CN115052761B - Method and device for detecting tire abnormality - Google Patents
Method and device for detecting tire abnormality Download PDFInfo
- Publication number
- CN115052761B CN115052761B CN202180000477.8A CN202180000477A CN115052761B CN 115052761 B CN115052761 B CN 115052761B CN 202180000477 A CN202180000477 A CN 202180000477A CN 115052761 B CN115052761 B CN 115052761B
- Authority
- CN
- China
- Prior art keywords
- tire
- tire pressure
- pressure data
- sound
- period
- 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
- 230000005856 abnormality Effects 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000002159 abnormal effect Effects 0.000 claims abstract description 113
- 230000004807 localization Effects 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 230000003213 activating effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 35
- 238000004891 communication Methods 0.000 description 10
- 238000012549 training Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 229960001948 caffeine Drugs 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000037433 frameshift Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- RYYVLZVUVIJVGH-UHFFFAOYSA-N trimethylxanthine Natural products CN1C(=O)N(C)C(=O)C2=C1N=CN2C RYYVLZVUVIJVGH-UHFFFAOYSA-N 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60C—VEHICLE TYRES; TYRE INFLATION; TYRE CHANGING; CONNECTING VALVES TO INFLATABLE ELASTIC BODIES IN GENERAL; DEVICES OR ARRANGEMENTS RELATED TO TYRES
- B60C23/00—Devices for measuring, signalling, controlling, or distributing tyre pressure or temperature, specially adapted for mounting on vehicles; Arrangement of tyre inflating devices on vehicles, e.g. of pumps or of tanks; Tyre cooling arrangements
- B60C23/02—Signalling devices actuated by tyre pressure
- B60C23/04—Signalling devices actuated by tyre pressure mounted on the wheel or tyre
- B60C23/0401—Signalling devices actuated by tyre pressure mounted on the wheel or tyre characterised by the type of alarm
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60C—VEHICLE TYRES; TYRE INFLATION; TYRE CHANGING; CONNECTING VALVES TO INFLATABLE ELASTIC BODIES IN GENERAL; DEVICES OR ARRANGEMENTS RELATED TO TYRES
- B60C23/00—Devices for measuring, signalling, controlling, or distributing tyre pressure or temperature, specially adapted for mounting on vehicles; Arrangement of tyre inflating devices on vehicles, e.g. of pumps or of tanks; Tyre cooling arrangements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60C—VEHICLE TYRES; TYRE INFLATION; TYRE CHANGING; CONNECTING VALVES TO INFLATABLE ELASTIC BODIES IN GENERAL; DEVICES OR ARRANGEMENTS RELATED TO TYRES
- B60C23/00—Devices for measuring, signalling, controlling, or distributing tyre pressure or temperature, specially adapted for mounting on vehicles; Arrangement of tyre inflating devices on vehicles, e.g. of pumps or of tanks; Tyre cooling arrangements
- B60C23/02—Signalling devices actuated by tyre pressure
- B60C23/04—Signalling devices actuated by tyre pressure mounted on the wheel or tyre
- B60C23/0408—Signalling devices actuated by tyre pressure mounted on the wheel or tyre transmitting the signals by non-mechanical means from the wheel or tyre to a vehicle body mounted receiver
- B60C23/0481—System diagnostic, e.g. monitoring battery voltage, detecting hardware detachments or identifying wireless transmission failures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L17/00—Devices or apparatus for measuring tyre pressure or the pressure in other inflated bodies
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measuring Fluid Pressure (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The embodiment of the application provides a method for detecting tire abnormality, which can be applied to intelligent driving automobiles, new energy automobiles and automatic driving automobiles, and comprises the following steps: periodically acquiring tire pressure data of a target tire through a pressure sensor; analyzing the periodically collected tire pressure data to identify that the tire pressure of the target tire is continuously reduced; collecting audio data through an acoustic sensor; abnormal sound identification is carried out on the audio data, and abnormal sound of the audio data is identified; performing sound source localization analysis on the audio data to identify an abnormal sound source; and matching the pointing position of the abnormal sound source with the target tire, wherein the matching of the pointing position of the abnormal sound source with the target tire indicates that the target tire is abnormal.
Description
Technical Field
The application relates to the field of automobiles, in particular to a method for detecting tire abnormality.
Background
In recent years, the automobile keeping amount in China reaches 2.6 hundred million, the number is still rapidly increased, and the automobile safety is receiving more attention. During the running of the vehicle, the failure of the automobile tires is most worry about the driver and is most difficult to prevent. It is counted that about 30% of traffic accidents in China are tire burst caused by too low or too high tire pressure each year, and up to 50% of high-speed traffic accidents are caused by abnormal tire pressure of automobile tires, so that how to monitor, prevent and detect abnormal tires has become an important subject of automobile safety.
Be applied to tire pressure monitoring system (Tire Pressure Monitoring System, TPMS) on the car, can detect the tire pressure of tire in real time, can in time send out the alarm even early warning when detecting that the tire pressure is unusual to ensure the safety of vehicle and passenger. The basic principle of the TPMS is that the reasonable range of the tire pressure of the vehicle tire is firstly set, the set value is ensured to be consistent with the parameters of the vehicle tire, and when the tire pressure deviates from the set value, the TPMS gives an alarm when the set value is not in the set reasonable range of the tire pressure of the vehicle tire. The TPMS can give an alarm in time when the tire pressure is too low or gas leaks.
TPMS currently on the market can be broadly divided into two categories: an indirect TPMS and a direct TPMS. The indirect TPMS is a system for directly measuring the pressure of the tires of the vehicle by measuring other parameters of the vehicle, such as the rotational speed of four wheels, but the indirect TPMS cannot measure the instantaneous air pressure of the tires of the vehicle and has low sensitivity. The direct type TPMS is a system for directly measuring the tire pressure through a pressure sensor arranged in a tire of a vehicle and directly transmitting data to a receiver, and has high monitoring precision, high sensitivity and no false alarm no matter what working condition the vehicle is in, but the direct type TPMS has higher installation cost and higher battery power consumption.
The conventional TPMS usually gives an alarm when the tire pressure value of the tire is lower than a certain preset value, and cannot give an alarm in time to prompt a driver, so that potential driving safety exists.
Disclosure of Invention
Aiming at the problem that TPMS (tire pressure monitor System) can not give an alarm in time when a tire is abnormal in the prior art, the embodiment of the application provides a tire abnormality detection method and device.
In a first aspect, an embodiment of the present application provides a method for detecting an abnormality in a tire, which may be used to detect whether the tire has an abnormality, including whether the tire leaks. The method comprises the following specific steps: periodically acquiring tire pressure data of a target tire through a pressure sensor built in a vehicle wheel; analyzing the periodically collected tire pressure data to identify the condition that the tire pressure of the target tire is continuously reduced; collecting audio data through a sound-sensitive sensor configured by a vehicle; abnormal sound identification is carried out on the audio data, and abnormal sound of the audio data is identified; performing sound source localization analysis on the audio data to identify an abnormal sound source; and matching the pointing position of the abnormal sound source with the target tire, wherein the matching of the pointing position of the abnormal sound source with the target tire indicates that the target tire is abnormal.
