), microprocessors, or any device that can execute instructions and responses). The processing unit can implement an operating system (OS) or a plurality of software applications running on an OS. In addition, the processing unit can access, store, manipulate, process, and generate data in response to the execution of software. It should be understood by those skilled in the art that, although a single processing unit can be shown for ease of understanding, the processing unit may include a plurality of processing elements and / or a variety of types of processing elements. For example, the processing unit may include a plurality of processors or a processor and a controller. Moreover, the processing unit may include different processing configurations, such as parallel processors.

[0153] Software may include computer programs, codes, instructions, or one or more combinations thereof, and may configure a processing unit to operate in a desired manner or may control a processing unit independently or collectively. Software and / or data may be embodied permanently or temporarily in any type of machine, component, physical device, virtual device, computer storage medium, or unit, or in a transmission signal wave that is interpreted by a processing unit or provides instructions or data to a processing unit. Software may be distributed among computer systems connected via a network and may be stored or executed in a decentralized manner. Software and data may be recorded in one or more computer-readable storage media.

[0154] The method of the above exemplary embodiment conceived according to the present disclosure can be implemented using program instructions, which can be executed by various computer devices and can be recorded in a computer-readable medium. The medium can also be included alone or in combination with program instructions, data files, data structures, etc. The program instructions recorded in the medium can be specially designed and configured for the exemplary embodiments conceived by the present disclosure, or are known and available to technicians in the field of computer software. Computer-readable media include magnetic media such as hard disks, floppy disks, and tapes; optical media, such as compact disk-read only memory (CD-ROM) disks and digital versatile disks (DVDs); magneto-optical media, such as floppy disks; and hardware devices specially configured to store and execute program instructions, such as read-only memory (ROM), random access memory (RAM), flash memory, etc. Program instructions include both machine codes such as those generated by a compiler and higher-level codes that can be executed by a computer using an interpreter.

[0155] The described hardware devices may be configured to act as one or more software modules in order to perform the operations of the above-described exemplary embodiments of the present disclosure concepts, or vice versa.

[0156] Effects of the apparatus for controlling noise and method thereof according to exemplary embodiments will be described below.

[0157] According to an embodiment, a noise control model may be trained based on removing interior noise of a vehicle by a predetermined amount, thereby improving road noise estimation performance.

[0158] Furthermore, according to an embodiment, noise control of a vehicle may be performed without attaching an acceleration sensor to the vehicle based on virtual road noise and noise weight obtained by applying an error input signal at a target time point to a trained noise control model.

[0159] Furthermore, according to the embodiment, vehicle noise can be controlled more accurately based on the first weight and the second weight related to noise removal at a target time point without attaching an acceleration sensor to the vehicle.

[0160] Furthermore, various effects directly or indirectly understood by the present disclosure can be provided.

[0161] Although several exemplary embodiments have been shown and described with reference to the accompanying drawings, it will be apparent to those skilled in the art that various modifications and variations may be made from the foregoing description. For example, adequate effects may be achieved even when the above-described processes and methods are performed in a different order than described above, and / or the above-described elements (such as systems, structures, devices, or circuits) are combined or coupled in a different form and mode than described above, or replaced or switched with other components or equivalents.

[0162] Thus, it is intended that the present disclosure cover other implementations and other embodiments of the present disclosure provided such implementations and other embodiments come within the scope of the appended claims and their equivalents.

[0163] For ease of explanation and accurate definition of the appended claims, the terms "upper", "lower", "inner", "outer", "upward", "downward", "upward", "downward", "front", "back", "inner", "outer", "inward", "outward", "interior", "exterior", "inner", "exterior", "forward", and "rearward" are used to describe features of the exemplary embodiments with reference to the locations of such features shown in the drawings. It should be further understood that the term "connected" or its derivatives refer to both direct and indirect connections.

[0164] In this specification, unless otherwise stated, a singular expression includes a plural expression unless the context clearly indicates otherwise.

[0165] In the exemplary embodiments of the present disclosure, it should be understood that terms such as “including” or “having” are intended to specify the presence of features, quantities, steps, operations, elements, parts, or a combination thereof described in the specification, and do not exclude the possibility of adding or existing one or more other features, quantities, steps, operations, elements, parts, or a combination thereof.

[0166] For the purpose of illustration and description, the foregoing descriptions of specific exemplary embodiments of the present disclosure have been presented. They are not intended to be exhaustive or to limit the present disclosure to the precise form disclosed, and it is apparent that many modifications and variations are feasible in light of the above teachings. In order to illustrate certain principles of the present invention and their practical applications, exemplary embodiments have been selected and described to enable other persons skilled in the art to carry out and utilize various exemplary embodiments of the present disclosure and various substitutions and modifications thereof. The scope of the present disclosure is intended to be limited by the appended claims and their equivalents.

Claims

1. A device for controlling noise, the device comprising: a memory configured to store computer executable instructions; as well as at least one processor operatively connected to the memory and configured to access the memory to execute the instructions, Wherein, the at least one processor is configured to: The virtual road noise and the noise weight are obtained by applying the error input signal at the target time point to the trained noise control model; obtaining a target road noise by applying the virtual road noise and a virtual road noise generated at a time point different from the target time point to a main path; obtaining a target controlled noise by applying the noise weight and a noise weight obtained at a time point different from the target time point to an auxiliary path; and Noise control is performed on the error input signal based on the target road noise and the target control noise.

