CN109591693B - Active sound production system for motion sound quality of electric automobile - Google Patents
Active sound production system for motion sound quality of electric automobile Download PDFInfo
- Publication number
- CN109591693B CN109591693B CN201811282370.3A CN201811282370A CN109591693B CN 109591693 B CN109591693 B CN 109591693B CN 201811282370 A CN201811282370 A CN 201811282370A CN 109591693 B CN109591693 B CN 109591693B
- Authority
- CN
- China
- Prior art keywords
- sound
- vehicle
- electric automobile
- acquisition device
- production system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 33
- 230000005236 sound signal Effects 0.000 claims abstract description 5
- 230000001133 acceleration Effects 0.000 claims description 20
- 210000002569 neuron Anatomy 0.000 claims description 11
- 238000003745 diagnosis Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 239000000295 fuel oil Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q5/00—Arrangement or adaptation of acoustic signal devices
- B60Q5/005—Arrangement or adaptation of acoustic signal devices automatically actuated
- B60Q5/008—Arrangement or adaptation of acoustic signal devices automatically actuated for signaling silent vehicles, e.g. for warning that a hybrid or electric vehicle is approaching
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
Abstract
The invention relates to an active sound production system for the quality of moving sound of an electric automobile, which comprises: signal pickup assembly, the control unit and the speaker of setting on electric automobile. The signal acquisition device is used for acquiring state data of the electric automobile; the control unit is loaded with a trained BP neural network and outputs a control signal containing the corresponding frequency, amplitude and phase of the expected dynamic sound according to the state of the electric vehicle acquired by the signal acquisition device; the loudspeaker emits a corresponding sound signal based on the control signal. And training the BP neural network in the control unit by adopting a training system. The training system comprises a target vehicle, a state data standard signal acquisition device for acquiring the target vehicle, a standard sound acquisition device for acquiring the sound emitted by the target vehicle and a database, and the control unit is connected with the database. The invention can transplant the required sound effect to the electric automobile, so that the dynamic sound types which can be adjusted by the electric automobile are richer, and the requirements of partial drivers are met.
Description
Technical Field
The invention belongs to the field of active noise control, and particularly relates to an active sound production system for the motion sound quality of an electric automobile, which is applied to the electric automobile industry and is arranged on the electric automobile to simulate the sound effect of a traditional fuel oil automobile.
Background
With the increasing awareness of environmental protection, electric automobiles will gradually replace internal combustion engine automobiles in the future. The sound emitted by the electric automobile is usually very small and sharp, and the requirement of part of drivers on the sound cannot be met, namely the electric automobile is generally a single-speed gearbox, and the moving sense of low-sinking and roaring sound of the traditional fuel oil automobile during accelerating gear shifting cannot be realized. The exhaust sound wave is adjusted by changing the exhaust system, so that the fuel oil vehicle is only suitable for the traditional fuel oil vehicle and is not suitable for the electric vehicle.
Disclosure of Invention
The invention aims to provide an active sound production system for the motion sound quality of an electric automobile, which is suitable for the electric automobile and can actively simulate the sound effect of a traditional fuel vehicle so as to meet the requirements of partial drivers on the driving sound.
In order to achieve the purpose, the invention adopts the technical scheme that:
the utility model provides an electric automobile motion sound quality initiative sound production system, installs on electric automobile, electric automobile motion sound quality initiative sound production system includes:
the signal acquisition device is connected with the electric automobile and acquires state data of the electric automobile;
the control unit is loaded with a trained BP neural network and outputs a control signal containing the corresponding frequency, amplitude and phase of the expected dynamic sound according to the state of the electric automobile collected by the signal collection device;
a speaker disposed on the electric vehicle, the speaker emitting a sound signal having a corresponding frequency, amplitude, and phase based on the control signal.
Preferably, the state data of the electric vehicle includes an accelerator opening, a vehicle speed, and an acceleration.
Preferably, the signal acquisition device is connected with a vehicle-mounted diagnosis system of the electric vehicle to acquire the opening degree of an accelerator pedal and the speed of the electric vehicle, and the signal acquisition device is connected with an acceleration sensor arranged on the electric vehicle to acquire the acceleration of the electric vehicle.
