TWI741816B - An abnormal sound testing device for a vehicle and method thereof - Google Patents

Abstract

The present invention relates an abnormal sound testing device for a vehicle that primarily utilizing a radio module to receive a sound signal in a range from the inside of the vehicle. The processor accords to a plurality of vehicle sound frequency data to compare a sound frequency feature point in a plurality of sound sources when the processor processing the sound signal and determines the plurality of sound frequency features whether conforming with a plurality of abnormal sound frequency. Then the processor generates a warning signal when at least one sound frequency feature point is conformed to any one of the abnormal sound frequency. Leading to a warning device receives and outputs the warning signal. Accordingly, the abnormal sound testing device of the present invention provides the vehicle whether the abnormal sound occurs based on the processor determining, further outputs in real-time to the driver for early reminding, and reducing the probability of incident occurrence thereby.

Description

Vehicle body abnormal sound detection device and method

The invention relates to the technical field of abnormal sound detection, in particular to a car body abnormal sound detection device and a method thereof that receive a sound signal in a car body and perform related processing on the sound signal to determine whether a warning signal is generated.

According to this, when driving in a moving vehicle environment, it is often because the sound of the car body is too small or the sound of playing music is too loud. Therefore, if the driver cannot immediately know that there may be a problem, it may be There is a risk of related accidents due to damage to the car body.

In this way, the prior art has invented a device for detecting abnormal sound, which is installed on the drum brake device to use the relevant sensor to receive external sound, and after capturing and amplifying it based on the sensed sound signal, Then the output action is performed according to the warning device, so that the driver can hear and sense the sound signal.

However, if only the above-mentioned sensors are used to capture and amplify, since a variety of sounds (such as music or chat sounds) are generally received in the car body, if the received sound signal is not separated from the sound source When comparing data and data, it is difficult to correctly determine whether the received sound signal is abnormal sound.

Therefore, in the current technology, there is an urgent need for a warning sound source that can effectively determine whether the received sound signal is an abnormal sound, and then output the warning sound source generated after the determination by the warning device, so as to improve the problems existing in the prior art.

The object of the present invention is to provide a vehicle body abnormal sound detection device, which mainly receives sound signals from the vehicle body, and then the processing module compares multiple vehicle body audio data and judges whether the audio feature points in the multiple sound sources match If there are a plurality of abnormal sound frequencies, when at least one audio feature point matches any abnormal sound frequency, the processing module correspondingly generates a warning signal so that the warning device can receive and output the warning signal. By using the processing module to determine whether the car body produces abnormal sounds, it is output to the driver in real time, and the driver will be reminded in advance to reduce the probability of accidents.

For the purpose of the above disclosure, the present invention provides a vehicle body abnormal sound detection device, which is installed in a vehicle body, and includes: a radio module, which is configured to receive a sound signal from the vehicle body; A processing module connected to the radio module and configured to receive the sound signal and separate a plurality of sound sources in the sound signal, and compare one of the sound sources based on the plurality of car body audio data Audio feature points, and use a deep learning algorithm to determine whether the audio feature points match a plurality of abnormal sound frequencies. When the processing module determines that at least one of the audio feature points conforms to any abnormal sound frequency, the processing The module generates a warning signal; and a warning device, which is connected to the processing module and is set to receive and output the warning signal.

Preferably, the vehicle body abnormal sound detection device further includes: a register connected to the processing module to store the abnormal sound frequencies, the sound sources, the vehicle body audio data, and the audio frequencies The characteristic point, the warning signal, or a combination of two or more of them.

Preferably, the vehicle body abnormal sound detection device further includes: an abnormal sound setting module connected to the processing module and an external electronic device, and the abnormal sound setting module is set to receive from the external electronic device Acquire the car body audio data, the abnormal sound audio frequencies, or both, and transmit the car body audio data, the abnormal sound audio frequencies, or both to the processing module, or the The abnormal sound setting module provides a setting interface to receive the car body audio data, the abnormal sound audio or both set by the user.

Preferably, the vehicle body abnormal sound detection device further includes: an activation module connected to the radio module and the processing module, the activation module being configured to receive the sound signal from the radio module , And determine the sound frequency in the sound signal according to an activation threshold to determine whether to activate the processing module. When the sound signal exceeds the activation threshold, the activation module activates the processing module. When the activation threshold is exceeded, the activation module continues to receive another audio signal.