By combining the tire pressure detection, abnormal sound identification and sound source localization technology, the tire abnormality of the vehicle can be timely detected and an alarm can be timely sent out, and compared with the traditional technical scheme that the tire pressure threshold value is only used for judging, the tire abnormality detection accuracy is higher.
One possible implementation manner, the continuous decrease in the tire pressure of the target tire includes: the first tire pressure data is larger than the second tire pressure data, and the difference value of the first tire pressure data minus the second tire pressure data is not larger than a preset value;
the first tire pressure data is tire pressure data of the target tire collected in a first period, the second tire pressure data of the target tire collected in a second period, the first period and the second period are any two adjacent periods in a plurality of continuous periods, and the first period is located before the second period.
In one possible implementation, the method for detecting an anomaly in a tire further includes: analyzing the periodically collected tire pressure data to identify that the target tire has air leakage; and sending out an alarm to prompt the user that the target tire leaks.
A possible implementation, the occurrence of air leakage of the target tire includes: the third tire pressure data is greater than the fourth tire pressure data, the difference of the third tire pressure data minus the fourth tire pressure data is greater than a preset value, the third tire pressure data is the tire pressure data of the target tire collected in a third period, the fourth tire pressure data of the target tire collected in a fourth period, the first period and the second period are two adjacent periods, and the third period is located before the fourth period.
A possible implementation manner, the identifying abnormal sound of the audio data, identifying that the abnormal sound exists in the audio data, includes: processing the audio data to obtain sound characteristic parameters corresponding to the audio data; and comparing the sound characteristic parameters corresponding to the audio data with a pre-trained audio template library, and outputting abnormal sounds of the audio data.
In one possible implementation, the method for detecting an anomaly in a tire further includes: a tire abnormality alarm is sent out to prompt a user that the target tire is abnormal; receiving a feedback result of the user for the tire abnormality alarm; and updating the audio template library based on the feedback result and the sound characteristic parameters corresponding to the audio data.
A possible implementation manner, the number of the sound-sensitive sensors is greater than 1, the performing sound source localization analysis on the audio data, identifying an abnormal sound source, includes: acquiring audio energy acquired by the sound-sensitive sensor based on the audio data; and calculating the distance of each sound-sensitive sensor relative to the sound source at the unknown position based on the audio energy, wherein the position of the sound-sensitive sensor corresponding to the minimum distance relative to the sound source at the unknown position represents the abnormal sound source.
A possible implementation manner, before the audio data is collected by the acoustic sensor, further includes: activating the acoustic sensor associated with the target tire.
In a second aspect, an embodiment of the present application provides an apparatus for detecting tire abnormality, configured to implement the method for detecting tire abnormality provided in the first aspect, where the apparatus for detecting tire abnormality includes: the tire pressure data acquisition module is used for periodically acquiring the tire pressure data of the target tire through the pressure sensor; the tire pressure analysis module is used for analyzing the periodically acquired tire pressure data and identifying that the tire pressure of the target tire is continuously reduced; the audio data acquisition module is used for acquiring audio data through the sound-sensitive sensor; the abnormal sound identification module is used for carrying out abnormal sound identification on the audio data and identifying that abnormal sound exists in the audio data; the sound source positioning module is used for carrying out sound source positioning analysis on the audio data and identifying an abnormal sound source; and the matching module is used for matching the pointing position of the abnormal sound source with the target tire, and the matching of the pointing position of the abnormal sound source with the target tire indicates that the target tire is abnormal.
One possible implementation manner, the continuous decrease in the tire pressure of the target tire includes: the first tire pressure data is larger than the second tire pressure data, and the difference value of the first tire pressure data minus the second tire pressure data is not larger than a preset value;
the first tire pressure data is tire pressure data of the target tire collected in a first period, the second tire pressure data of the target tire collected in a second period, the first period and the second period are any two adjacent periods in a plurality of continuous periods, and the first period is located before the second period.
A possible implementation manner, the tire pressure analysis module is further configured to: analyzing the periodically collected tire pressure data to identify that the target tire has air leakage; the apparatus further comprises: and the tire air leakage alarming module is used for sending out an alarm so as to prompt the user that the target tire is out of air.
A possible implementation, the occurrence of air leakage of the target tire includes: the third tire pressure data is greater than the fourth tire pressure data, the difference of the third tire pressure data minus the fourth tire pressure data is greater than a preset value, the third tire pressure data is the tire pressure data of the target tire collected in a third period, the fourth tire pressure data of the target tire collected in a fourth period, the first period and the second period are two adjacent periods, and the third period is located before the fourth period.
A possible implementation manner, the abnormal sound identification module is specifically configured to: processing the audio data to obtain sound characteristic parameters corresponding to the audio data; and comparing the sound characteristic parameters corresponding to the audio data with a pre-trained audio template library, and outputting abnormal sounds of the audio data.
In one possible implementation manner, the apparatus for detecting tire abnormality further includes: the tire abnormality alarming module is used for sending out tire abnormality alarming to prompt a user that the target tire is abnormal; and the audio template library updating module is used for receiving a feedback result of the user for the tire abnormality alarm and updating the audio template library based on the feedback result and the sound characteristic parameters corresponding to the audio data.
In one possible implementation manner, the number of the sound-sensitive sensors is greater than 1, and the sound source positioning module is specifically configured to: acquiring audio energy acquired by the sound-sensitive sensor based on the audio data; and calculating the distance of each sound-sensitive sensor relative to the sound source at the unknown position based on the audio energy, wherein the position of the sound-sensitive sensor corresponding to the minimum distance relative to the sound source at the unknown position represents the abnormal sound source.
In one possible implementation manner, the apparatus for detecting tire abnormality further includes: and the sound-sensitive sensor activation module is used for activating the sound-sensitive sensor associated with the target tire.
In a third aspect, an embodiment of the present application provides a control unit for tire anomaly detection, the control unit being configured with programmable instructions that, when executed, are capable of implementing the method for detecting tire anomalies provided in the first aspect.
In a fourth aspect, an embodiment of the present application provides a system for detecting tire anomalies, the system including a tire pressure sensor, an acoustic sensor, and a control unit. The tire pressure sensor is built in each wheel and is used for collecting tire pressure data of each wheel. The sound-sensitive sensor is arranged on a vehicle which can collect audio data at the tire and is used for collecting the audio data. The control unit is coupled with the tire pressure sensor and the sound sensor for executing the method for detecting tire abnormality provided in the first aspect.
In a fifth aspect, an embodiment of the present application provides a storage medium storing instructions that, when executed, implement the method for detecting tire anomalies provided in the first aspect.
The method for detecting the tire abnormality provided by the embodiment of the application combines the tire pressure detection, abnormal sound identification and sound source localization technology, can give an alarm in time when the tire is abnormal (for example, the tire is punctured with foreign matters, the tire leaks air and the like), improves the driving safety, and can continuously increase the identification accuracy in an incremental learning mode.
