System and method for vehicle noise localization

Abstract

A system for vehicle noise localization includes a plurality of vehicle sensors. The plurality of vehicle sensors includes at least one of a microphone, a vibration sensor, a vehicle road speed sensor, and a vehicle motor speed sensor. The system also includes a controller in electrical communication with the plurality of vehicle sensors. The controller is programmed to perform a plurality of measurements on noise generated by a faulty component of a vehicle using a plurality of vehicle sensors. The controller is further programmed to determine a location of a faulty component within the vehicle using at least one of a machine learning based method and an analysis method based at least in part on the plurality of measurements. The controller is also programmed to identify a faulty component of the vehicle based at least in part on the location of the faulty component within the vehicle.

Description

Technical Field

[0001] The present disclosure relates to systems and methods for vehicle noise localization, and more particularly to systems and methods for determining the location of a faulty component within a vehicle. Background Art

[0002] To improve occupant awareness and convenience, a vehicle may be equipped with an on-board diagnostic (OBD) system that is configured to collect and store data about the operation of vehicle systems for diagnostic purposes. The OBD system may use a variety of sensors and data analysis techniques to collect data about the operation of vehicle systems. The data may include, for example, engine / motor performance, emission levels, transmission performance, safety system performance, etc. If there is an anomaly in the data, the OBD system may save one or more diagnostic trouble codes (DTCs) and remind the vehicle occupant to send the vehicle for repair. A maintenance technician may connect a diagnostic device to the OBD system to read the saved DTCs and further analyze the data collected by the OBD system. However, the OBD system may not be able to resolve noise and / or vibrations generated by degraded, damaged and / or faulty components of the vehicle. For example, a purely mechanical component without any electrical sensors that communicate with the OBD system may not be monitored or diagnosed by the OBD system.

[0003] Therefore, while on-board diagnostic systems and methods achieve their intended purposes, a need remains for a new and improved system and method for determining the location of a faulty component within a vehicle. Summary of the invention

[0004] According to several aspects, a system for vehicle noise localization is provided. The system includes a plurality of vehicle sensors. The plurality of vehicle sensors include at least one of a microphone, a vibration sensor, a vehicle road speed sensor, and a vehicle motor speed sensor. The system also includes a controller in electrical communication with the plurality of vehicle sensors. The controller is programmed to perform a plurality of measurements of noise generated by a faulty component of the vehicle using the plurality of vehicle sensors. The controller is further programmed to determine the location of the faulty component within the vehicle based at least in part on the plurality of measurements using at least one of a machine learning-based method and an analytical method. The controller is further programmed to identify the faulty component of the vehicle based at least in part on the location of the faulty component within the vehicle.

[0005] In another aspect of the present disclosure, in order to determine the location of a faulty component in a vehicle using a machine learning-based method, the controller is further programmed to input a plurality of measurements into a machine learning algorithm. The machine learning algorithm is configured to receive a plurality of measurements as input and generate a plurality of probabilities as output. Each of the plurality of probabilities corresponds to a probability that the noise in the plurality of measurements comes from a particular location in the vehicle. In order to determine the location of a faulty component in a vehicle using a machine learning-based method, the controller is further programmed to determine the location of the faulty component in the vehicle based at least in part on the plurality of probabilities.

[0006] In another aspect of the present disclosure, the plurality of vehicle sensors include at least three vibration sensors. Each of the at least three vibration sensors is fixed to a different position in the vehicle. To perform the plurality of measurements, the controller is further programmed to perform a first plurality of vibration measurements using a first vibration sensor in the plurality of vehicle sensors. To perform the plurality of measurements, the controller is further programmed to perform a second plurality of vibration measurements using a second vibration sensor in the plurality of vehicle sensors. To perform the plurality of measurements, the controller is further programmed to perform a third plurality of vibration measurements using a third vibration sensor in the plurality of vehicle sensors.

[0007] In another aspect of the present disclosure, in order to determine the location of the faulty component in the vehicle using the analysis method, the controller is also programmed to identify a vibration event based at least in part on the first, second and third plurality of vibration measurements. The vibration event comes from the location of the faulty component in the vehicle. The vibration event includes at least three vibration pairs. The first vibration pair is detected in the first plurality of vibration measurements, the second vibration pair is detected in the second plurality of vibration measurements, and the third vibration pair is detected in the third plurality of vibration measurements. Each of the first, second and third vibration pairs includes a longitudinal vibration and a lateral vibration. In order to determine the location of the faulty component in the vehicle using the analysis method, the controller is also programmed to determine a first distance between the first vibration sensor and the faulty component based at least in part on the difference between the receiving time of the longitudinal vibration of the first vibration pair and the receiving time of the lateral vibration of the first vibration pair. In order to determine the location of the faulty component in the vehicle using the analysis method, the controller is also programmed to determine a second distance between the second vibration sensor and the faulty component based at least in part on the difference between the receiving time of the longitudinal vibration of the second vibration pair and the receiving time of the lateral vibration of the second vibration pair. To determine the location of the faulty component in the vehicle using the analytical method, the controller is further programmed to determine a third distance between the third vibration sensor and the faulty component based at least in part on a difference between a reception time of the longitudinal vibration of the third vibration pair and a reception time of the lateral vibration of the third vibration pair. To determine the location of the faulty component in the vehicle using the analytical method, the controller is further programmed to determine the location of the faulty component using trilateration based at least in part on the first distance, the second distance, and the third distance.

[0008] In another aspect of the present disclosure, to identify a vibration event, the controller is further programmed to perform a spectrum analysis to identify a plurality of frequencies present in the first, second, and third plurality of vibration measurements. To identify a vibration event, the controller is further programmed to compare the plurality of frequencies to a normal operating frequency range. To identify a vibration event, the controller is further programmed to identify a vibration event in response to determining that at least one of the plurality of frequencies is outside the normal operating frequency range.

[0009] In another aspect of the present disclosure, to identify a vibration event, the controller is further programmed to input the first, second, and third plurality of vibration measurements into a machine learning algorithm. The machine learning algorithm is configured to use unsupervised learning to separate the first, second, and third plurality of vibration measurements into a normal measurement subset and an abnormal measurement subset. To identify a vibration event, the controller is further programmed to identify a vibration event based at least in part on the abnormal measurement subset.

[0010] In another aspect of the present disclosure, the plurality of vehicle sensors include at least three microphones. Each of the at least three microphones is fixed at a different location in the vehicle. To perform the plurality of measurements, the controller is further programmed to perform a first plurality of noise measurements using a first microphone of the at least three microphones. To perform the plurality of measurements, the controller is further programmed to perform a second plurality of noise measurements using a second microphone of the at least three microphones. To perform the plurality of measurements, the controller is further programmed to perform a third plurality of noise measurements using a third microphone of the at least three microphones.