Preferably, the activation threshold is such that the activation module determines whether the sound frequency in the sound signal exceeds the audio frequency range of the car body according to the stored at least one car body audio frequency, if the sound frequency in the sound signal exceeds the audio frequency range of the car body When the audio frequency range of the car body audio, the activation module determines that the audio signal exceeds the activation threshold to activate the processing module, and when the sound frequency in the audio signal does not exceed the audio frequency range of the car body audio, The activation module determines that the audio signal does not exceed the activation threshold, so as to continue to receive another audio signal.

Preferably, when the activation module starts the processing module, the activation module stops operating, and when the processing module stops operating, the activation module starts to determine the content of the sound signal according to the activation threshold The frequency of the sound to determine whether to activate the processing module.

Preferably, the processing module is connected with a vehicle control device to obtain a control signal from the vehicle control device, and the processing module executes activation or deactivation of the radio module according to a command in the control signal; or The processing module executes and adjusts the output volume of the warning device according to a command in the control signal.

Preferably, the processing module is further connected to a component detection device to transmit the warning signal to the component detection device. When the component detection device receives the warning signal, the component detection device performs a detection operation to Detect whether each component in the vehicle body conforms to an abnormal state data.

Preferably, the warning device includes a display module, a lamp, a speaker, or any combination of two or more thereof.

Another object of the present invention is to provide a vehicle body abnormal sound detection device, which mainly receives sound signals from the vehicle body, and the reprocessing module compares multiple vehicle body audio data and determines whether the audio feature points in the multiple sound sources are It conforms to a plurality of abnormal sound frequencies. When at least one audio feature point matches any abnormal sound frequency, the processing module correspondingly generates a warning signal so that the warning device can receive and output the warning signal. By using the processing module to determine whether the car body produces abnormal sounds, it is output to the driver in real time, and the driver will be reminded in advance to reduce the probability of accidents.

In order to achieve another objective of the above disclosure, the present invention provides a vehicle body abnormal sound detection method applied to the above-mentioned vehicle body abnormal sound detection device.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, detailed descriptions are given below in conjunction with the specific embodiments listed in the drawings.

The advantages, features, and technical methods of the present invention will be described in more detail with reference to the exemplary embodiments and the accompanying drawings to make it easier to understand, and the present invention can be implemented in different forms, so it should not be understood as the present invention It is limited to the embodiments set forth here. On the contrary, for those with ordinary knowledge in the technical field, the provided embodiments will make this disclosure more thorough, comprehensive and complete to convey the scope of the present invention, and the present invention will only It is defined by the scope of the attached patent application.

In addition, the terms "including" and/or "including" refer to the existence of the features, regions, wholes, steps, operations, elements, and/or components, but do not exclude one or more other features, regions, wholes, steps, operations , The presence or addition of elements, components, and/or combinations thereof.

In order to make it easier for your reviewer to understand the content of the present invention and the effects that can be achieved, the specific embodiments listed in the drawings are described in detail as follows:

Please refer to FIG. 1, which is a schematic diagram of the arrangement of the components of the present invention. As shown in the figure, the present invention installs a vehicle body abnormal sound detection device 100 on a vehicle body, and it is mainly connected to a radio module 10 and a processing module 20 in the vehicle body abnormal sound detection device 100. And a warning device 30. The vehicle body abnormal sound detection device 100 can be mainly a plastic shell or other modules that can accommodate related modules in the vehicle body abnormal sound detection device 100 to provide a container for protecting these modules. The vehicle body abnormal sound detection device 100 The device 100 can be installed on the vehicle body. More specifically, the vehicle body abnormal sound detection device 100 can be installed on a position inside the vehicle body.

The radio module 10 may specifically be a microphone or other related devices that can receive external sound. In order to enable the present invention to effectively receive the sound signal to be analyzed and processed from the interior of the vehicle body, it is disclosed here The radio module 10 is limited to sense a sound signal 11 in the vehicle body. More specifically, when the radio module 10 senses and receives the sound signal 11, it is mainly transmitted through the radio module 10. A sound wave is provided inside the vehicle body, and when the sound wave provided by the radio module 10 vibrates due to the sound waves generated by the components inside the vehicle body, the radio module 10 can determine that the sound wave has been sensed. The external sound wave in the vehicle body (that is, the sound wave outside the radio module), and the sound signal 11 is generated according to the sensed vibration wave pattern.

The processing module 20 can specifically be a central processing unit or other data processing device. When the processing module 20 is connected to the radio module 10, it can receive the data received by the radio module 10 The audio signal 11, at this time, the processing module 20 will first separate the multiple audio sources 21 in the audio signal 11 (for example, the sounds of various parts in the vehicle body), and compare the multiple audio data 22 based on the vehicle body. An audio feature point 211 of 21 of these sound sources, when each of the sound sources 21 is separated, in order to effectively distinguish the difference of the sound sources 21.

After the audio feature points 211 of the sound sources 21 are compared, the processing module 20 further uses a deep learning algorithm to determine whether the audio feature points 211 match a plurality of abnormal sound audio frequencies 23, and the cars The body audio data 22 and the abnormal sound audio frequencies 23 can be obtained through a period of sound learning or the data stored in the original register 50. When the processing module 10 determines that the abnormal sound audio frequency corresponds to any one of the abnormal sound frequencies. When at least one of the audio feature points 211 in 23, the processing module 10 will correspondingly generate a warning signal 24. Among them, the car body audio data 22 mainly refers to the normal sound or audio frequency of various parts in the car body (such as engine or gearbox, etc.), and the abnormal sound audio frequency 23 can be that the parts of the car body do not conform to the car body. The audio data of the audio data 22.

The warning device 30 may include a display module, a lamp, a speaker, a combination of any two or more thereof, or any related device that can output the warning signal 24. When the warning signal 24 is generated, the warning device 30 can receive the warning signal 24 by connecting with the processing module 20, and output the warning signal 24 to the driver listener (such as a speaker) and display damaged Components (such as a display screen) or use warning lights (such as lamps) to inform the driver. In addition, the processing module 20 can further display the direction in which the sound signal 11 is received by the radio module 10 The location of the part. For example, when the sound signal 11 is received from the radio module 10 in the vehicle body, when the processing module 20 completes the action of generating the warning signal 24, it can use a speaker or a display screen to output the warning signal 24. When the warning device 30 is a speaker, it can be presented in the form of warning sound or voice. If the warning device 30 is a display screen, the damaged parts can be displayed on the display in the form of images or graphics. On the screen, or if the warning device 30 is a lamp, when the warning signal 24 is received, it can output, for example, flashing lights, etc., to show that, of course, the above-mentioned components (display modules, lamps and speakers) The way of outputting the warning signal 24 does not conflict. Therefore, when the warning device 30 is a combination of a speaker and a display screen, it can simultaneously perform the functions of outputting a warning sound (or voice) and displaying damaged parts.

Wherein, the register 50 is connected with the processing module 20 to store the abnormal sounds 23, the sound sources 21, the car body audio data 22, the audio feature points 211, the warning signal 24 or A combination of the two or more.

Please refer to FIG. 2, which is a schematic diagram of the component arrangement relationship of the abnormal sound setting module of the present invention. As shown in the figure, the present invention may further include an abnormal sound setting module 40. Due to different vehicle models or vehicle types, the sound frequencies emitted by each component will be different. Therefore, when used to determine abnormal sound data, It must be updated, calculated or learned. In this way, the car body audio data 22 and the abnormal sound audio 23 usually need to be learned through a period of time of audio or voiceprint or the original register 50 Set the stored data (to complete the learning calculation data). Therefore, in this embodiment, the abnormal sound setting module 40 is connected to the processing module 10 and an external electronic device 60, and the abnormal sound setting module 40 is configured to obtain the cars from the external electronic device 60. The body audio data 22, the abnormal sound audio 23, or both, and the car body audio data 22, the abnormal sound audio 23, or both are transmitted to the processing module 10, or The abnormal sound setting module 40 provides a setting interface 41 to receive the car body audio data 22, the abnormal sound audio 23 or both set by the user, and then through the setting of the abnormal sound data, the original The invention can effectively make relevant judgments.

Please refer to FIG. 3 again, which is a schematic diagram of the activation module configuration of the present invention. As shown in the figure, in order to effectively save power, the vehicle body abnormal sound detection device of the present invention may further include an activation module 70, which is set in the vehicle body abnormal sound detection device 100 and interacts with the processing module. The group 20 is connected to the radio module 10. The activation module 70 receives the sound signal 11 from the radio module 10, and determines the sound frequency in the sound signal 11 according to the activation threshold 61 and the sound signal 11 To determine whether to activate the processing module 20, when the sound signal 11 exceeds the activation threshold 71, the activation module 70 activates the processing module 20, when the sound signal does not exceed the activation threshold 71, the activation module The group 70 continues to receive another audio signal. Wherein, the activation threshold 71 is that the activation module 70 determines whether the sound frequency in the sound signal 11 exceeds the audio frequency range of the car body audio data 22 according to at least one of the stored audio data 22 of the car body. When the sound frequency in the signal 11 exceeds the audio frequency range of the vehicle body audio data 22, the activation module 70 determines that the sound signal 11 exceeds the activation threshold 71 to activate the processing module 20, and when the sound signal 11 is When the audio frequency of the vehicle body audio data 22 does not exceed the audio frequency range, the activation module 70 determines that the audio signal 11 does not exceed the activation threshold 71 to continue to receive another audio signal 11.

When the processing module 20 has been activated by the activation module 70, the activation module 70 stops operating, and when the processing module 20 stops operating, the activation module 70 starts to determine according to the activation threshold 71 The sound frequency in the sound signal 11 determines whether to activate the processing module 20 or not. In this way, the activation module 70 is provided to effectively provide the power-saving function of the vehicle body abnormal sound detection device of the present invention.

Please refer to FIG. 4 again, which is a schematic diagram of the component arrangement relationship of the vehicle control device of the present invention. As shown in the figure, the processing module 20 can be further connected to a vehicle control device 200 in the vehicle body to receive a control signal 201 from the vehicle control device 200, and control according to at least one command in the control signal 201 The radio module 10 or the warning device 30. For example, when the driver wants to set the radio module 10 (for example, activate or deactivate the radio module), the vehicle control device 200 can be used to generate the related control signal 201, so as to demodulate the radio module 10 through the processing module 20. Perform related actions after the control signal 201, or when the driver wants to adjust the output volume of the warning device 30, the control signal 201 generated by the vehicle control device 200 can also be used to perform related operations through the processing module 20

Please refer to FIG. 5 again, which is a schematic diagram of the component arrangement relationship of the component inspection device of the present invention. As shown in the figure, the present invention may further include a component detection device 80. Due to different vehicle models or vehicle types, the arrangement positions of the components will also be different. Therefore, when the processing module 20 generates the warning signal 24 , The component detection device 80 will receive the warning signal 24. At this time, the component detection device 80 can receive the sound signal 11 according to the direction, the audio frequency, or the difference between the sound frequency and the abnormal sound 23 of the radio module 10 A detection operation is performed on data such as the comparison result, and then a detection operation is performed to determine whether each component in the vehicle body conforms to an abnormal state data 81 (that is, whether it exceeds the detection result of the vehicle body audio data 22).

Please refer to FIG. 6 again, which is a flowchart of the steps of the present invention. As shown in the figure, the present invention can be based on the following main steps to achieve the function of car body abnormal sound detection, which includes:

S01: The radio module receives sound signals within the range of the car body;

S02: The processing module separates multiple audio sources in the audio signal;

S03: The processing module compares the audio feature points in the audio sources based on multiple car body audio data;

S04: The processing module uses a deep learning algorithm to determine whether the audio feature points conform to a plurality of abnormal sound frequencies;

S05: When the processing module determines that at least one audio feature point is consistent with any abnormal sound frequency, the processing module generates a warning signal accordingly;

S06: The warning device receives and outputs a warning signal.

In this way, the present invention can determine whether the vehicle body produces abnormal noise according to the processing module, and then output it to the driver in real time, so as to remind the driver in advance to reduce the probability of accidents.

The disclosure in this case is a preferred embodiment, and any partial changes or modifications that are derived from the technical ideas of the case and can be easily inferred by those who are familiar with the art will not deviate from the scope of the patent right of the case.

In summary, regardless of the purpose, means, and effects of this case, it is showing its technical characteristics that are very different from conventional knowledge, and its first invention is suitable for practical use, and it is also in line with the patent requirements of the invention. Granting patents as soon as possible will benefit the society and feel the virtues.

100: Vehicle body abnormal sound detection device 200: Vehicle control device 201: Control signal 10: Radio module 11: Sound signal 20: Processing module 21: Sound source 211: Audio feature points 22: Car body audio data 23: Abnormal sound frequency 24: Warning signal 30: Warning device 40: Abnormal sound setting module 41: Setting interface 50: register 60: External electronic device 70: Activate the module 71: Activation threshold 80: Component inspection device 81: Abnormal status data S01-S06: Step flow

Figure 1 is a schematic diagram of the arrangement of the components of the present invention; FIG. 2 is a schematic diagram of the component arrangement relationship of the abnormal sound setting module of the present invention; Figure 3 is a schematic diagram of the activation module configuration of the present invention; Figure 4 is a schematic diagram of the component arrangement relationship of the vehicle control device of the present invention; FIG. 5 is a schematic diagram of the component arrangement relationship of the component inspection device of the present invention; Figure 6 is a flow chart of the steps of the present invention.

100: Vehicle body abnormal sound detection device

10: Radio module

11: Sound signal

20: Processing module

21: Sound source

211: Audio feature points

22: Car body audio data

23: Abnormal sound frequency

24: Warning signal

30: Warning device

50: register

Claims (9)

A vehicle body abnormal sound detection device, which is set in a vehicle body, and includes: a radio module, which is set to receive a sound signal from the interior of the vehicle body; and a processing module, which is connected to the radio module , And is set to receive the audio signal and separate multiple audio sources in the audio signal, and compare an audio feature point in these audio sources based on the multiple car body audio data, and use a deep learning algorithm to determine Whether the audio feature points conform to a plurality of abnormal sound frequencies, when the processing module determines that at least one of the audio feature points conforms to any of the abnormal sound frequencies, the processing module generates a warning signal; a warning device, It is connected to the processing module and is set to receive and output the warning signal; and an activation module is connected to the radio module and the processing module, and the activation module is set to receive and output the alarm signal from the radio module Receive the sound signal, and determine the sound frequency in the sound signal according to an activation threshold to determine whether to activate the processing module. When the sound signal exceeds the activation threshold, the activation module activates the processing module. When the sound signal does not exceed the activation threshold, the activation module continues to receive another sound signal. The vehicle body abnormal sound detection device according to claim 1, further comprising: a register connected with the processing module to store the abnormal sound frequencies, the sound sources, the vehicle body audio data, and the These audio feature points, the warning signal, or a combination of two or more of them. The vehicle body abnormal sound detection device according to claim 1, further comprising: a abnormal sound setting module connected to the processing module and an external electronic device, and the abnormal sound setting module is set to be connected from the external The electronic device acquires these car body sounds Frequency data, the abnormal sound audio frequencies, or both, and the car body audio data, the abnormal sound audio frequencies, or both are transmitted to the processing module, or the abnormal sound setting module A setting interface is provided to receive the car body audio data, the abnormal sound audio or both set by the user. The car body abnormal sound detection device according to claim 1, wherein the activation threshold is that the activation module determines whether the sound frequency in the sound signal exceeds the audio frequency range of the car body audio according to at least one stored car body audio frequency , If the sound frequency in the sound signal exceeds the sound frequency range of the car body audio, the activation module determines that the sound signal exceeds the activation threshold to activate the processing module, and when the sound frequency in the sound signal When the audio frequency range of the vehicle body audio frequency is not exceeded, the activation module determines that the audio signal does not exceed the activation threshold, so as to continue to receive another audio signal. The vehicle body abnormal sound detection device according to claim 4, wherein when the activation module activates the processing module, the activation module stops operating, and when the processing module stops operating, the activation module stops operating Start by judging the sound frequency in the sound signal according to the activation threshold to determine whether to activate the processing module. The vehicle body abnormal sound detection device according to claim 1, wherein the processing module is connected with a vehicle control device to obtain a control signal from the vehicle control device, and the processing module executes according to a command in the control signal Turn on or turn off the radio module; or the processing module executes and adjusts the output volume of the warning device according to a command in the control signal. The vehicle body abnormal sound detection device according to claim 1, wherein the processing module is further connected with a component detection device to transmit the warning signal to the component detection device, and when the component detection device receives the warning signal, The component inspection equipment The setting system executes a detection operation to detect whether each component in the vehicle body conforms to an abnormal state data. The vehicle body abnormal sound detection device according to claim 1, wherein the warning device includes one of a display module, a lamp, a speaker, or a combination of any two or more thereof. A vehicle body abnormal sound detection method applied to the vehicle body abnormal sound detection device according to any one of claims 1 to 8, comprising: a radio module receiving a sound signal in a range inside a vehicle body; A processing module separates a plurality of sound sources in the sound signal; the processing module compares an audio feature point in the sound sources based on a plurality of car body audio data; the processing module uses a deep learning algorithm to determine the Whether the audio feature points conform to a plurality of abnormal sound frequencies; when the processing module determines that at least one of the audio feature points conforms to any of the abnormal sound frequencies, the processing module generates a warning signal correspondingly; and a warning device receives And output the warning signal; among them, an activation module receives the sound signal from the radio module, and determines the sound frequency in the sound signal according to an activation threshold to determine whether to activate the processing module. When the sound signal exceeds When the activation threshold is reached, the activation module activates the processing module, and when the sound signal does not exceed the activation threshold, the activation module continues to receive another sound signal.

Images