Drawings
FIG. 1 is a schematic diagram of a tire anomaly detection system according to an embodiment of the present application;
fig. 2 is a schematic view of a microphone mounting position according to an embodiment of the present application;
FIG. 3 is a flowchart of a tire anomaly detection method according to an embodiment of the present application;
FIG. 4 is a flowchart of an abnormal sound recognition method according to an embodiment of the present application;
fig. 5 is a schematic diagram of a sound source localization principle according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a tire abnormality detection apparatus according to an embodiment of the present application;
fig. 7 is a schematic diagram of another tire abnormality detection apparatus according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be further described in detail below with reference to the accompanying drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
An embodiment of the present application provides a tire abnormality detection system, as shown in fig. 1, a tire abnormality detection system 100 including: a data acquisition module 101, a control module 102, a display module 103 and a feedback module 104.
The data acquisition module 101 includes a pressure sensor module 1011 and an acoustic sensor module 1012. Specifically, the pressure sensor module 1011 includes a pressure sensor built in each wheel, and typically, one pressure sensor is disposed on each wheel, and specifically, the pressure sensor is disposed on the hub of each wheel, for collecting tire pressure data of the north portion of the tire of the corresponding wheel. Optionally, each pressure sensor is internally provided with a wireless communication component, and the pressure sensor can convert the collected tire pressure signal into an analog signal, and then sends the collected tire pressure data to the control module 102 through the wireless communication component, so that the control module 102 performs data analysis and abnormality judgment. Specifically, the acoustic sensor module 1012 includes one or more acoustic sensors that may be disposed at locations inboard of the vehicle door or near the vehicle wheels, respectively, for collecting audio data of the vehicle during travel. Acoustic sensors generally refer to devices capable of audio data acquisition, such as microphones, pickups. As shown in fig. 2, the sound-sensitive sensor module uses 4 microphones as sound-sensitive sensors, which are respectively disposed at positions outside the vehicle and close to wheels, and are used for audio data during the running of the vehicle. Note that the number of acoustic sensors and the deployment position are not particularly limited. Alternatively, the voice recognition microphone in the vehicle may be multiplexed. Optionally, the one or more acoustic sensors send the collected audio data to the control module 102 wirelessly or by wire.
The control module 102 includes a storage unit 1021, an abnormal sound recognition unit 1022, and a sound source localization unit 1023. The storage unit 1021 stores the tire pressure data, the audio data, and the audio database received from the data collection module 101. The abnormal sound recognition unit 1022 performs abnormal sound analysis on the audio data received from the data acquisition module 101. The sound source localization unit 1023 performs sound source localization analysis on the audio data received from the data acquisition module 101. When the control module 102 determines that there is an abnormality in the tire based on the analysis results of the abnormal sound recognition unit 1022 and the sound source positioning unit 1023, a signal is sent to the display module 103, and the display module 103 is used to display the abnormality in the tire to prompt the user that there is an abnormality in the tire. In addition to prompting the user of the presence of an abnormality in the tire through the display module 103, the user may also be prompted of the presence of an abnormality in the tire through audio, vibration, visual, etc.
The audio template library updating module 104 is configured to receive feedback information of a user prompting the display module 103 that the tire is abnormal, for example, a positive feedback that the user has checked that the tire is indeed abnormal after the display module 103 prompts the tire to be abnormal, or a negative feedback that the user has checked that the tire is not abnormal after the display module 103 prompts the tire to be abnormal. The audio template library update module 104 is further configured to update the audio template library according to user feedback to improve the performance of the tire anomaly detection system 100.
An embodiment of the present application provides a tire abnormality detection method, as shown in fig. 3, the tire abnormality detection method 200 may include the following steps:
and S100, when the vehicle is started, activating each pressure sensor built in each wheel hub and collecting tire pressure data of the corresponding wheel. In the complete tire abnormality detection method, the pressure sensor periodically collects tire pressure data of corresponding wheels, for example, the tire pressure data is collected every preset time (such as 20 seconds, 30 seconds, etc.), and the tire pressure data can be collected once or multiple times. When tire pressure data is collected a plurality of times at every preset time, the average tire pressure data may be taken as tire pressure data collected in one cycle.
And S200, comparing and analyzing the tire pressure data acquired by each pressure sensor in the current period with the tire pressure data acquired by each pressure sensor in the previous period so as to detect the tire pressure states of the corresponding wheels of each pressure sensor. For example, the tire pressure data of the wheel a collected by the pressure sensor a in the current period is compared with the tire pressure data of the wheel a collected by the pressure sensor a in the previous period, and the tire pressure data of the wheel B collected by the pressure sensor B in the current period is compared with the tire pressure data of the wheel B collected by the pressure sensor B in the previous period. It should be noted that, if the current cycle is the first cycle, that is, after the vehicle is started, each pressure sensor collects the tire pressure data of the corresponding wheel for the first time, in this case, S200 may not be executed, that is, the tire pressure data collected during the week may not be subjected to the comparative analysis. The tire pressure data collected by each pressure sensor in the current period can be used as the tire pressure data collected by each pressure sensor in the previous period of the first period, namely, the tire pressure data collected by each pressure sensor in the current period is compared and analyzed with the tire pressure data collected by each pressure sensor in the current period. The tire pressure data collected by each pressure sensor in the current period can be compared and analyzed with the tire pressure data collected by each pressure sensor recently before the vehicle is started.
The tire pressure state may include a rapid decrease in the tire pressure, a non-rapid decrease in the tire pressure, a decrease in the tire pressure indicating that there is rapid air leakage in the tire of the wheel, and a normal tire pressure indicating that there is no rapid air leakage in the tire but a decrease in the tire pressure, a decrease in the tire pressure indicating that the tire pressure of the wheel is rising, and a normal tire pressure indicating that the tire pressure of the wheel is not changing.
Optionally, S200 further includes:
s201, if the tire pressure state is that the tire pressure is rapidly reduced, and the tire is in air leakage, an alarm is given through modes such as display, sound and vibration, and the user is prompted that the tire is in air leakage. Optionally, the user is prompted to finish the tire pressure abnormality detection method after the tire leaks.
S202, if the tire pressure state is that the tire pressure is not rapidly reduced, judging whether the value of the timer reaches a preset value. If the value of the timer does not reach the preset value, the value of the timer is increased by 1, and the process returns to step S100. If the value of the timer reaches the preset value, the value of the timer is cleared, and the following step S300 is performed. The value of the timer reaching the preset value indicates that the tire is abnormal. The timer is used for recording the number of times that the tire pressure is not rapidly reduced, and the numerical value of the timer represents the number of times that the tire pressure is not rapidly reduced, that is, the numerical value of the timer continuously increases to represent that the tire pressure is in a continuously reduced state. It should be noted that, the number of times that the tire pressure state of each tire is not rapidly reduced is counted separately, and may be counted by one timer or may be counted by a plurality of timers. The timer is a device capable of counting, and the specific structure and composition of the timer are not limited. Alternatively, the preset value may be set according to actual requirements, for example, 10, 20, to indicate that the preset tire pressure state is the number of times that the non-rapid decrease of the tire pressure occurs continuously.
S203, if the tire pressure state is that the tire pressure is increased, the numerical value of the timer is cleared, and further, the step S100 is executed.
S204, if the tire pressure state is that the tire pressure is normal, the numerical value of the timer is cleared, and further, the step S100 is executed.
One example, assume that pressure sensor A is built into the hub of wheel AIn the current period n, the tire data of the wheel A acquired by the pressure sensor A is P n The unit is kilopascals (Kpa). The tire data of the wheel A acquired by the pressure sensor A in the last period n-1 is P n-1 . The step S200 specifically includes:
if P n-1 -P n If P, the tire pressure state is that the tire pressure is rapidly reduced, which means that the tire of the wheel A is rapidly leaked.
If 0 < P n-1 -P n And P is less than or equal to, the tire pressure state is that the tire pressure is not rapidly reduced, meaning that the tire pressure of the wheel a is being reduced although there is no rapid leakage.
If P n-1 -P n And < 0, the tire pressure state is an increase in tire pressure, indicating an increase in tire pressure of the wheel a.
If P n-1 -P n =0, the tire pressure state is that the tire pressure is normal, indicating that the tire pressure of the wheel a does not change. It should be noted that in practical applications, the tire pressure generally fluctuates and P does not occur n -P n-1 =0, merely an example of the present application. In fact P n And P n-1 The difference is not large, for example, between-0.5 and 0.5, and it can be judged that the tire pressure state is the tire pressure normal. Similarly, -0.5 < P n-1 -P n And < 0.5, it cannot be determined that the tire pressure state is a non-rapid decrease in tire pressure or an increase in tire pressure.
The above P is a preset value, which is a positive number, and is used for representing a threshold value of a tire leakage, and the preset value may be a fixed threshold value (e.g., 5 kpa), or may be a dynamic threshold value, for example, a threshold value dynamically adjusted based on information such as an environmental temperature, a driving environment, weather, tire materials, road conditions, and the like.
S300, activating the sound-sensitive sensor and collecting audio data. The description about the deployment location of the acoustic sensor may refer to the description about the acoustic sensor module and the acoustic sensor in the corresponding embodiment of fig. 1. In general, the acoustic sensor performs audio data acquisition for a tire during running of a vehicle. Alternatively, the acoustic sensor may periodically collect audio data for a period of time, such as once every minute, each collection lasting 10 seconds. Alternatively, the number of activated sound-sensitive sensors may be determined according to a demand, a preset rule, or the like, and only one or more sound-sensitive sensors whose tire pressure state of the wheel is not rapidly reduced and whose timer value reaches or is near a preset value may be activated, and all of the sound-sensitive sensors may be activated. Besides activating the acoustic sensor that the tire pressure state of the wheel is not rapidly reduced and the value of the timer reaches the preset value, other acoustic sensors (such as all or nearby sensors) are activated to collect audio data more comprehensively for abnormal sound recognition. Referring to fig. 2, for example, if it is detected in step S200 that the tire condition of the wheel corresponding to the microphone 1 (the upper left wheel in the drawing) is that the tire pressure is not rapidly reduced and the value of the timer reaches the preset value, then in step S300, the microphone 1, the microphone 2 and the microphone 3 may be activated, and the microphone 4 further from the wheel corresponding to the microphone 1 does not need to be activated, because the microphone 1 is relatively further from the wheel corresponding to the microphone 4 (the lower right wheel in the drawing), the influence of the sound at the wheel corresponding to the microphone 4 on the audio data collected by the microphone 1 is smaller, and the energy consumption may be reduced and the occupation of the computing resources may be reduced by not activating the microphone 4.
S400, carrying out abnormal sound identification on the collected audio data to identify whether abnormal sound exists. If an abnormal sound exists, step S500 is performed. If no abnormal sound exists, the value of the timer is cleared, and the execution returns to S100. As to how to perform abnormal sound recognition on the audio data, the abnormal sound recognition method in the prior art may be adopted, and the following description related to the embodiments may also be referred to, which is not repeated here.
S500, performing sound source localization on the abnormal sound by adopting a sound source localization technology, identifying the tire with the abnormality, specifically, positioning the sound sensor from which the abnormal sound identified in the step S400 originates, further determining that the tire corresponding to the positioned sound sensor has the abnormality, and combining with FIG. 2, for example, forcing the source of the abnormal sound and the microphone 1, then identifying that the tire with the abnormality is the tire corresponding to the microphone 1 (the upper left wheel in the figure).
S600 matches the tire identified as having the abnormality based on the sound source localization with the tire identified as having the abnormality based on the tire pressure state.
S601, if the matching is successful, a tire abnormality warning is issued to the user, for example, by means of display, sound, vibration, etc., to prompt the user that there is an abnormality in the tire.
As one example, if the tire identified as having an abnormality based on the sound source localization is a and the tire identified as having an abnormality based on the tire pressure state is also a, a successful match is indicated, and a tire abnormality warning is issued to the user: the tire A has abnormality and can be used for prompting a user to get off to detect whether the discussion has abnormality or not.
S602, if the matching is unsuccessful, namely, the tire with the abnormality identified based on the sound source localization is not the same tire with the abnormality identified based on the tire pressure state, the sound sensor is turned off. Further, the value of the timer is cleared.
S700, receiving feedback information of a user aiming at abnormal warning of the tire. For example, the user detects feedback that the tire does have an abnormality, or the user detects feedback that the tire does not have an abnormality.
S800, updating an audio database based on feedback information of a user and audio data corresponding to the tire abnormality warning aimed at by the feedback information so as to improve the accuracy of an abnormal sound recognition algorithm in an incremental learning mode.
The prior art is that when the monitored tire pressure value exceeds the threshold value of the tire leakage, the warning is sent out when the tire leakage is judged, and the tire abnormality detection method provided by the embodiment can identify that the tire is abnormal and send out the warning in time through continuous tire pressure reduction and abnormal tire sound monitoring under the condition that the tire does not leak, so that the driving safety of a vehicle is ensured.
In combination with the above embodiments of the present application, the embodiments of the present application provide an abnormal sound recognition method, which may be used to implement step S400 in the corresponding embodiment of fig. 3. As shown in fig. 4, the abnormal sound recognition method includes the steps of:
s301, extracting sound characteristic parameters of the collected audio data. Optionally, prior to extracting the sound characteristic parameters of the audio data, valid sound segments are separated from the audio data, also referred to as end point detection, and the starting point and the stopping point of the abnormal sound are extracted from the audio data. After endpoint detection, sound feature parameters are extracted from the valid sound segments. Accurate endpoint detection can improve abnormal sound recognition accuracy. The endpoint detection can be based on short-time energy and short-time zero-crossing rate, short-time amplitude and short-time dynamic threshold rate and other methods in the prior art, and the endpoint detection method is not repeated.
The sound characteristic parameters may be selected to reflect the audio data according to specific requirements, such as short-time amplitude, mel-frequency cepstral coefficients (Mel Frequency Cepstrum Coefficient, MFCC), MFCC first-order difference coefficients, and the like. Optionally, using the MFCC to characterize the audio data, the method of calculating the MFCC generally includes: decomposing an audio signal (i.e., audio data or active sound segments, as well as the following) into a plurality of frames; pre-emphasis the audio signal through a high pass filter; then, carrying out Fourier transform on the audio signal passing through the high-pass filter, and transforming the audio signal into a frequency domain; passing the spectrum obtained for each frame through a mel filter (triangular overlapping window) to obtain mel scales; extracting logarithmic energy on each mel scale; the result obtained above is subjected to inverse discrete fourier transform to the cepstrum domain. MFCC is the magnitude (amplides) of this cepstral pattern. Typically 12 coefficients are used, which are superimposed with the frame energy to obtain 13-dimensional coefficients. Furthermore, the method for extracting the audio characteristic parameters corresponding to the audio data in the abnormal sound recognition stage adopts the same characteristic parameters as the audio characteristic parameters corresponding to the audio sample extracted in the audio template library stage for training the abnormal sound recognition.
S302, comparing the sound characteristic parameters corresponding to the extracted audio data with an audio template library, and outputting a recognition result. The specific contents include:
for voice characteristic parameters corresponding to audio data to be identifiedRepresenting that the audio data is an audio templateThe maximum a posteriori probability for audio class j in the library is P (λ j I X). According to the bayesian criterion, the maximum posterior probability can be expressed as:
assuming that the audio data to be identified is equal in probability for each type of sound in the audio template library, i.eAnd P (X) is constant and the same. Thus finding lambda by finding the maximum posterior probability j The value of (1) is such that P (X|lambda j ) Maximum. Since the likelihood probability of an audio is multiplied by the likelihood probability of each frame, theIn logarithmic form +.>The identification result is->That is, the probability that the audio data to be recognized is the j-th audio is the largest, and if the j-th audio is an abnormal sound in the audio template library, the audio data to be recognized is output as the abnormal sound.
The recognition rate of abnormal sounds depends greatly on the accuracy of the audio template library obtained by training. The audio template library can be trained by using acoustic models such as hidden Markov models (Hidden Markov Model, HMM), gaussian mixture models (Gaussian Mixture Model, GMM), and the like. Alternatively, the GMM is used for training the audio template library, and a gaussian distribution combination of different parameters can be used for characterizing different audios, i.e. a GMM is corresponding to the characteristic parameter of each audio.
The audio template library training process comprises the following steps: and a sound characteristic parameter extraction stage and an audio template library training stage of the audio sample. In the example of the present application, the acoustic feature parameters employ MFCCs. The specific steps of the voice characteristic parameter extraction stage of the audio sample comprise the following steps:
1) Normalization: the audio samples of each type can be provided with a unified standard, the audio amplitude is normalized between [ -1,1], and the difference between different audio samples is eliminated, namely, each sampling value is divided by the amplitude peak value of the section of signal. The calculation formula is as follows:
where x (i) is the original audio sample,is the normalized audio sample and n is the audio sample length.
2) Pre-emphasis: pre-emphasis may boost high frequency content, flattening the spectrum of the audio sample, for spectral analysis or channel parameter analysis. The transfer function of the pre-emphasis filter z is:
H(z)＝1-μ·z -1 ，
where μ is a constant, typically 0.97.
3) Windowing and framing: in order to ensure the short-time stability of the audio sample, a hamming window function is selected for framing. A typical window size is 25ms and the frame shift is 10ms. The window function is:
w(n)＝(1-α)-α·cos(2πn/(N-1)),0≤n≤N-1，
wherein the window sequence length is N, and alpha is 0.4.
4) MFCC extraction: taking frame length N=256 points, carrying out fast Fourier transform (Fast Fourier Transformation, FFT) transformation on each frame to obtain spectrum parameters, carrying out convolution operation on the spectrum parameters of each frame of data through a Mel frequency filter formed by a group of N triangular band-pass filters, and then taking logarithm of output of each frequency band to obtain logarithm energy S (m) of each output. Finally, discrete cosine transformation is carried out on the N parameters, and the mel cepstrum coefficient is obtained to be used as an audio characteristic parameter. The formula is expressed as:
Wherein n is the number of the MFCCs; c (C) i (n) is the nth MFCC coefficient of the ith frame, S (M) is the logarithmic power spectrum of the audio samples, and M is the number of triangular filters.
It should be noted that the processing method for extracting the sound feature parameters of the audio sample during the training of the audio template library may be applicable to extracting the sound feature parameters of the collected audio data in step S301.
The audio template library training stage may employ GMM, including the following specific steps: aiming at the tire abnormal sound identification scene, an audio sample in the running process of a vehicle under the road conditions of a plurality of scenes and an audio sample in the running process of the vehicle tire pricking foreign matters are stored in an audio template library, sound characteristic parameters are extracted, then GMM is adopted for training, each type of audio sample is obtained, and GMM corresponding to each type of audio sample can be used as lambda j To refer to, the resulting triplet describing the GMM for each type of audio sample:
λ j ＝{P j ,μ j ,Σ j },j＝1,2,…,N，
wherein P is j For the weights of the mixed components, mu j Is the mean vector, Σ j For covariance matrix, N is the mixing order, j is the sample number, and the ternary combination of GMM describing each type of audio sample is the audio template library.
In combination with the above embodiments of the present application, the embodiments of the present application provide a sound source localization analysis method, which may be used to implement step S500 in the corresponding embodiment of fig. 5, including the following steps:
S501, audio data in which abnormal sounds are recognized is input.
S502: according to the audio data with abnormal sound in S501, the audio energy collected by a sound-sensitive sensor (such as a microphone) at a certain moment is obtained.
S503: the distance between the microphone and the sound source position is calculated based on the two-dimensional position coordinates of the corresponding microphone.
With reference to fig. 5, a possible implementation is as follows:
the figure comprises n+1 indiscriminate microphones and sound sources with unknown positions, and the expression that the ith microphone receives energy at the time t is as follows:s (t) is the energy value of the sound source, g i Is the gain coefficient of the ith microphone, d i Is the distance, epsilon, between the i-th microphone and the sound source of unknown position i And (t) is the superimposed background noise energy value. Epsilon for simplifying the calculation i (t) is 0, gi is 1, and the energy value S (t) of the sound source can be set to a certain constant (e.g., 1000). Can be based on the energy measurement result E i (t) calculating the distance from the ith microphone to the sound source at the unknown position +.>
S504: and identifying the sound source of the abnormal sound by adopting a least square method. Specifically, the probability of the sound source of the abnormal sound pointing at which sound-sensitive sensor (e.g., microphone) is the greatest.
Optionally, taking the acoustic sensor as a microphone as an example, the specific implementation is:
Let the two-dimensional position coordinate of the ith microphone be r i ＝(x i ,y i ) I=1, 2, … n, the distance between each microphone i and the sound source of unknown position isThe formula can be obtained: />Wherein i is more than or equal to 1 and n is more than or equal to n. Is obtained by the least square method:
the above equation can be expressed as:
i.e.Wherein->To estimate the pointing position of the sound source of unknown position, again according to +.>The minimum distance between the microphone and the four microphones is obtained, and the minimum value is obtained, so that a certain microphone i pointed by the sound source at the unknown position at the moment t can be obtained.
S505: and identifying the tire with abnormality according to the estimation result of the last step.
Further, based on a certain microphone i pointed by the sound source with unknown position at t moment obtained in S504, continuing to calculate the microphone pointed by the sound source with unknown position at other moment, finally calculating which microphone is pointed by the sound source with unknown position in the whole audio data, and finding out the wheel corresponding to the microphone with the maximum probability based on the position relation between the microphone and the wheel, thereby positioning the tire with abnormality. The sound source localization is to find the position pointed by the sound source at the unknown position of the audio data, so that the tire with the abnormality is identified. In step S600 described in the corresponding embodiment of fig. 3, the tire having the abnormality identified based on the sound source localization is matched with the tire having the abnormality identified based on the tire pressure state, and it is actually whether the tire having the abnormality identified based on the tire pressure state corresponds to the tire having the abnormality at the position where the sound source is directed at the unknown position found based on the sound source localization method. Note that an unknown position sound source, that is, an abnormal sound source, corresponds to an abnormal sound identified by an abnormal sound.
Traditional TPMS can't in time report to the police when the tire pressure takes place to reduce, and the nail inlays in the tire for a long time, threatens passenger's life safety, and often takes place when reporting to the police, the tire pressure has passed through lowly and can't go. Aiming at the problems, the vehicle driving audio data is collected through the microphone, the tire pressure data collected by the tire pressure sensor and the audio data collected by the sound-sensitive sensor are analyzed through the incremental learning type abnormal sound identification technology and the sound source positioning technology based on the GMM, so that the vehicle driving safety can be improved when the tire is abnormal (for example, the tire is pricked into a foreign object), and the identification accuracy can be continuously increased through an incremental learning mode.
An embodiment of the present application provides an apparatus for detecting tire abnormality, as shown in fig. 6, an apparatus 1000 for detecting tire abnormality includes: the tire pressure data acquisition module 1010, the tire pressure analysis module 1020, the audio data acquisition module 1030, the abnormal sound identification module 1040, the sound source localization module 1050, the matching module 1060, the tire air leakage alarm module 1070, the tire abnormal alarm module 1080, the audio template library updating module 1090 and the sound sensor activation module 1110.
The tire pressure data acquisition module 1010 is used for periodically acquiring the tire pressure data of the target tire through the pressure sensor; the tire pressure analysis module 1020 is used for analyzing the periodically collected tire pressure data and identifying that the tire pressure of the target tire is continuously reduced; an audio data acquisition module 1030 for acquiring audio data by the sound sensitive sensor; the abnormal sound identification module 1040 is configured to perform abnormal sound identification on the collected audio data, and identify that abnormal sound exists in the audio data; the sound source localization module 1050 is configured to perform sound source localization analysis on the collected audio data, and identify an abnormal sound source; and the matching module 1060 is used for matching the pointing position of the abnormal sound source with the target tire, and the matching of the pointing position of the abnormal sound source with the target tire indicates that the target tire is abnormal. The continuous decrease in tire pressure of the target tire includes: the first tire pressure data is larger than the second tire pressure data, and the difference value of the first tire pressure data minus the second tire pressure data is not larger than a preset value; the first tire pressure data is tire pressure data of a target tire collected in a first period, the second tire pressure data of the target tire collected in a second period, the first period and the second period are any two adjacent periods in a plurality of continuous periods, and the first period is located before the second period. The plurality of cycles includes at least 3 acquisition cycles.
Further, the tire pressure analysis module 1020 is further configured to: and analyzing the periodically collected tire pressure data to identify that the target tire leaks.
Optionally, the apparatus 1000 further includes: and the tire air leakage alarming module is used for sending out an alarm so as to prompt the user that the target tire is out of air. The occurrence of air leakage of the target tire includes: the third tire pressure data is larger than the fourth tire pressure data, the difference value of the third tire pressure data minus the fourth tire pressure data is larger than a preset value, the third tire pressure data is the tire pressure data of the target tire collected in a third period, the fourth tire pressure data of the target tire collected in a fourth period, the first period and the second period are two adjacent periods, and the third period is located before the fourth period.
The abnormal sound recognition module 1040 is specifically configured to: processing the audio data to obtain sound characteristic parameters corresponding to the audio data; and comparing the sound characteristic parameters corresponding to the audio data with a pre-trained audio template library, and outputting abnormal sounds of the audio data.
The apparatus 1000 further comprises:
the tire abnormality alarming module is used for sending out tire abnormality alarming to prompt a user that the target tire is abnormal; and the audio template library updating module 1090 is used for receiving a feedback result of the user for the tire abnormality alarm and updating the audio template library based on the feedback result and the sound characteristic parameters corresponding to the audio data.
Optionally, the number of sound-sensitive sensors is greater than 1, and the sound source localization module 1050 is specifically configured to: acquiring audio energy acquired by the sound-sensitive sensor based on the audio data; based on the audio energy, the distance of each sound-sensitive sensor relative to the sound source at the unknown position is calculated, wherein the position of the sound-sensitive sensor corresponding to the smallest distance relative to the sound source at the unknown position represents an abnormal sound source.
The apparatus 1000 further comprises a sound sensitive sensor activation module 1110 for activating the sound sensitive sensor associated with the target tire.
The embodiment of the present application provides another tire abnormality detection apparatus, and referring to fig. 7, the tire abnormality detection apparatus 200 may implement the tire abnormality detection method described in the corresponding embodiment of fig. 3. The tire abnormality detection apparatus 200 includes: memory 201, processor 202, communication interface 203, and bus 204. The memory 201, the processor 202, and the communication interface 203 are connected to each other by a bus 204.
Memory 201 may be a read-only memory, a static memory device, a dynamic memory device, or a random access memory. The memory 201 may store a program, and when the program stored in the memory 201 is executed by the processor 202, the processor 202 is configured to execute the tire abnormality detection method described in the embodiment of the present application corresponding to fig. 3.
The processor 202 may be a general-purpose central processing unit, a microprocessor, an application specific integrated circuit, a graphics processor (graphics process ing unit, GPU) or one or more integrated circuits for executing related programs to perform the functions required by the units in the signaling analysis device according to the embodiment of the present application or to perform the image segmentation method according to the embodiment of the method of the present application. The processor may implement the functions of the modules in fig. 6.
The processor 202 may also be an integrated circuit chip with signal processing capabilities. In implementation, the various steps of the image segmentation method of the present application may be accomplished by instructions in the form of integrated logic circuitry of hardware or software in the processor 202. The processor 202 described above may also be a general purpose processor, a digital signal processor (Digital Signal Processing, DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 201, and the processor 202 reads the information in the memory 201, and combines the hardware (such as a display screen) thereof to perform functions required to be performed by the modules included in the tire abnormality detection apparatus 100 of the embodiment of the present application, or to perform the tire abnormality detection method 100 of the method embodiment of the present application.
The communication interface 203 enables communication between the tire anomaly detection apparatus 200 and other devices or communication networks using a transceiver device such as, but not limited to, a transceiver. For example, data of the actual parking space around the vehicle to be parked may be received through the communication interface 203.
Bus 204 may include a path for transferring information between the various components of tire anomaly detection apparatus 200 (e.g., memory 201, processor 202, communication interface 203).
It should be noted that although the tire abnormality detection apparatus 200 shown in fig. 7 shows only a memory, a processor, and a communication interface, those skilled in the art will appreciate that in a specific implementation, the tire abnormality detection apparatus 200 also includes other devices necessary to achieve normal operation. Meanwhile, it should be understood by those skilled in the art that the tire abnormality detection apparatus 200 may further include hardware devices that realize other additional functions according to specific needs. Further, it will be understood by those skilled in the art that the tire abnormality detection apparatus 200 may include only the components necessary to implement the embodiment of the present application, and not necessarily all of the components shown in fig. 7.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (15)
1. A method of detecting anomalies in a tire, comprising:
periodically acquiring tire pressure data of a target tire through a pressure sensor;
analyzing the periodically collected tire pressure data to identify that the tire pressure of the target tire is continuously reduced;
activating an acoustic sensor associated with the target tire;
collecting audio data through the sound-sensitive sensor;
abnormal sound identification is carried out on the audio data, and abnormal sound of the audio data is identified;
performing sound source localization analysis on the audio data to identify an abnormal sound source;
and matching the pointing position of the abnormal sound source with the target tire, wherein the matching of the pointing position of the abnormal sound source with the target tire indicates that the target tire is abnormal.
2. The method of claim 1, wherein the continuous decrease in tire pressure of the target tire comprises: the first tire pressure data is larger than the second tire pressure data, and the difference value of the first tire pressure data minus the second tire pressure data is not larger than a preset value;
the first tire pressure data are tire pressure data of the target tire collected in a first period, the second tire pressure data are tire pressure data of the target tire collected in a second period, the first period and the second period are any two adjacent periods in a plurality of continuous periods, and the first period is located before the second period.
3. The method according to claim 1 or 2, further comprising:
analyzing the periodically collected tire pressure data to identify that the target tire has air leakage;
and sending out an alarm to prompt the user that the target tire leaks.
4. A method according to claim 3, wherein the occurrence of a puncture in the target tyre comprises: the third tire pressure data is greater than the fourth tire pressure data, the difference of the third tire pressure data minus the fourth tire pressure data is greater than a preset value, the third tire pressure data is the tire pressure data of the target tire collected in a third period, the fourth tire pressure data is the tire pressure data of the target tire collected in a fourth period, the third period and the fourth period are two adjacent periods, and the third period is located before the fourth period.
5. The method of any of claims 1-4, wherein the identifying the audio data for an anomaly, comprises:
processing the audio data to obtain sound characteristic parameters corresponding to the audio data;
and comparing the sound characteristic parameters corresponding to the audio data with a pre-trained audio template library, and outputting abnormal sounds of the audio data.
6. The method as recited in claim 5, further comprising:
a tire abnormality alarm is sent out to prompt a user that the target tire is abnormal;
receiving a feedback result of the user for the tire abnormality alarm;
and updating the audio template library based on the feedback result and the sound characteristic parameters corresponding to the audio data.
7. The method of any one of claims 1-6, wherein the number of sound sensitive sensors is greater than 1, wherein performing sound source localization analysis on the audio data identifies an abnormal sound source, comprising:
acquiring audio energy acquired by the sound-sensitive sensor based on the audio data;
and calculating the distance of each sound-sensitive sensor relative to the sound source at the unknown position based on the audio energy, wherein the position of the sound-sensitive sensor corresponding to the minimum distance relative to the sound source at the unknown position represents the abnormal sound source.
8. An apparatus for detecting anomalies in tires, comprising:
the tire pressure data acquisition module is used for periodically acquiring the tire pressure data of the target tire through the pressure sensor;
the tire pressure analysis module is used for analyzing the periodically acquired tire pressure data and identifying that the tire pressure of the target tire is continuously reduced;
A sound-sensitive sensor activation module for activating the sound-sensitive sensor associated with the target tire;
the audio data acquisition module is used for acquiring audio data through the sound-sensitive sensor;
the abnormal sound identification module is used for carrying out abnormal sound identification on the audio data and identifying that abnormal sound exists in the audio data;
the sound source positioning module is used for carrying out sound source positioning analysis on the audio data and identifying an abnormal sound source;
and the matching module is used for matching the pointing position of the abnormal sound source with the target tire, and the matching of the pointing position of the abnormal sound source with the target tire indicates that the target tire is abnormal.
9. The apparatus of claim 8, wherein the continuous decrease in tire pressure of the target tire comprises: the first tire pressure data is larger than the second tire pressure data, and the difference value of the first tire pressure data minus the second tire pressure data is not larger than a preset value;
the first tire pressure data are tire pressure data of the target tire collected in a first period, the second tire pressure data are tire pressure data of the target tire collected in a second period, the first period and the second period are any two adjacent periods in a plurality of continuous periods, and the first period is located before the second period.
10. The apparatus of claim 8 or 9, wherein the tire pressure analysis module is further to: analyzing the periodically collected tire pressure data to identify that the target tire has air leakage;
the apparatus further comprises:
and the tire air leakage alarming module is used for sending out an alarm so as to prompt the user that the target tire is out of air.
11. The apparatus of claim 10, wherein the occurrence of a puncture in the target tire comprises: the third tire pressure data is greater than the fourth tire pressure data, the difference of the third tire pressure data minus the fourth tire pressure data is greater than a preset value, the third tire pressure data is the tire pressure data of the target tire collected in a third period, the fourth tire pressure data is the tire pressure data of the target tire collected in a fourth period, the third period and the fourth period are two adjacent periods, and the third period is located before the fourth period.
12. The apparatus according to any one of claims 8-11, wherein the abnormal sound identification module is specifically configured to:
processing the audio data to obtain sound characteristic parameters corresponding to the audio data;
And comparing the sound characteristic parameters corresponding to the audio data with a pre-trained audio template library, and outputting abnormal sounds of the audio data.
13. The apparatus as recited in claim 12, further comprising:
the tire abnormality alarming module is used for sending out tire abnormality alarming to prompt a user that the target tire is abnormal;
and the audio template library updating module is used for receiving a feedback result of the user for the tire abnormality alarm and updating the audio template library based on the feedback result and the sound characteristic parameters corresponding to the audio data.
14. The apparatus according to any one of claims 8-13, wherein the number of sound sensitive sensors is greater than 1, the sound source localization module being specifically configured to:
acquiring audio energy acquired by the sound-sensitive sensor based on the audio data;
and calculating the distance of each sound-sensitive sensor relative to the sound source at the unknown position based on the audio energy, wherein the position of the sound-sensitive sensor corresponding to the minimum distance relative to the sound source at the unknown position represents the abnormal sound source.
15. A control unit comprising programmable instructions which when invoked are adapted to perform the method of any one of claims 1-7.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2021/071370 WO2022150999A1 (en) | 2021-01-13 | 2021-01-13 | Tire abnormality detection method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115052761A CN115052761A (en) | 2022-09-13 |
| CN115052761B true CN115052761B (en) | 2023-11-03 |
Family
ID=82446479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202180000477.8A Active CN115052761B (en) | 2021-01-13 | 2021-01-13 | Method and device for detecting tire abnormality |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115052761B (en) |
| WO (1) | WO2022150999A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115880925A (en) * | 2022-11-30 | 2023-03-31 | 东风汽车有限公司东风日产乘用车公司 | Tire puncture auxiliary identification method, device, equipment and storage medium |
| CN116051897B (en) * | 2023-01-28 | 2023-06-27 | 合肥中科类脑智能技术有限公司 | Door opening and closing state detection method and device, edge processing equipment and storage medium |
| CN117589480B (en) * | 2024-01-18 | 2024-05-10 | 山东中亚轮胎试验场有限公司 | Tire abnormal state detecting system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102717671A (en) * | 2012-07-10 | 2012-10-10 | 江苏科技大学 | Vehicle tyre burst detection emergency method |
| CN104908645A (en) * | 2015-06-08 | 2015-09-16 | 上海斐讯数据通信技术有限公司 | Auxiliary vehicle driving system and working method thereof |
| KR20160066755A (en) * | 2014-12-03 | 2016-06-13 | 현대모비스 주식회사 | Apparatus and Method for detecting error of wheel alignment |
| CN107458383A (en) * | 2016-06-03 | 2017-12-12 | 法拉第未来公司 | Use the vehicle trouble automatic detection of audio signal |
| CN107499069A (en) * | 2017-09-08 | 2017-12-22 | 江苏金坛绿能新能源科技有限公司 | Vehicle tyre flat tire prewarning device |
| CN109017166A (en) * | 2018-08-16 | 2018-12-18 | 杭州容大智造科技有限公司 | A kind of equipment using sound detection tire pressure |
| CN111890850A (en) * | 2020-09-10 | 2020-11-06 | 李光明 | Tire noise monitoring and alarming system and method for preventing tire burst of automobile |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09145501A (en) * | 1995-11-20 | 1997-06-06 | Yokohama Rubber Co Ltd:The | Method and apparatus for measuring tire fitting pressure |
| CN101973192B (en) * | 2010-10-03 | 2013-01-30 | 燕山大学 | Method for monitoring tire pressure during corning process of automobile |
| WO2012162241A2 (en) * | 2011-05-20 | 2012-11-29 | Northeastern University | Real-time wireless dynamic tire pressure sensor and energy harvesting system |
| CN203580528U (en) * | 2013-11-29 | 2014-05-07 | 山东永泰化工有限公司 | Tire abnormity monitoring device |
| TWI593571B (en) * | 2016-05-06 | 2017-08-01 | Mobiletron Electronics Co Ltd | Tire monitoring methods |
| CN107933212A (en) * | 2017-10-23 | 2018-04-20 | 深圳市招科智控科技有限公司 | Harbour container is horizontal to carry the quick-fried detecting system of unmanned vehicle tire tire and method |
| CN110789278A (en) * | 2018-08-02 | 2020-02-14 | 郑州宇通客车股份有限公司 | Tire pressure monitoring method and device |
-
2021
- 2021-01-13 WO PCT/CN2021/071370 patent/WO2022150999A1/en active Application Filing
- 2021-01-13 CN CN202180000477.8A patent/CN115052761B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102717671A (en) * | 2012-07-10 | 2012-10-10 | 江苏科技大学 | Vehicle tyre burst detection emergency method |
| KR20160066755A (en) * | 2014-12-03 | 2016-06-13 | 현대모비스 주식회사 | Apparatus and Method for detecting error of wheel alignment |
| CN104908645A (en) * | 2015-06-08 | 2015-09-16 | 上海斐讯数据通信技术有限公司 | Auxiliary vehicle driving system and working method thereof |
| CN107458383A (en) * | 2016-06-03 | 2017-12-12 | 法拉第未来公司 | Use the vehicle trouble automatic detection of audio signal |
| CN107499069A (en) * | 2017-09-08 | 2017-12-22 | 江苏金坛绿能新能源科技有限公司 | Vehicle tyre flat tire prewarning device |
| CN109017166A (en) * | 2018-08-16 | 2018-12-18 | 杭州容大智造科技有限公司 | A kind of equipment using sound detection tire pressure |
| CN111890850A (en) * | 2020-09-10 | 2020-11-06 | 李光明 | Tire noise monitoring and alarming system and method for preventing tire burst of automobile |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022150999A1 (en) | 2022-07-21 |
| CN115052761A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115052761B (en) | Method and device for detecting tire abnormality | |
| US10224053B2 (en) | Audio signal quality enhancement based on quantitative SNR analysis and adaptive Wiener filtering | |
| JP5837341B2 (en) | Road surface condition determination method and apparatus | |
| KR100870889B1 (en) | Sound signal processing method, sound signal processing apparatus and recording medium | |
| CN113380272A (en) | Audio-based emergency vehicle detection and tracking | |
| WO2020143089A1 (en) | Automobile interior noise detection method and device and computer equipment | |
| US9733346B1 (en) | Method for providing sound detection information, apparatus detecting sound around vehicle, and vehicle including the same | |
| JP2008076881A (en) | Speech recognizing method and device, and computer program | |
| JP2012242214A (en) | Strange noise inspection method and strange noise inspection device | |
| CN112529177A (en) | Vehicle collision detection method and device | |
| CN113837150B (en) | Non-contact tire pressure obtaining method based on computer vision and related device | |
| Couvreur et al. | Automatic noise recognition in urban environments based on artificial neural networks and hidden markov models | |
| Bulatović et al. | Mel-spectrogram features for acoustic vehicle detection and speed estimation | |
| CN113674763A (en) | Whistling sound identification method, system, equipment and storage medium by utilizing line spectrum characteristics | |
| CN113345443A (en) | Marine mammal vocalization detection and identification method based on mel-frequency cepstrum coefficient | |
| Kubo et al. | Design of ultra low power vehicle detector utilizing discrete wavelet transform | |
| CN112230208B (en) | Automobile running speed detection method based on smart phone audio perception | |
| CN116910690A (en) | Target classification system based on data fusion | |
| CN116364108A (en) | Transformer voiceprint detection method and device, electronic equipment and storage medium | |
| CN115346514A (en) | Intelligent driving evaluation-oriented audio early warning intelligent identification method | |
| CN109318862A (en) | Applied mental-acoustics index vehicle rain detector | |
| CN111968671B (en) | Low-altitude sound target comprehensive identification method and device based on multidimensional feature space | |
| Oettle et al. | Assessing the aeroacoustic response of a vehicle to transient flow conditions from the perspective of a vehicle occupant | |
| JP7112909B2 (en) | Tire type discrimination method and tire type discrimination device | |
| Astapov et al. | A method of real-time mobile vehicle identification by means of acoustic noise analysis implemented on an embedded device |
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 |