[0011] In another aspect of the present disclosure, in order to determine the location of the faulty component in the vehicle using the analytical method, the controller is also programmed to identify a noise event based at least in part on the first, second, and third plurality of noise measurements. The noise event comes from the location of the faulty component in the vehicle. In order to determine the location of the faulty component in the vehicle using the analytical method, the controller is also programmed to determine a first possible position range of the faulty component relative to the first of at least three microphones and the second of at least three microphones based at least in part on the first phase difference between the first plurality of noise measurements and the second plurality of noise measurements. In order to determine the location of the faulty component in the vehicle using the analytical method, the controller is also programmed to determine a second possible position range of the faulty component relative to the first of at least three microphones and the third of at least three microphones based at least in part on the second phase difference between the first plurality of noise measurements and the third plurality of noise measurements. In order to determine the location of the faulty component in the vehicle using the analytical method, the controller is also programmed to determine a third possible position range of the faulty component relative to the second of at least three microphones and the third of at least three microphones based at least in part on the third phase difference between the second plurality of noise measurements and the third plurality of noise measurements. To determine the location of the faulty component within the vehicle using the analytical method, the controller is further programmed to determine the location of the faulty component based at least in part on the first possible position range, the second possible position range, and the third possible position range.

[0012] In another aspect of the present disclosure, the controller is further programmed to scan the location of the faulty component using a beamforming microphone array to detect noise generated by the faulty component.

[0013] In another aspect of the present disclosure, the controller is further programmed to use an analytical method to determine a possible location of a faulty component within the vehicle based at least in part on the plurality of measurements. The controller is further programmed to use a machine learning-based method to determine a location of a faulty component within the vehicle based at least in part on the plurality of measurements and possible locations.

[0014] According to several aspects, a method for noise localization is provided. The method includes performing a plurality of measurements of noise generated by a faulty component using a plurality of vehicle sensors. The method also includes determining a location of the faulty component based at least in part on the plurality of measurements using at least one of a machine learning-based method and an analytical method, and identifying the faulty component based at least in part on the location of the faulty component.

[0015] In another aspect of the present disclosure, determining the location of the faulty component using a machine learning-based method may also include inputting a plurality of measurements into a machine learning algorithm. The machine learning algorithm is configured to receive a plurality of measurements as input and generate a plurality of probabilities as output. Each of the plurality of probabilities corresponds to a probability that the noise in the plurality of measurements is from a particular location. Determining the location of the faulty component using a machine learning-based method may also include determining the location of the faulty component based at least in part on the plurality of probabilities.

[0016] In another aspect of the present disclosure, performing multiple measurements may also include performing a first plurality of vibration measurements using a first vibration sensor in the plurality of vehicle sensors. Performing multiple measurements may also include performing a second plurality of vibration measurements using a second vibration sensor in the plurality of vehicle sensors. Performing multiple measurements may also include performing a third plurality of vibration measurements using a third vibration sensor in the plurality of vehicle sensors.

[0017] In another aspect of the present disclosure, determining the location of the faulty component using the analysis method may also include identifying a vibration event based at least in part on the first, second, and third plurality of vibration measurements. The vibration event is from the location of the faulty component. The vibration event includes at least three vibration pairs. The first vibration pair is detected in the first plurality of vibration measurements, the second vibration pair is detected in the second plurality of vibration measurements, and the third vibration pair is detected in the third plurality of vibration measurements. Each of the first, second, and third vibration pairs includes a longitudinal vibration and a lateral vibration. Determining the location of the faulty component using the analysis method may also include determining a first distance between the first vibration sensor and the faulty component based at least in part on the difference between the receiving time of the longitudinal vibration of the first vibration pair and the receiving time of the lateral vibration of the first vibration pair. Determining the location of the faulty component using the analysis method may also include determining a second distance between the second vibration sensor and the faulty component based at least in part on the difference between the receiving time of the longitudinal vibration of the second vibration pair and the receiving time of the lateral vibration of the second vibration pair. Determining the location of the faulty component using the analysis method may also include determining a third distance between the third vibration sensor and the faulty component based at least in part on the difference between the receiving time of the longitudinal vibration of the third vibration pair and the receiving time of the lateral vibration of the third vibration pair. Using the analytical method to determine the location of the faulty component may also include using trilateration to determine the location of the faulty component based at least in part on the first distance, the second distance, and the third distance.

[0018] In another aspect of the present disclosure, identifying a vibration event may further include performing a spectrum analysis to identify a plurality of frequencies present in the first, second, and third plurality of vibration measurements. Identifying a vibration event may further include comparing the plurality of frequencies to a normal operating frequency range. Identifying a vibration event may further include identifying a vibration event in response to determining that at least one of the plurality of frequencies is outside the normal operating frequency range.

[0019] In another aspect of the present disclosure, performing multiple measurements may further include performing a first plurality of noise measurements using a first microphone of at least three microphones. Performing multiple measurements may further include performing a second plurality of noise measurements using a second microphone of at least three microphones. Performing multiple measurements may further include performing a third plurality of noise measurements using a third microphone of at least three microphones.

[0020] In another aspect of the present disclosure, determining the location of the faulty component using the analysis method may also include identifying a noise event based at least in part on the first, second, and third plurality of noise measurements. The noise event comes from the location of the faulty component. Determining the location of the faulty component using the analysis method may also include determining a first possible position range of the faulty component relative to the first of at least three microphones and the second of at least three microphones based at least in part on a first phase difference between the first plurality of noise measurements and the second plurality of noise measurements. Determining the location of the faulty component using the analysis method may also include determining a second possible position range of the faulty component relative to the first of at least three microphones and the third of at least three microphones based at least in part on a second phase difference between the first plurality of noise measurements and the third plurality of noise measurements. Determining the location of the faulty component using the analysis method may also include determining a third possible position range of the faulty component relative to the second of at least three microphones and the third of at least three microphones based at least in part on a third phase difference between the second plurality of noise measurements and the third plurality of noise measurements. Determining the location of the faulty component using the analysis method may also include determining the location of the faulty component based at least in part on the first possible position range, the second possible position range, and the third possible position range.

[0021] According to several aspects, a system for locating vehicle noise is provided. The system includes a plurality of vehicle sensors. The plurality of vehicle sensors include at least three microphones. Each of the at least three microphones is fixed at a different location in the vehicle. The system also includes a controller in electrical communication with the plurality of vehicle sensors. The controller is programmed to perform a plurality of measurements of noise generated by a faulty component of the vehicle using each of the at least three microphones. The controller is also programmed to determine the location of the faulty component within the vehicle based at least in part on the plurality of measurements. The controller is also programmed to identify the faulty component of the vehicle based at least in part on the location of the faulty component within the vehicle.