2. The device according to claim 1, wherein: The at least one processor is further configured to: Based on an error input signal at a time point different from the target time point and an error output signal at a time point different from the target time point, a first weight and a second weight related to noise removal at the target time point are obtained.

3. The device according to claim 1, wherein: The at least one processor is further configured to: obtaining an estimated error signal by applying estimated road noise measured from an acceleration sensor installed in the vehicle to a feed-forward active noise control model; removing interior noise of the vehicle based on the estimated road noise and the estimated weight; as well as Based on removing the interior noise by a predetermined noise amount, a training input and a training output are generated, the training input including the estimated error signal, and in the training output, the estimated road noise is paired with the estimation weights.

4. The device according to claim 3, wherein: The at least one processor is further configured to: The noise control model is trained based on the training input and the training output.

5. The device according to claim 4, wherein: The at least one processor is further configured to: The noise control model is trained based on the training input and the training output, wherein a road sign representing each of at least one road condition is paired with the estimated error signal.

6. The device according to claim 2, wherein: The at least one processor is further configured to: generating a first virtual road noise by applying the first weight to the virtual road noise; generating a second virtual road noise by applying the second weight to a virtual road noise obtained at a time point different from the target time point; as well as The target road noise is obtained by applying the first virtual road noise and the second virtual road noise to the main path.

7. The device according to claim 2, wherein: The at least one processor is further configured to: generating a first target weight by applying the first weight to the noise weight; generating a second target weight by applying the second weight to a noise weight obtained at a time point different from the target time point; as well as The target controlled noise is obtained by applying the first target weight, the second target weight, and the virtual road noise to the auxiliary path.

8. The device according to claim 7, wherein: The at least one processor is further configured to: Obtaining a third target weight from the adaptive filter at the target time point; and The target controlled noise is obtained by applying the first target weight, the second target weight, the third target weight, and the virtual road noise to the auxiliary path.

9. The device according to claim 1, wherein: The at least one processor is further configured to: obtaining an error output signal based on the target road noise and the target control noise; and The error output signal is set to be the error input signal at a time point after the target time point.

10. The device according to claim 9, wherein: The at least one processor is further configured to: The error output signal is obtained by subtracting the target control noise from the target road noise.

11. A method for controlling noise, the method comprising: Obtaining, by at least one processor, a virtual road noise and a noise weight by applying an error input signal at a target time point to a trained noise control model; obtaining, by the at least one processor, a target road noise by applying the virtual road noise and a virtual road noise generated at a time point different from the target time point to a main path; obtaining, by the at least one processor, a target controlled noise by applying the noise weight and a noise weight obtained at a time point different from the target time point to a secondary path; as well as Noise control is performed, by the at least one processor, on the error input signal based on the target road noise and the target control noise.

12. The method according to claim 11, further comprising: The at least one processor obtains a first weight and a second weight related to noise removal at the target time point based on an error input signal at a time point different from the target time point and an error output signal at a time point different from the target time point.

13. The method according to claim 11, wherein: Obtaining the road noise and the weight comprises: obtaining an estimated error signal by applying estimated road noise measured from an acceleration sensor installed in the vehicle to a feed-forward active noise control model; removing interior noise of the vehicle based on the estimated road noise and the estimated weight; and Based on removing the interior noise by a predetermined noise amount, a training input and a training output are generated, the training input including the estimated error signal, and in the training output, the estimated road noise is paired with the estimation weights.

14. The method according to claim 13, further comprising: The noise control model is trained, by the at least one processor, based on the training input and the training output.

15. The method according to claim 14, further comprising: The noise control model is trained, by the at least one processor, based on the training input and the training output, wherein a road sign representing each of at least one road condition is paired with the estimated error signal.

16. The method according to claim 12, wherein: Obtaining the target road noise includes: generating a first virtual road noise by applying the first weight to the virtual road noise; generating a second virtual road noise by applying the second weight to a virtual road noise obtained at a time point different from the target time point; and The target road noise is obtained by applying the first virtual road noise and the second virtual road noise to the main path.

17. The method according to claim 12, wherein: Acquiring the target control noise includes: generating a first target weight by applying the first weight to the noise weight; generating a second target weight by applying the second weight to a noise weight obtained at a time point different from the target time point; and The target controlled noise is obtained by applying the first target weight, the second target weight, and the virtual road noise to the secondary path.

18. The method according to claim 17, wherein: Acquiring the target control noise includes: Obtaining a third target weight from the adaptive filter at the target time point; and The target controlled noise is obtained by applying the first target weight, the second target weight, the third target weight, and the virtual road noise to the secondary path.

19. The method according to claim 11, further comprising: obtaining, by the at least one processor, an error output signal based on the target road noise and the target control noise; as well as The at least one processor sets the error output signal to be the error input signal at a time point after the target time point.

20. The method according to claim 19, wherein: Obtaining the error output signal includes: The error output signal is obtained, by the at least one processor, by subtracting the target control noise from the target road noise.

Images