Preferably, a training system is adopted to train the BP neural network in the control unit; the training system comprises:
the target vehicle can emit different rumbling sounds in different states;
the standard signal acquisition device is connected with the alignment mark vehicle and acquires the state data of the alignment mark vehicle;
the standard sound acquisition device is connected with the benchmarking vehicle and correspondingly acquires sound parameter data of sounds emitted by the benchmarking vehicle when the benchmarking vehicle has different state data;
the database is respectively connected with the standard signal acquisition device and the standard sound acquisition device and records different state data of the benchmarking vehicle and corresponding sound parameter data;
the control unit is connected with the database.
Preferably, the state data of the target vehicle comprises an accelerator opening degree, a vehicle speed and an acceleration of the target vehicle.
Preferably, the number of neurons of the input layer of the BP neural network is the same as the number of types of state data of the benchmarking vehicle.
Preferably, the number of neurons in the output layer of the BP neural network varies with the set frequency interval.
Further preferably, the frequency interval is set to 1 Hz.
Preferably, the number j of the neurons in the hidden layer of the BP neural network is
Wherein m is the number of the collected different speeds of the alignment mark vehicle, n is the number of the collected different opening degrees of the accelerator of the alignment mark vehicle, and epsilon is [1, 10]]A natural number of any value within the range.
Due to the application of the technical scheme, compared with the prior art, the invention has the following advantages: the invention can transplant the required sound effect to the electric automobile, so that the dynamic sound types which can be adjusted by the electric automobile are richer, and the requirements of partial drivers are met.
Drawings
Fig. 1 is a control schematic diagram of the active sound production system for the moving sound quality of the electric vehicle according to the present invention.
FIG. 2 is a schematic diagram of a BP neural network structure.
Fig. 3 is a schematic structural diagram of a BP neural network according to the present invention.
FIG. 4 is a flow chart of the establishment of the BP neural network in the present invention.
Detailed Description
The invention will be further described with reference to examples of embodiments shown in the drawings to which the invention is attached.
The first embodiment is as follows: an active sounding system for the moving sound quality of an electric automobile installed on the electric automobile comprises a signal acquisition device, a control unit and a loudspeaker (which can be a loudspeaker of the electric automobile or a loudspeaker additionally arranged on the electric automobile) arranged on the electric automobile.
The signal acquisition device is in signal connection with the electric automobile so as to be used for acquiring state data of the electric automobile. The state data of the electric vehicle includes an accelerator opening α ', a vehicle speed u ', and an acceleration a '. Generally, a signal acquisition device is connected to an on-board diagnostic system (OBD) of an electric vehicle to acquire an accelerator pedal (accelerator pedal) opening degree α and a vehicle speed u of the electric vehicle, and is connected to an acceleration sensor provided in the electric vehicle to acquire an acceleration a of the electric vehicle.
The input end of the control unit is connected with a signal acquisition device, and a trained BP neural network is loaded in the signal acquisition device. Therefore, the input signals of the control unit are various signals collected by the signal collecting device, so that the control unit outputs control signals containing the corresponding frequency, amplitude and phase of the expected dynamic sound according to the state of the electric automobile collected by the signal collecting device.
The output of the control unit is connected to a loudspeaker arranged on the electric vehicle, so that the loudspeaker can emit a sound signal having a corresponding frequency, amplitude and phase on the basis of the control signal.
For the BP neural network in the control unit, a training system is required to train the BP neural network so as to obtain a required function. The training system comprises a benchmarking vehicle, a standard signal acquisition device, a standard sound acquisition device and a database.
Since the dynamic sound is subjective, it is necessary to specify an appropriate target vehicle that can emit different booming sounds in different states, and the booming sounds are used as the desired dynamic sound, so that dynamic sound data of the target vehicle in different driving states need to be studied. The state data of the target vehicle comprises an accelerator opening degree alpha, a vehicle speed u and an acceleration a of the target vehicle.
The standard signal acquisition device is connected with the alignment mark vehicle and acquires the state data of the alignment mark vehicle, namely, the standard signal acquisition device acquires the opening degrees alpha of different accelerator pedals of the alignment mark vehicle1，α2，…，αnDifferent vehicle speeds u1，u2，…，umDifferent acceleration a1，a2，…，ak. The standard sound acquisition device is connected with the benchmarking vehicle and correspondingly acquires sound parameter data of sounds emitted by the benchmarking vehicle when the benchmarking vehicle has different state data. For example, the accelerator opening is alphaiSound signal S of time-target vehicle at different accelerations a and different vehicle speeds ukm(i) As shown in table 1:
TABLE 1 Accelerator opening degree αiDynamic sound data numbering of time-alignment mark vehicle at different accelerated speeds and vehicle speeds
| a1 | a2 | … | ak | |
| u1 | S11(i) | S21(i) | … | Sk1(i) |
| u2 | S12(i) | S22(i) | … | Sk2(i) |
| … | … | … | … | … |
| um | S1m(i) | S2m(i) | … | Skm(i) |
For each sound signal, its frequency components and the corresponding amplitudes and phases of the frequencies are phased so as to obtain the sound parameter data of the desired dynamic sound.