[0022] In another aspect of the present disclosure, to perform multiple measurements, the controller is further programmed to perform a first plurality of noise measurements using a first microphone of at least three microphones. To perform multiple measurements, the controller is further programmed to perform a second plurality of noise measurements using a second microphone of at least three microphones. To perform multiple measurements, the controller is further programmed to perform a third plurality of noise measurements using a third microphone of at least three microphones.

[0023] In another aspect of the present disclosure, in order to determine the location of the faulty component in the vehicle, the controller is further programmed to identify a noise event based at least in part on the first, second and third plurality of noise measurements. The noise event comes from the location of the faulty component in the vehicle. In order to determine the location of the faulty component in the vehicle, the controller is further programmed to determine a first possible position range of the faulty component relative to the first of at least three microphones and the second of at least three microphones based at least in part on the first phase difference between the first plurality of noise measurements and the second plurality of noise measurements. In order to determine the location of the faulty component in the vehicle, the controller is further programmed to determine a second possible position range of the faulty component relative to the first of at least three microphones and the third of at least three microphones based at least in part on the second phase difference between the first plurality of noise measurements and the third plurality of noise measurements. In order to determine the location of the faulty component in the vehicle, the controller is further programmed to determine a third possible position range of the faulty component relative to the second of at least three microphones and the third of at least three microphones based at least in part on the third phase difference between the second plurality of noise measurements and the third plurality of noise measurements. In order to determine the location of the faulty component in the vehicle, the controller is further programmed to determine the location of the faulty component based at least in part on the first possible position range, the second possible position range and the third possible position range.

[0024] Further areas of applicability will become apparent from the description provided herein.It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.

[0026] Figure 1 is a schematic diagram of a system for vehicle noise localization according to an exemplary embodiment;

[0027] Figure 2 is a schematic diagram of a first embodiment of a system for vehicle noise localization according to an exemplary embodiment;

[0028] Figure 3 is a schematic diagram of a second embodiment of a system for vehicle noise localization according to an exemplary embodiment;

[0029] Figure 4 is a flow chart of a method for noise localization according to an exemplary embodiment;

[0030] Figure 5 is a flow chart of a first embodiment of a method for determining a location of a faulty component according to an exemplary embodiment;

[0031] Figure 6 is a flow chart of a second embodiment of a method for determining a location of a faulty component according to an exemplary embodiment;

[0032] Figure 7 is a flow chart of a first embodiment of a method for identifying a vibration event according to an exemplary embodiment;

[0033] Figure 8 is a flow chart of a second embodiment of a method for identifying a vibration event according to an exemplary embodiment; and

[0034] Fig. 9 is a flow chart of a third embodiment of a method for determining a location of a faulty component according to an exemplary embodiment. DETAILED DESCRIPTION

[0035] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses.

[0036] Once degraded, malfunctioned and / or failed, the electrical and / or mechanical components of a vehicle may generate abnormal vibrations and / or noise. As part of the diagnostic process, a maintenance technician may evaluate the abnormal noise generated by the vehicle. However, some noise and / or vibrations are imperceptible to human senses due to reasons such as volume and / or frequency level. In addition, it can be challenging to locate a faulty component that is the source of abnormal noise and / or vibration in a complex vehicle system, especially when the abnormal noise and / or vibration is primarily generated when the vehicle is in motion. Therefore, the present disclosure provides a new and improved system and method for locating a faulty component in a vehicle that generates abnormal noise and / or vibration.

[0037] refer to Figure 1 , a system for vehicle noise localization is shown, generally indicated by reference numeral 10. The system 10 is shown with an exemplary vehicle 12. Although a passenger vehicle is shown, it should be understood that the vehicle 12 can be any type of vehicle without departing from the scope of the present disclosure. The system 10 generally includes a controller 14 and a plurality of vehicle sensors 16.

[0038] The controller 14 is used to implement the noise localization method 100, as described below. The controller 14 includes at least one processor 18 and a non-transitory computer-readable storage device or medium 20. The processor 18 can be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor of several processors associated with the controller 14, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or a device generally used to execute instructions. The computer-readable storage device or medium 20 can include volatile and non-volatile storage devices such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables when the processor 18 is powered off. The computer readable storage device or medium 20 may be implemented using a plurality of storage devices, such as a PROM (Programmable Read Only Memory), an EPROM (Electrically Programmable Read Only Memory), an EEPROM (Electrically Erasable Read Only Memory), a flash memory, or other electrical, magnetic, optical, or combination storage device capable of storing data, some of which represents executable instructions used by the controller 14 to control the various systems of the vehicle 12. The controller 14 may also be comprised of multiple controllers in electrical communication with each other. The controller 14 may be interconnected with other systems and / or controllers of the vehicle 12, thereby allowing the controller 14 to access data such as the speed, acceleration, braking, and steering angle of the vehicle 12.

[0039] The controller 14 is in electrical communication with a plurality of vehicle sensors 16. In an exemplary embodiment, the electrical communication is established using, for example, a CAN network, a FLEXRAY network, a local area network (e.g., WiFi, Ethernet, etc.), a serial peripheral interface (SPI) network, etc. It should be understood that various other wired and wireless technologies and communication protocols for communicating with the controller 14 are within the scope of the present disclosure.

[0040] The plurality of vehicle sensors 16 are used to detect and measure vibrations and / or sound waves generated by a faulty component 22 in the vehicle 12. Within the scope of the present disclosure, the faulty component 22 is a mechanical and / or electrical component that requires repair. The faulty component 22 may include, for example, suspension components (such as connecting rods, shock absorbers, struts, etc.), engine components (such as ignition coils, crankshafts, timing chains, etc.), transmission components, electric drive system components (such as electric motors), and / or the like. Due to the degraded state of the faulty component 22, the faulty component 22 may generate noise and / or vibrations during operation, which may be detected by the plurality of vehicle sensors 16.

[0041] refer to Figure 2, shows a first exemplary embodiment 10a of the system 10. In the first exemplary embodiment 10a, the plurality of vehicle sensors 16 includes at least a first vibration sensor 24a, a second vibration sensor 24b, and a third vibration sensor 24c.

[0042] The first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c are used to detect vibrations generated by the faulty component 22 and transmitted through the structure of the vehicle 12. In an exemplary embodiment, the first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c are fixed at different locations in the vehicle 12.