The database is respectively connected with the standard signal acquisition device and the standard sound acquisition device, and the information acquired by the standard signal acquisition device and the standard sound acquisition device is sent into the database, so that the database is used for recording different state data of the alignment mark vehicle and the corresponding sound parameter data. The control unit is connected with the database, and the initial BP neural network established in the control unit can be trained by using the information stored in the database as a training sample.
The BP neural network is also called an error back propagation neural network, and the error propagation direction is opposite to the input signal propagation direction. The BP neural network is mainly divided into three layers: the basic model of the input layer, the hidden layer and the output layer is shown in figure 2. Specifically, in the scheme, a BP neural network model is established by utilizing vehicle state data and dynamic voice audio parameter data of the target vehicle. The number of the neurons of the input layer of the established BP neural network is the same as the number of the types of the state data of the target vehicle, namely the neuron corresponds to three types of the opening degree alpha of an accelerator pedal, the vehicle speed u and the acceleration a. The number j of the neurons of the hidden layer of the BP neural network is as follows:
wherein m is the number of the collected different speeds of the alignment mark vehicle, n is the number of the collected different opening degrees of the accelerator of the alignment mark vehicle, and epsilon is a natural number of any value in the range of [1, 10 ]. The output of the BP neural network is a control signal containing frequency, amplitude and phase, namely the output is the amplitude A and the phase P under each frequency within the range of 20Hz-20kHz, so the number of neurons of the output layer of the BP neural network changes along with the set frequency interval. For example, when the frequency interval is set to 1Hz, the number of neurons is 19980. The smaller the frequency spacing setting, the better the effect. The model of the BP neural network built based on this is shown in fig. 3, in which [ a (n), p (n) ], represents the amplitude and phase of the collected dynamic sound at frequency nHz.
The working process of the BP neural network is divided into two stages: a learning period and a working period. Training the BP neural network is a learning period. In the learning period, an input signal is transmitted from an input layer to a hidden layer, the input signal is processed in the hidden layer and transmitted to an output layer, when the error between the output quantity obtained by the output layer and an expected value is large, the error returns along the original propagation route, the connection weight is modified to enable the error to be within an allowable range, therefore, the connection weight between the layers is trained through a plurality of samples until the BP neural network reaches a stable state, and the training process is shown in figure 4.
The trained BP neural network can be used for the electric automobile, so that the electric automobile can send out dynamic sound matched with the actual running state of the electric automobile (including the opening degree alpha ' of an accelerator pedal, the speed u ' and the acceleration a '). The process is the working period of the BP neural network, namely the trained BP neural network is used for carrying out forward propagation on input information to obtain output information.
To sum up, this scheme is the initiative sound production system that increases on electric automobile, and when electric automobile went, this system read vehicle accelerator pedal aperture alpha ', speed of a motor vehicle u ' in through the OBD, install acceleration sensor additional on electric automobile in addition and measure car acceleration a ', according to corresponding control strategy, control the speaker in the car, let its initiative sound production, simulate traditional fuel motion sports car powerful low heavy rumble when shifting gears and accelerating, build strong motion sense, its beneficial effect lies in:
firstly, an active sounding system is used for transplanting the special powerful low-level roaring sound of the internal combustion engine automobile to the electric automobile;
secondly, simulating dynamic sound generated by an engine when the traditional fuel vehicle is shifted in an accelerating way according to the change rule of the opening degree of an accelerator pedal, the speed and the acceleration of the vehicle;
the electric vehicle carrying the active sounding system can adjust more dynamic sound types;
and fourthly, the opening degree of an accelerator pedal, the speed and the acceleration of the vehicle are used as reference signals, so that the stability and the convergence speed of the system are improved.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (7)
1. The utility model provides an electric automobile motion sound quality initiative sound production system, installs on electric automobile, its characterized in that: the active sound production system for the moving sound quality of the electric automobile comprises:
the signal acquisition device is connected with the electric automobile and acquires state data of the electric automobile; the state data of the electric automobile comprises the opening degree of an accelerator pedal, the speed and the acceleration;
the control unit is loaded with a trained BP neural network, outputs a control signal containing the corresponding frequency, amplitude and phase of the expected dynamic sound according to the state of the electric automobile collected by the signal collecting device, and changes the number of neurons of an output layer of the BP neural network along with the set frequency interval;
a speaker disposed on the electric vehicle, the speaker emitting a sound signal having a corresponding frequency, amplitude, and phase based on the control signal.
2. The active sound production system for sports sound quality of the electric vehicle according to claim 1, wherein: the signal acquisition device is connected with a vehicle-mounted diagnosis system of the electric automobile to acquire the opening degree of an accelerator pedal and the speed of the electric automobile, and the signal acquisition device is connected with an acceleration sensor arranged on the electric automobile to acquire the acceleration of the electric automobile.
3. The active sound production system for sports sound quality of the electric vehicle according to claim 1, wherein: training the BP neural network in the control unit by adopting a training system; the training system comprises:
the target vehicle can emit different rumbling sounds in different states;
the standard signal acquisition device is connected with the alignment mark vehicle and acquires the state data of the alignment mark vehicle;
the standard sound acquisition device is connected with the benchmarking vehicle and correspondingly acquires sound parameter data of sounds emitted by the benchmarking vehicle when the benchmarking vehicle has different state data;
the database is respectively connected with the standard signal acquisition device and the standard sound acquisition device and records different state data of the benchmarking vehicle and corresponding sound parameter data;
the control unit is connected with the database.
4. The active sound production system for sports sound quality of the electric vehicle according to claim 3, wherein: the state data of the target vehicle comprises the opening degree of an accelerator pedal, the vehicle speed and the acceleration of the target vehicle.
5. The active sound production system for sports sound quality of the electric vehicle according to claim 4, wherein: the number of the neurons of the input layer of the BP neural network is the same as the number of the types of the state data of the benchmarking vehicle.
6. The active sound production system for sports sound quality of the electric vehicle according to claim 1, wherein: the frequency interval is set to 1 Hz.
7. The active sound production system for sports sound quality of the electric vehicle according to claim 4, wherein: the number j of the neurons of the hidden layer of the BP neural network is
Wherein m is the number of the collected different speeds of the alignment mark vehicle, n is the number of the collected different opening degrees of the accelerator of the alignment mark vehicle, and epsilon is [1, 10]]A natural number of any value within the range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811282370.3A CN109591693B (en) | 2018-10-31 | 2018-10-31 | Active sound production system for motion sound quality of electric automobile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811282370.3A CN109591693B (en) | 2018-10-31 | 2018-10-31 | Active sound production system for motion sound quality of electric automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109591693A CN109591693A (en) | 2019-04-09 |
| CN109591693B true CN109591693B (en) | 2022-03-22 |
Family
ID=65957080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811282370.3A Active CN109591693B (en) | 2018-10-31 | 2018-10-31 | Active sound production system for motion sound quality of electric automobile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109591693B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109982202A (en) * | 2019-04-22 | 2019-07-05 | 北京灵伴未来科技有限公司 | A kind of flexible piezoelectric sound-generating devices and sound production method for vehicle |
| CN110341591A (en) * | 2019-07-10 | 2019-10-18 | 太原科技大学 | It is a kind of for pure electric vehicle or the acoustic management system of hybrid vehicle active safety |
| CN110446136B (en) * | 2019-07-11 | 2020-07-14 | 华研慧声（苏州）电子科技有限公司 | Control method adopted by in-vehicle sound field partition reconstruction system |
| CN111559320A (en) * | 2020-04-26 | 2020-08-21 | 东风汽车集团有限公司 | Method and system for realizing active sounding of vehicle based on vehicle-mounted intelligent terminal |
| CN112298031B (en) * | 2020-10-29 | 2024-09-06 | 中科上声（苏州）电子有限公司 | Active sounding method and system for electric automobile based on shift strategy migration |
| CN113805524A (en) * | 2021-09-15 | 2021-12-17 | 北京铁道工程机电技术研究所股份有限公司 | Safety interlocking control system and method |