[0043] In a non-limiting example, the first vibration sensor 24a is fixed near the front of the vehicle 12 (e.g., in the engine compartment of the vehicle 12). The second vibration sensor 24b is fixed near the middle portion of the vehicle 12 (e.g., on the frame of the vehicle 12 in the passenger compartment of the vehicle 12). The third vibration sensor 24c is fixed near the rear of the vehicle 12 (e.g., in the cargo area of ​​the vehicle 12). In an exemplary embodiment, the first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c are fixedly coupled to a structural component of the vehicle 12 (e.g., the frame of the vehicle 12, the body pillars of the vehicle 12, and / or the like) so that vibrations are effectively transmitted to the first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c.

[0044] In an exemplary embodiment, the first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c can measure and distinguish between lateral vibration and longitudinal vibration. Within the scope of the present disclosure, lateral vibration refers to a vibration perpendicular to the direction in which the lateral vibration wave propagates in the medium, causing the medium particles that transmit the lateral vibration to be displaced. Longitudinal vibration refers to a vibration parallel to the direction in which the longitudinal vibration wave propagates in the medium, causing the medium particles that transmit the longitudinal vibration to be displaced. Lateral vibration and longitudinal vibration propagate at different speeds. In an exemplary embodiment, the first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c are accelerometers. It should be understood that the first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c can be any sensor that can detect and measure lateral vibration and longitudinal vibration. In some embodiments, the first vibration sensor 24a, the second vibration sensor 24b, and the third vibration sensor 24c can also each include a microphone.

[0045] refer to Figure 3 , a second exemplary embodiment 10b of the system 10 is shown. In the second exemplary embodiment 10b, the plurality of vehicle sensors 16 include at least a first microphone 26a, a second microphone 26b, and a third microphone 26c.

[0046] The first microphone 26a, the second microphone 26b, and the third microphone 26c are used to detect noise generated by the faulty component 22. In an exemplary embodiment, the first microphone 26a, the second microphone 26b, and the third microphone 26c are fixed at different locations in the vehicle 12.

[0047] In a non-limiting example, the first microphone 26a is secured near the front of the vehicle 12 (e.g., in the engine compartment of the vehicle 12). The second microphone 26b is secured near the middle portion of the vehicle 12 (e.g., on the frame of the vehicle 12 in the passenger compartment of the vehicle 12). The third microphone 26c is secured near the rear of the vehicle 12 (e.g., in the cargo area of ​​the vehicle 12).

[0048] In an exemplary embodiment, each of the first microphone 26a, the second microphone 26b, and the third microphone 26c includes at least one microphone. Based on the difference in arrival time and / or power level of the received noise between the first microphone 26a, the second microphone 26b, and the third microphone 26c, the position direction of the faulty component 22 relative to each of the first microphone 26a, the second microphone 26b, and the third microphone 26c can be determined.

[0049] For a given one of the first microphone 26a, the second microphone 26b, and the third microphone 26c, if the faulty component 22 is located in a specific area (sometimes referred to as a confusion cone 30) relative to a given pair of microphones, the position direction of the faulty component 22 may be ambiguous. The axis of the confusion cone 30 is located on the axis between the pair of microphones. In some cases, the two microphones may not be able to clearly locate the noise emitted from a certain position on the circumference of the conical slice of the confusion cone 30. This is because, for the noise emitted from a certain position on the circumference of the conical slice of the confusion cone 30, there is no difference in the arrival time or power level of the signals received by any two microphones of the first microphone 26a, the second microphone 26b, and the third microphone 26c. Therefore, in the second exemplary embodiment 10b, the plurality of vehicle sensors 16 include three microphones (i.e., the first microphone 26a, the second microphone 26b, and the third microphone 26c), so that the faulty component 22 can be accurately located.

[0050] In a non-limiting example, each of the first microphone 26a, the second microphone 26b, and the third microphone 26c includes at least one micro-electromechanical system (MEMS) microphone (e.g., a microphone having a pressure-sensitive diaphragm etched directly into a silicon wafer). It should be understood that other types of microphones configured to convert sound waves into electrical signals (e.g., digital and / or analog electrical signals) are also included within the scope of the present disclosure.

[0051] In an exemplary embodiment, one or more of the first microphone 26a, the second microphone 26b, and the third microphone 26c may include a beamforming microphone array. Within the scope of the present disclosure, "beamforming" refers to the process of forming a directional sensitivity beam toward a desired noise source while suppressing noise and interference from other directions. In a non-limiting example, the beamforming microphone array uses a signal processing algorithm to analyze the signals received from each microphone and selectively combines them to form a directional sensitivity beam. As will be discussed in more detail below, once the possible location of the faulty component 22 is determined, the beamforming microphone array can be used to scan the possible location to confirm and / or improve the accuracy of determining the location of the faulty component 22.

[0052] It should be understood that in both the first exemplary embodiment 10a and the second exemplary embodiment 10b, the plurality of vehicle sensors 16 also include sensors for determining performance data regarding the vehicle 12. In an exemplary embodiment, the plurality of vehicle sensors 16 also include at least one of a motor speed sensor, a motor torque sensor, a road speed sensor, an electric drive motor voltage and / or current sensor, an accelerator pedal position sensor, a coolant temperature sensor, a cooling fan speed sensor, and a transmission oil temperature sensor.

[0053] In another exemplary embodiment, the plurality of vehicle sensors 16 also include sensors for determining environmental information within the vehicle 12 , such as seat occupancy sensors, cabin air temperature sensors, cabin motion detection sensors, cabin cameras, cabin microphones, etc.

[0054] In another exemplary embodiment, the plurality of vehicle sensors 16 also includes sensors for determining information about the environment surrounding the vehicle 12 , such as an ambient air temperature sensor, an atmospheric pressure sensor, and / or a camera positioned to observe the environment in front of the vehicle 12 .

[0055] refer to Figure 4 , a flow chart of a method 100 for noise localization is shown. The method 100 starts at box 102 and proceeds to box 104. At box 104, the controller 14 uses multiple vehicle sensors 16 to perform multiple measurements and determine the location of the faulty component 22, as will be discussed in more detail below. After box 104, the method 100 proceeds to box 106.

[0056] At box 106, the controller 14 identifies the faulty component 22 based at least in part on the location of the faulty component 22 determined at box 104. In an exemplary embodiment, the controller 14 identifies the faulty component 22 using a lookup table (LUT) stored in the medium 20 of the controller 14. The LUT has a key column (i.e., a key column of the location of the faulty component 22) and a value column (i.e., a name of the faulty component 22, a part number of the faulty component 22, etc.). In an exemplary embodiment, the LUT includes a plurality of rows, each of which maps a unique position in the key column to a value in the value column (i.e., an identification of the faulty component 22). The LUT is stored in the medium 20 of the controller 14. In an exemplary embodiment, the plurality of rows of the LUT are predetermined. In another exemplary embodiment, the plurality of rows of the LUT can be modified by an occupant using, for example, a human-machine interface device. In yet another exemplary embodiment, the plurality of rows of the LUT can be updated over the air (OTA). It should be understood that any method of mapping keys to values ​​(e.g., programming data structures, logic equations, mathematical functions, and / or the like, etc.) is within the scope of the present disclosure.

[0057] In an exemplary embodiment, after identifying the faulty component 22, the controller 14 may take action based at least in part on the identification of the faulty component 22. In an exemplary embodiment, the controller 14 provides a notification to an occupant of the vehicle 12 using, for example, an infotainment system or other display of the vehicle 12. In another exemplary embodiment, the controller 14 transmits information regarding the identification of the faulty component 22 to an external system, for example, to a diagnostic computer device operated by a service technician and in electrical communication with the controller 14. In another exemplary embodiment, the controller 14 saves a diagnostic trouble code (DTC) in the medium 20 and / or in an onboard diagnostic module of the vehicle 12. After frame 106, the method 100 proceeds to frame 108.

[0058] At block 108, the method 100 enters a standby state. In an exemplary embodiment, the controller 14 repeatedly exits the standby state 108 and restarts the method 100 at block 102. In a non-limiting example, the controller 14 exits the standby state 108 and restarts the method 100 on a timer, such as every three hundred milliseconds.

[0059] refer to Figure 5, a flow chart of a first exemplary embodiment 104a of box 104 is shown. The first exemplary embodiment 104a of box 104 can be used with embodiment 10a or embodiment 10b of system 10, or a combination of embodiments 10a and 10b. The first exemplary embodiment 104a of box 104 is also referred to as a machine learning-based method for determining the location of a faulty component 22. The first exemplary embodiment 104a of box 104 begins at box 502. At box 502, the controller 14 performs a plurality of measurements using a plurality of vehicle sensors 16. In an exemplary embodiment, the plurality of measurements include one or more of the following: noise measurements, vibration measurements, performance data, environmental data, etc. In a non-limiting example, the plurality of measurements also include data stored in the medium 20 of the controller 14, such as vehicle service history data. After box 502, the first exemplary embodiment 104a of box 104 proceeds to box 504.

[0060] At box 504, the controller 14 inputs the multiple measurements obtained at box 502 into the machine learning algorithm. In an exemplary embodiment, the machine learning algorithm is configured to receive multiple measurements as input and generate multiple probabilities as output. Each of the multiple probabilities corresponds to the probability that the noise detected in the multiple measurements comes from a specific location in the vehicle (i.e., the location of the faulty component 22). In a non-limiting example, the machine learning algorithm includes multiple layers, including an input layer and an output layer, and one or more hidden layers. The input layer receives the multiple measurements obtained at box 502 as input. The input is then passed to the hidden layer. Each hidden layer applies a transformation (e.g., a nonlinear transformation) to the data and passes the result to the next hidden layer until the last hidden layer. The output layer generates multiple probabilities.

[0061] To train the machine learning algorithm, the input dataset and the corresponding faulty part locations are used. The algorithm is trained by adjusting the internal weights between the nodes in each hidden layer to minimize the prediction error. During the training process, optimization techniques such as gradient descent are used to adjust the internal weights to reduce the prediction error. The training process is repeated for the entire dataset until the prediction error is minimized, and the resulting trained model is then used to classify new input data.

[0062] After the machine learning algorithm has been sufficiently trained, the algorithm is able to accurately and precisely determine a plurality of probabilities based on the plurality of measurements acquired at block 502. By adjusting the weights between nodes in each hidden layer during the training process, the algorithm "learns" to identify patterns in the data that represent various locations of failed components 22 in the vehicle 12. After block 504, the first exemplary embodiment 104a of block 104 proceeds to block 506.

[0063] At block 506, the controller 14 determines the location of the faulty component 22 within the vehicle 12 based at least in part on the plurality of probabilities determined at block 504. In an exemplary embodiment, the location of the faulty component 22 is determined to be the location corresponding to the highest probability of the plurality of probabilities determined at block 504. After block 506, the first exemplary embodiment 104a of block 104 ends and the method 100 continues as described above.

[0064] refer to Figure 6 , a flow chart of a second exemplary embodiment 104b of block 104 is shown. The second exemplary embodiment 104b of block 104 is used with the embodiment 10a of the system 10. The second exemplary embodiment 104b of block 104 is also referred to as a first analysis method for determining the location of the faulty component 22. The second exemplary embodiment 104b of block 104 begins at blocks 602, 604, and 606. At blocks 602, 604, and 606, the controller 14 performs a plurality of measurements.

[0065] At block 602, the controller 14 performs a first plurality of vibration measurements using the first vibration sensor 24a. In an exemplary embodiment, the first plurality of vibration measurements includes continuously recording vibration data at a predetermined frequency (e.g., one hundred hertz) over a predetermined period of time (e.g., five seconds). After block 602, the second exemplary embodiment 104b of block 104 proceeds to block 608, as will be discussed in more detail below.

[0066] At block 604, the controller 14 performs a second plurality of vibration measurements using the second vibration sensor 24b. In an exemplary embodiment, the second plurality of vibration measurements includes continuously recording vibration data at a predetermined frequency (e.g., one hundred hertz) over a predetermined period of time (e.g., five seconds). After block 604, the second exemplary embodiment 104b of block 104 proceeds to block 608, as will be discussed in more detail below.

[0067] At block 606, the controller 14 performs a third plurality of vibration measurements using the third vibration sensor 24c. In an exemplary embodiment, the third plurality of vibration measurements includes continuously recording vibration data at a predetermined frequency (e.g., one hundred hertz) over a predetermined period of time (e.g., five seconds). After block 606, the second exemplary embodiment 104b of block 104 proceeds to block 608.

[0068] At block 608, the controller 14 identifies a vibration event based at least in part on the first, second, and third plurality of vibration measurements performed at blocks 602, 604, and 606. Figure 2 And continue to refer to Figure 6In an exemplary embodiment, the vibration event includes at least a first vibration pair 32a, a second vibration pair 32b, and a third vibration pair 32c (i.e., at least three vibration pairs 32a, 32b, 32c). The first vibration pair 32a is detected in the first plurality of vibration measurements (i.e., the first vibration pair 32a is detected by the first vibration sensor 24a). The second vibration pair 32b is detected in the second plurality of vibration measurements (i.e., the second vibration pair 32b is detected by the second vibration sensor 24b). The third vibration pair 32c is detected in the third plurality of vibration measurements (i.e., the third vibration pair 32c is detected by the third vibration sensor 24c). Each of the first vibration pair 32a, the second vibration pair 32b, and the third vibration pair 32c includes a longitudinal vibration 34a and a lateral vibration 34b. It should be understood that although the first vibration pair 32a, the second vibration pair 32b, and the third vibration pair 32c are depicted as separate waves, the first vibration pair 32a, the second vibration pair 32b, and the third vibration pair 32c can also be part of a wavefront radiating outward from the faulty component 22. Identification of vibration events will be discussed in more detail below. After block 608 , the second exemplary embodiment 104 b of block 104 proceeds to block 610 .

[0069] At block 610, if a vibration event is not identified at block 608, the second exemplary embodiment 104b of block 104 enters the standby state at block 108. If a vibration event is identified at block 608, the second exemplary embodiment 104b of block 104 proceeds to blocks 612, 614, and 616.

[0070] At block 612, the controller 14 determines a first distance between the first vibration sensor 24a and the faulty component 22. Figure 2 And continue to refer to Figure 6 In an exemplary embodiment, to determine the first distance, the controller 14 determines a first difference 36a between a time of receipt of the longitudinal vibration 34a of the first vibration pair 32a and a time of receipt of the lateral vibration 34b of the first vibration pair 32a based at least in part on the first plurality of vibration measurements performed at block 602. As described above, the longitudinal vibration 34a and the lateral vibration 34b propagate through the structure of the vehicle 12 at different speeds. Therefore, the first difference 36a is positively correlated with the first distance (e.g., the first difference 36a may be proportional to the first distance). After block 612, the second exemplary embodiment 104b of block 104 proceeds to block 618, as will be discussed in more detail below.

[0071] At block 614, the controller 14 determines a second distance between the second vibration sensor 24b and the faulty component 22. Figure 2 And continue to refer to Figure 6In an exemplary embodiment, to determine the second distance, the controller 14 determines a second difference 36b between the time of receipt of the longitudinal vibration 34a of the second vibration pair 32b and the time of receipt of the lateral vibration 34b of the second vibration pair 32b based at least in part on the second plurality of vibration measurements performed at block 604. As described above, the longitudinal vibration 34a and the lateral vibration 34b propagate through the structure of the vehicle 12 at different speeds. Therefore, the second difference 36b is positively correlated with the second distance (e.g., the second difference 36b may be proportional to the second distance). After block 614, the second exemplary embodiment 104b of block 104 proceeds to block 618, as will be discussed in more detail below.

[0072] At block 616, the controller 14 determines a third distance between the third vibration sensor 24c and the faulty component 22. Figure 2 And continue to refer to Figure 6 In the exemplary embodiment, to determine the third distance, the controller 14 determines a third difference 36c between the time of receipt of the longitudinal vibration 34a of the third vibration pair 32c and the time of receipt of the lateral vibration 34b of the third vibration pair 32c based at least in part on the third plurality of vibration measurements performed at block 606. As described above, the longitudinal vibration 34a and the lateral vibration 34b propagate through the structure of the vehicle 12 at different speeds. Therefore, the third difference 36c is positively correlated with the third distance (e.g., the third difference 36c may be proportional to the third distance). After block 616, the second exemplary embodiment 104b proceeds to block 618.

[0073] At box 618, the controller 14 determines the location of the faulty component 22. In an exemplary embodiment, to determine the location of the faulty component 22, the controller 14 uses trilateration based on the first distance determined at box 612, the second distance determined at box 614, and the third distance determined at box 616. Within the scope of the present disclosure, trilateration is a mathematical technique for determining the location of an object based on distance measurements between the object and three known reference points. In a non-limiting example, the process of trilateration involves determining the intersection of three spheres. The first sphere is centered at the location of the first vibration sensor 24a and has a radius equal to the first distance. The second sphere is centered at the location of the second vibration sensor 24b and has a radius equal to the second distance. The third sphere is centered at the location of the third vibration sensor 24c and has a radius equal to the third distance. After box 618, the second exemplary embodiment 104b of box 104 ends, and the method 100 continues as described above.

[0074] refer to Figure 7, a flow chart of a first exemplary embodiment 608a of block 608 for identifying vibration events is provided. The first exemplary embodiment 608a of block 608 begins at block 702. At block 702, the controller 14 performs a spectral analysis on the first plurality of vibration measurements performed at block 602, the second plurality of vibration measurements performed at block 604, and the third plurality of vibration measurements performed at block 606. In an exemplary embodiment, the spectral analysis includes identifying a plurality of frequencies present in the first, second, and third plurality of vibration measurements. In a non-limiting example, the spectral analysis also includes identifying the intensity of each of the plurality of frequencies present in the first, second, and third plurality of vibration measurements. In a non-limiting example, the spectral analysis is performed using a Fourier transform (e.g., using a fast Fourier transform algorithm). After block 702, the first exemplary embodiment 608a of block 608 proceeds to block 704.

[0075] At block 704, the controller 14 compares the plurality of frequencies identified at block 702 to a normal operating frequency range. Within the scope of the present disclosure, the normal operating frequency range includes vibration frequencies generated during normal operation of the vehicle 12 (e.g., normal vibrations generated by the internal combustion engine of the vehicle 12). In an exemplary embodiment, the normal vibration frequency range is stored in the medium 20 of the controller 14. Therefore, if one or more of the plurality of frequencies identified at block 702 is outside the normal operating frequency range, then a determination is made at block 610 that a vibration event is to be identified, as described above. After block 704, the first exemplary embodiment 608a of block 608 ends, and the second exemplary embodiment 104b of block 104 continues as described above.

[0076] refer to Figure 8, a flow chart of a second exemplary embodiment 608b of block 608 for identifying a vibration event is provided. The second exemplary embodiment 608b of block 608 begins at block 802. At block 802, the controller 14 inputs the first plurality of vibration measurements performed at block 602, the second plurality of vibration measurements performed at block 604, and the third plurality of vibration measurements performed at block 606 into a machine learning algorithm. In an exemplary embodiment, the machine learning algorithm is configured to use unsupervised learning to divide the vibration measurements of the first plurality of vibration measurements, the second plurality of vibration measurements, and the third plurality of vibration measurements into a normal measurement subset and an abnormal measurement subset. In a non-limiting example, the unsupervised learning is used to analyze the first, second, and third plurality of vibration measurements and identify patterns and / or trends. The normal measurement subset includes vibrations caused by normal operation of the vehicle 12. The abnormal measurement subset includes vibrations caused by a faulty component (e.g., a faulty component 22). Therefore, if one or more vibration measurements of the first, second, and third plurality of vibration measurements are classified in the abnormal measurement subset, it is determined at block 610 that a vibration event is identified, as described above. After block 804, the second exemplary embodiment 608b of block 608 ends and the second exemplary embodiment 104b of block 104 continues as described above.

[0077] refer to Fig. 9 , a flow chart of a third exemplary embodiment 104c of block 104 is shown. The third exemplary embodiment 104c is used with the embodiment 10b of the system 10. The third exemplary embodiment 104c of block 104 is also referred to as a second analysis method for determining the location of the faulty component 22. The third exemplary embodiment 104c begins at blocks 902, 904, and 906. At blocks 902, 904, and 906, the controller 14 performs a plurality of measurements. At block 902, the controller 14 performs a first plurality of noise measurements using the first microphone 26a. After block 902, the third exemplary embodiment 104c of block 104 proceeds to block 914, as will be discussed in more detail below.

[0078] At block 904, the controller 14 performs a second plurality of noise measurements using the second microphone 26 b. After block 904, the third exemplary embodiment 104 c of block 104 proceeds to block 914, as will be discussed in more detail below. At block 906, the controller 14 performs a third plurality of noise measurements using the third microphone 26 c. After block 906, the third exemplary embodiment 104 c of block 104 proceeds to block 914, as will be discussed in more detail below.

[0079] At box 914, the controller 14 identifies a noise event based at least in part on the first plurality of noise measurements determined at box 902, the second plurality of noise measurements determined at box 904, and the third plurality of noise measurements determined at box 906. In an exemplary embodiment, to identify a noise event, the controller 14 first performs a spectrum analysis on the first, second, and third plurality of noise measurements. In an exemplary embodiment, the spectrum analysis includes identifying a plurality of noise frequencies present in the first, second, and third plurality of noise measurements. Then, the controller 14 compares the plurality of noise frequencies to a normal operating noise frequency range. If one or more of the plurality of noise frequencies exceeds the normal operating frequency range, it is determined that a noise event is identified. After box 914, the third exemplary embodiment 104c of box 104 proceeds to box 916.

[0080] At block 916, if a noise event is not identified at block 914, the third exemplary embodiment 104c of block 104 enters the standby state at block 108. If a noise event is identified at block 914 (e.g., if one or more of the plurality of noise frequencies are outside a normal operating frequency range), the third exemplary embodiment 104c of block 104 proceeds to blocks 918, 920, and 922.

[0081] At box 918, the controller 14 identifies a first possible range of positions of the faulty component 22 relative to the first microphone 26a and the second microphone 26b. In an exemplary embodiment, the first possible range of positions is determined based at least in part on a first phase difference between the first plurality of noise measurements performed at box 902 and the second plurality of noise measurements performed at box 904. As described above, the first phase difference quantifies the arrival time difference of the received noise. In addition, as described above, if the faulty component 22 is located on the confusion cone 30 of the first microphone 26a and / or the second microphone 26b, the first possible range of positions may include a possible range of positions. Therefore, the first possible range of positions may be represented by a three-dimensional cone. In some cases, if the faulty component 22 is located outside the confusion cone 30, the first possible range of positions may only include one possible position. After box 918, the third exemplary embodiment 104c of box 104 proceeds to box 924, as will be discussed in more detail below.

[0082] At box 920, the controller 14 identifies a second possible range of positions of the faulty component 22 relative to the first microphone 26a and the third microphone 26c. In an exemplary embodiment, the second possible range of positions is determined based at least in part on a second phase difference between the first plurality of noise measurements performed at box 902 and the third plurality of noise measurements performed at box 906. As described above, the second phase difference quantifies the arrival time difference of the received noise. In addition, as described above, if the faulty component 22 is located on the confusion cone 30 of the first microphone 26a and / or the third microphone 26c, the second possible range of positions may include a possible range of positions. Therefore, the second possible range of positions may be represented by a three-dimensional cone. In some cases, if the faulty component 22 is located outside the confusion cone 30, the second possible range of positions may only include one possible position. After box 920, the third exemplary embodiment 104c of box 104 proceeds to box 924, as will be discussed in more detail below.

[0083] At box 922, the controller 14 identifies a third possible range of positions of the faulty component 22 relative to the second microphone 26b and the third microphone 26c. In an exemplary embodiment, the third possible range of positions is determined based at least in part on a third phase difference between the second plurality of noise measurements performed at box 904 and the third plurality of noise measurements performed at box 906. As described above, the third phase difference quantifies the arrival time difference of the received noise. In addition, as described above, if the faulty component 22 is located on the confusion cone 30 of the second microphone 26b and / or the third microphone 26c, the third possible range of positions may include a possible range of positions. Therefore, the third possible range of positions may be represented by a three-dimensional cone. In some cases, if the faulty component 22 is located outside the confusion cone 30, the third possible range of positions may only include one possible position. After box 922, the third exemplary embodiment 104c of box 104 proceeds to box 924.

[0084] At block 924, the controller 14 determines the location of the faulty component 22 based at least in part on the first possible position range determined at block 918, the second possible position range determined at block 920, and the third possible position range determined at block 922. In an exemplary embodiment, to determine the location of the faulty component 22, the controller 14 determines the intersection of a first three-dimensional cone representing the first possible position range determined at block 918, a second three-dimensional cone representing the second possible position range determined at block 920, and a third three-dimensional cone representing the third possible position range determined at block 922. The location of the faulty component 22 is determined to be at the intersection of the first three-dimensional cone, the second three-dimensional cone, and the third three-dimensional cone. After block 924, the third exemplary embodiment 104c of block 104 proceeds to block 926.

[0085] At block 926, the controller 14 uses one or more of the first microphone 26a, the second microphone 26b, and the third microphone 26c configured as a beamforming microphone array to scan the location determined at block 924. In another embodiment, the controller 14 scans one of the first three-dimensional cone, the second three-dimensional cone, and the third three-dimensional cone. Thus, a more localized and isolated noise measurement can be performed, allowing the location of the faulty component 22 to be confirmed and the faulty component 22 to be further analyzed, including information such as the nature and / or severity of the fault. After block 926, the third exemplary embodiment 104c of block 104 ends, and the method 100 continues as described above.

[0086] It should be understood that the first exemplary embodiment 104a of block 104, the second exemplary embodiment 104b of block 104, and the third exemplary embodiment 104c of block 104 can be used in combination, such as in series, in parallel, and / or in other combinations, without departing from the scope of the present disclosure. In a non-limiting example, the possible location of the faulty component 22 is determined using the second exemplary embodiment 104b of block 104 and / or the third exemplary embodiment 104c of block 104 (i.e., using an analytical method). The possible location is then used as an input to the first exemplary embodiment 104a of block 104 (i.e., as one of the multiple measurements discussed with reference to block 502). Subsequently, the first exemplary embodiment 104a of block 104 is used to determine the location of the faulty component 22 based at least in part on the possible location determined using the second exemplary embodiment 104b of block 104 and / or the third exemplary embodiment 104c of block 104 (i.e., using an analytical method) and the multiple measurements performed at block 502.

[0087] The system 10 and method 100 of the present disclosure have several advantages. By continuously and / or repeatedly performing the method 100, a faulty component in the vehicle 12 can be identified in a timely manner so that service and repair can be provided in a timely manner. In addition, multiple vehicle sensors 16 can be used to identify and diagnose components that are about to fail based on subtle vibration and / or noise signals. The system 10 and method 100 improve vehicle reliability, reduce repair costs / time, and increase occupant convenience.

[0088] The description of the present disclosure is merely exemplary in nature, and variations that do not depart from the gist of the present disclosure are intended to fall within the scope of the present disclosure. These variations should not be regarded as departing from the spirit and scope of the present disclosure.

Claims

1. A system for locating vehicle noise, the system comprising: a plurality of vehicle sensors, wherein the plurality of vehicle sensors comprises at least one of: a microphone, a vibration sensor, a vehicle road speed sensor, and a vehicle motor speed sensor; and a controller in electrical communication with the plurality of vehicle sensors, wherein the controller is programmed to: performing a plurality of measurements of noise generated by a faulty component of the vehicle using the plurality of vehicle sensors; Determining a location of the faulty component within the vehicle based at least in part on the plurality of measurements using at least one of a machine learning-based approach and an analytical approach; and A faulty component of the vehicle is identified based at least in part on a location of the faulty component within the vehicle.

2. The system according to claim 1, wherein: To determine the location of the faulty component within the vehicle using the machine learning based method, the controller is further programmed to: inputting the plurality of measurements into a machine learning algorithm, wherein the machine learning algorithm is configured to receive the plurality of measurements as input and generate a plurality of probabilities as output, and wherein each of the plurality of probabilities corresponds to a probability that noise in the plurality of measurements is from a particular location in the vehicle; and A location of the faulty component within the vehicle is determined based at least in part on the plurality of probabilities.

3. The system according to claim 1, wherein: The plurality of vehicle sensors includes at least three vibration sensors, wherein each of the at least three vibration sensors is secured at a different location in the vehicle, wherein to perform the plurality of measurements, the controller is further programmed to: performing a first plurality of vibration measurements using a first vibration sensor of the plurality of vehicle sensors; performing a second plurality of vibration measurements using a second vibration sensor from the plurality of vehicle sensors; and A third plurality of vibration measurements is performed using a third vibration sensor of the plurality of vehicle sensors.

4. The system according to claim 3, wherein: In order to determine the location of the faulty component within the vehicle using the analysis method, the controller is further programmed to: identifying a vibration event based at least in part on the first, second, and third pluralities of vibration measurements, wherein the vibration event is from a location of the faulty component within the vehicle, wherein the vibration event includes at least three vibration pairs, wherein a first vibration pair is detected in the first plurality of vibration measurements, a second vibration pair is detected in the second plurality of vibration measurements, and a third vibration pair is detected in the third plurality of vibration measurements, wherein Each of the first, second and third vibration pairs includes a longitudinal vibration and a lateral vibration; determining a first distance between the first vibration sensor and the faulty component based at least in part on a difference between a time of receiving the longitudinal vibration of the first vibration pair and a time of receiving the lateral vibration of the first vibration pair; determining a second distance between the second vibration sensor and the faulty component based at least in part on a difference between a time of receipt of the longitudinal vibration of the second vibration pair and a time of receipt of the lateral vibration of the second vibration pair; determining a third distance between the third vibration sensor and the faulty component based at least in part on a difference between a time of receipt of the longitudinal vibration of the third vibration pair and a time of receipt of the lateral vibration of the third vibration pair; and A location of the faulty component is determined using trilateration based at least in part on the first distance, the second distance, and the third distance.

5. The system according to claim 4, wherein: To identify the vibration event, the controller is also programmed to: performing a spectral analysis to identify a plurality of frequencies present in the first, second, and third pluralities of vibration measurements; comparing the plurality of frequencies to a normal operating frequency range; as well as The vibration event is identified in response to determining that at least one of the plurality of frequencies is outside the normal operating frequency range.

6. The system according to claim 4, wherein: To identify the vibration event, the controller is also programmed to: inputting the first, second, and third pluralities of vibration measurements into a machine learning algorithm, wherein the machine learning algorithm is configured to separate the first, second, and third pluralities of vibration measurements into a subset of normal measurements and a subset of abnormal measurements using unsupervised learning; and The vibration event is identified based at least in part on the subset of abnormal measurements.

7. The system according to claim 1, wherein: The plurality of vehicle sensors includes at least three microphones, wherein each of the at least three microphones is fixed at a different location in the vehicle, wherein, to perform the plurality of measurements, the controller is further programmed to: performing a first plurality of noise measurements using a first microphone of the at least three microphones; performing a second plurality of noise measurements using a second microphone of the at least three microphones; and A third plurality of noise measurements is performed using a third microphone of the at least three microphones.

8. The system according to claim 7, wherein: In order to determine the location of the faulty component within the vehicle using the analysis method, the controller is further programmed to: identifying a noise event based at least in part on the first, second, and third pluralities of noise measurements, wherein: The noise event originates from the location of the faulty component in the vehicle; determining a first range of possible positions of the faulty component relative to a first one of the at least three microphones and a second one of the at least three microphones based at least in part on a first phase difference between the first plurality of noise measurements and the second plurality of noise measurements; determining a second range of possible positions of the faulty component relative to a first of the at least three microphones and a third of the at least three microphones based at least in part on a second phase difference between the first plurality of noise measurements and the third plurality of noise measurements; determining a third range of possible positions of the faulty component relative to a second of the at least three microphones and a third of the at least three microphones based at least in part on a third phase difference between the second plurality of noise measurements and the third plurality of noise measurements; and The location of the faulty component is determined based at least in part on the first range of possible positions, the second range of possible positions, and the third range of possible positions.

9. The system of claim 8, further comprising a beamforming microphone array, wherein: The controller is also programmed to: The beamforming microphone array is used to scan the location of the faulty component to detect noise generated by the faulty component.

10. The system according to claim 1, wherein: The controller is also programmed to: determining a possible location of the faulty component within the vehicle using the analysis method based at least in part on the plurality of measurements; and Based at least in part on the plurality of measurements and the possible locations, the location of the faulty component within the vehicle is determined using the machine learning based method.

Images