| CN114162042A (en) * | 2021-12-31 | 2022-03-11 | 江苏理工学院 | Self-adaptive vehicle horn developed based on BP neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103260951A (en) * | 2011-08-08 | 2013-08-21 | 雅马哈发动机株式会社 | Driving-linked sound generation device |
| CN103895567A (en) * | 2014-03-26 | 2014-07-02 | 北京长安汽车工程技术研究有限责任公司 | Method and device for sound simulation and sound production of electric vehicle |
| CN107554417A (en) * | 2016-06-30 | 2018-01-09 | 通用汽车环球科技运作有限责任公司 | Electric vehicle sound enhancement system and method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2983439B1 (en) * | 2011-12-02 | 2014-10-31 | Renault Sa | MOTOR VEHICLE SOUND GENERATION SYSTEM FOR THE WARNING OF INDIVIDUALS LOCATED NEARBY |
| WO2013145083A1 (en) * | 2012-03-26 | 2013-10-03 | パイオニア株式会社 | Audio device, sound output management device, terminal device and sound output control method |
| US20180090125A1 (en) * | 2016-09-26 | 2018-03-29 | Yung Yeung | Simulation of driving sound of electric vehicle |
| CN108016351A (en) * | 2017-12-29 | 2018-05-11 | 合肥东胜汽车电子有限公司 | A kind of electric car warns sound control device and method |
-
2018
- 2018-10-31 CN CN201811282370.3A patent/CN109591693B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103260951A (en) * | 2011-08-08 | 2013-08-21 | 雅马哈发动机株式会社 | Driving-linked sound generation device |
| CN103895567A (en) * | 2014-03-26 | 2014-07-02 | 北京长安汽车工程技术研究有限责任公司 | Method and device for sound simulation and sound production of electric vehicle |
| CN103895567B (en) * | 2014-03-26 | 2016-06-29 | 北京长安汽车工程技术研究有限责任公司 | The speech simulation vocal technique of a kind of electric automobile and device |
| CN107554417A (en) * | 2016-06-30 | 2018-01-09 | 通用汽车环球科技运作有限责任公司 | Electric vehicle sound enhancement system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109591693A (en) | 2019-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109591693B (en) | Active sound production system for motion sound quality of electric automobile | |
| KR102474355B1 (en) | Vehicle control total management system and central artificial intelligence server connected with vehicle control total management system via communcation | |
| CN110718206B (en) | Sound target setting method of active sound production system and active sound production system | |
| US10625671B2 (en) | Engine sound color control method based on engine dynamic characteristic with artificial intelligence and vehicle thereof | |
| EP1097445B1 (en) | Method and device for producing sounds corresponding to the operation of an internal combustion engine in the inner space of a motor vehicle | |
| WO2010000532A2 (en) | Arrangement for generating a simulated operating noise of a vehicle drive unit | |
| WO2011050274A1 (en) | System for simulated multi-gear vehicle sound generation | |
| CN110880313B (en) | Control method and system for outputting counternoise of current environment based on noise reduction feedback | |
| JP2020095260A (en) | System and method for controlling engine tone by artificial intelligence based on sound quality index of vehicle | |
| CN102519580A (en) | Method for separating speed changer knocking structure noise and air noise based on transmission path | |
| CN113689842A (en) | Integrated system for active noise reduction and audio power amplification of automobile | |
| CN111933105B (en) | Automobile noise control device and control method thereof | |
| CN102224541B (en) | Voice output device | |
| KR20230167464A (en) | Method of virtualizing characteristics of internal-combustion-engine vehicle in electric vehicle | |
| CN109121041A (en) | Audio control system and method based on road characteristics and vehicle operation | |
| CN103871397A (en) | Device for influencing passenger compartment noise | |
| CN110021288A (en) | Vehicle active noise reduction control method and its system | |
| CN108022596A (en) | Audio signal processing method and vehicle electronic device | |
| CN116884377A (en) | Active sounding method for improving tone quality | |
| CN213422401U (en) | Engine noise acquisition system | |
| CN112061046A (en) | System for simulating noise decomposition and synthesis of fuel vehicle | |
| KR20230168325A (en) | Method of virtualizing characteristics of internal-combustion-engine vehicle in electric vehicle | |
| Lee et al. | Adaptive algorithm of active sound design for the engine noise | |
| Wu et al. | Vibro-impact analysis of manual transmission gear rattle and its sound quality evaluation | |
| Philippen et al. | Experience NVH Performance on Vehicle Level in Real-Time based on Powertrain Test Bench Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |