Abnormal sound diagnosis system

Abstract

To allow a user to easily obtain an accurate diagnosis result of an abnormal sound occurring in an object even when the user has little experience in an abnormal sound diagnosis system.SOLUTION: An abnormal sound diagnosis system includes: a sound acquisition unit which acquires data on sound issued from an object; an inquiry information acquisition unit which acquires inquiry information on the abnormal sound which has occurred in the object; an arithmetic processing unit which acquires a spectrogram showing a relation between times, frequencies, and sound pressures from the sound data; an extraction unit which acquires an estimated frequency range of an abnormal sound which has occurred in the object on the basis of the inquiry information acquired by the inquiry information acquisition unit and extracts a range corresponding to the estimated frequency range of the spectrogram acquired by the arithmetic processing unit; and a diagnosis unit which diagnoses the cause of the abnormal sound which has occurred in the object on the basis of the range of the spectrogram extracted by the extraction unit.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a abnormal sound diagnosis system for diagnosing abnormal sounds generated in an object.

Background Art

[0002] Conventionally, there is known a sound and vibration analysis device that captures and analyzes data on sounds or vibrations generated along with the rotation of a rotating body and data on the rotational speed of a selected rotating body during the operation of a power transmission mechanism of a vehicle having a plurality of rotating bodies (see, for example, Patent Document 1). This sound and vibration analysis device frequency-analyzes sound or vibration data and calculates an order corresponding to the specifications of the rotating body from the frequency-analyzed sound or vibration data. Further, the sound and vibration analysis device displays the sound pressure level calculated from the sound or vibration data in correspondence with the order and the vehicle speed on a display unit, and reproduces a sound having a specific order selected by an operator on the display unit.

[0003] Conventionally, there has been known an interrogation device that conducts an interrogation to obtain related information on malfunction symptoms occurring in a vehicle to be diagnosed, and either estimates the cause of the malfunction symptoms on its own based on the obtained information or outputs the obtained information externally (see, for example, Patent Document 2). This interrogation device includes a display unit that displays questions for obtaining the above-mentioned related information, a sample abnormal sound output unit that outputs a sample abnormal sound corresponding to the malfunction symptoms, a control unit that controls the display on the display unit and the output sound of the sample abnormal sound output unit and processes the user's operation input, and a storage unit that stores display data that is data related to the display on the display unit and sample abnormal sound data that is data obtained by collecting vehicle sounds generated corresponding to each malfunction symptom. The control unit of such an interrogation device causes the display unit to display a plurality of scene selection buttons that are selection buttons for requesting selection of a driving operation scene in which a malfunction symptom has occurred, and a plurality of symptom selection buttons that are selection buttons for requesting selection of the content of the malfunction symptom associated with the selection result of the scene selection buttons. Further, when the content of the malfunction symptom relates to the occurrence of an abnormal sound in the vehicle to be diagnosed, the control device causes the display unit to display a sample abnormal sound output button for outputting a sample abnormal sound corresponding to the malfunction symptom side by side with the symptom selection buttons. As a result, when the content of the malfunction symptom is related to the occurrence of an abnormal sound, it becomes possible to output a corresponding sample abnormal sound as an index for selecting the symptom, and a customer who has actually heard the abnormal sound can compare a plurality of sample abnormal sounds and select and answer the content of the symptom of the abnormal sound occurrence that is difficult to express.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] According to the conventional sound vibration analysis device described in the above Patent Document 1, graph display using vehicle speed makes it easier to match with sensory evaluation. By examining the frequency at which the sound is generated or playing back the captured sound, it may be possible to identify the rotating body that is the sound source. However, for an inexperienced operator, it is not easy to identify the rotating body that is the sound source using the sound vibration analysis device. To accurately identify the rotating body that is the sound source while comparing the frequency, vehicle speed, and sound pressure level, a certain degree of experience is required of the operator. Also, like the interview device described in the above Patent Document 2, even if sample abnormal sounds are output as candidates, it is not always the case that the sample abnormal sound closest to the actually generated abnormal sound is selected by the customer or the like. And when a sound close to the actual abnormal sound is not selected by the customer or the like, it becomes necessary to diagnose the cause of the abnormal sound only from interview information such as the driving operation scene where the malfunction symptom occurred, and there is a risk that the accuracy of the diagnosis result will deteriorate instead.

[0006] Therefore, the main object of the present disclosure is to enable an operator with little experience in using an abnormal sound diagnosis system to easily obtain an accurate diagnosis result of the abnormal sound generated in the object.

Means for Solving the Problems

[0007] The abnormal sound diagnosis system of the present disclosure is an abnormal sound diagnosis system for diagnosing an abnormal sound generated in an object, including a sound acquisition unit that acquires data of the sound emitted from the object, an interview information acquisition unit that acquires interview information regarding the abnormal sound generated in the object, an arithmetic processing unit that acquires a spectrogram showing the relationship between time, frequency, and sound pressure from the sound data, an extraction unit that acquires an estimated frequency range of the abnormal sound generated in the object based on the interview information acquired by the interview information acquisition unit and extracts a range corresponding to the estimated frequency range of the spectrogram acquired by the arithmetic processing unit, and a diagnosis unit that diagnoses the cause of the abnormal sound generated in the object based on the range extracted by the extraction unit of the spectrogram. The diagnosis unit of such an abnormal sound diagnosis system may be constructed by machine learning.

[0008] In addition, another abnormal sound diagnosis system of the present disclosure is an abnormal sound diagnosis system for diagnosing abnormal sounds generated in an object, including a sound acquisition unit that acquires data of sounds emitted from the object, an inquiry information acquisition unit that acquires inquiry information regarding the abnormal sounds generated in the object, an arithmetic processing unit that acquires at least the relationship between time and sound pressure from the sound data, an extraction unit that acquires the time zone in which the abnormal sound is generated in the object based on the inquiry information acquired by the inquiry information acquisition unit, and extracts a range corresponding to the time zone of the relationship between time and sound pressure acquired by the arithmetic processing unit, and a diagnosis unit that diagnoses the cause of the abnormal sound generated in the object based on the range extracted by the extraction unit. The diagnosis unit of such an abnormal sound diagnosis system may also be constructed by machine learning.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Mode for Carrying Out the Invention

[0010] Next, with reference to the drawings, the mode for carrying out the invention of the present disclosure will be described.

[0011] FIG. 1 is a schematic configuration diagram showing the abnormal noise diagnosis system 1 of the present disclosure. The abnormal noise diagnosis system 1 shown in the figure is for diagnosing the cause of abnormal noise generated in a vehicle V as an object such as a vehicle equipped only with an engine as a power generation source, a hybrid vehicle, or an electric vehicle (including a fuel cell vehicle), and includes a mobile terminal 10 and a server 20 capable of exchanging information with the mobile terminal 10 through communication.

[0012] The mobile terminal 10 is used by an operator (user of the abnormal noise diagnosis system 1) such as a vehicle dealership or a repair shop when responding to the owner of the vehicle V (user of the vehicle V) where an abnormal noise has occurred, or when performing a reproduction test to reproduce the abnormal noise by driving (operating) the vehicle V on a road or a test bench. In the present embodiment, the mobile terminal 10 is a smartphone including an SoC including a CPU and a GPU, a ROM, a RAM, an auxiliary storage device (flash memory) M, a display unit 11, a communication module 12, a microphone (not shown), etc., and an abnormal noise diagnosis support application (program) is installed in the mobile terminal 10. And, as shown in FIG. 1, the mobile terminal 10 is constructed by the cooperation of an abnormal noise diagnosis support application (software) and hardware such as the display unit 11, the communication module 12, the SoC, the ROM, the RAM, and the microphone, and includes an inquiry information acquisition unit 13, a sound acquisition unit 14, a vehicle state acquisition unit 15, an arithmetic processing unit 16, an extraction unit 17, and a display control unit 18.

[0013] The display unit 11 of the mobile terminal 10 includes a touch panel type liquid crystal panel or an organic EL panel, etc. The communication module 12 exchanges various information with the electronic control device of the vehicle V via short-range wireless communication or a cable (dongle), and can also exchange various information with the server 20 via a network such as the Internet. The inquiry information acquisition unit 13 is constructed by the cooperation of the abnormal noise diagnosis support application and the display unit 11, the communication module 12, the SoC, the ROM, the RAM, etc., and acquires information (hereinafter referred to as "inquiry information") indicating the state of the vehicle V at the time of abnormal noise generation provided from the owner of the vehicle V or the like via the display unit 11 or the communication module 12. The inquiry information may be input to the mobile terminal 10 via the display unit 11 by an operator such as a vehicle dealership who has interviewed the owner of the vehicle V or the like. Also, the inquiry information may be input by the owner of the vehicle V or the like to a dedicated web page provided by, for example, the server 20 from their own mobile information terminal, personal computer, etc. In this case, the mobile terminal 10 acquires the inquiry information from the server 20 via the communication module 12 according to the operation of the operator.

[0014] Figure 2 shows an input screen (questionnaire) and an example of input of the consultation information displayed on the display unit 11 of the mobile terminal 10 (or the above website). As shown in a part of Figure 2, the consultation information includes vehicle type information, instructions, date and time of occurrence, frequency of occurrence, type of sound, physical quantities that change during the running of the vehicle V such as vehicle speed, driving state of the vehicle V, warm-up influence in an engine-equipped vehicle, selection items selected by the driver during the running of the vehicle V, driving environment information of the vehicle V, and the like. The vehicle type information is information for specifying the vehicle type of the vehicle V such as the chassis number or the vehicle identification number. The instructions are detailed contents of the occurrence state of abnormal noise provided by the owner of the vehicle V or the like. The frequency of occurrence is selected by an operator or an owner or the like from a pre-prepared drop-down list (list) including options such as always, several times a day, once a day, several times a week, once a week, once or less a month.

[0015] The type of sound is selected by the owner of the vehicle V or the like from a drop-down list including a plurality of onomatopoeias (for example, rattling, clattering, rumbling, rumbling, clicking, key, keening, etc.) corresponding to any abnormal sound generated in the vehicle V, and is recognized as similar to the actually generated abnormal sound. The physical quantities include vehicle speed, engine speed, motor speed, ON / OFF time of the brake lamp switch, steering angle, SOC of the high-voltage battery of a hybrid vehicle or an electric vehicle (for example, fully charged, normal, extremely low, etc.). The physical quantities are either heard by the operator from the owner of the vehicle V or the like or input by the owner or the like.

[0016] The driving state of the vehicle V is selected by an operator, owner, etc. from a drop-down list including options such as start, idling, stop, departure, acceleration, constant-speed driving, deceleration (brake off), braking (brake on), reverse, turning, motor driving in a hybrid vehicle (with / without engine drive (charging)), and hybrid driving in a hybrid vehicle (driven by an engine and a motor). The warm-up effect is selected by an operator, owner, etc. from a drop-down list including options such as cold, warm, cold and warm. The selection items include the shift position (any of P, R, N, D, B, S (sports), etc.), the driving mode (for example, any of normal, power, eco, snow, comfort), the operating state of auxiliary equipment (ON / OFF state of air conditioner, headlight, etc.), etc., and are selected by an operator, owner, etc. from a drop-down list. The driving environment information includes road surface conditions such as stepped road / rough road surface, flat road, uphill road, downhill road, and weather such as sunny, cloudy, rainy, snowy, etc., and is selected by an operator, owner, etc. from a drop-down list. It goes without saying that not all of the above multiple items are provided by the owner, etc. of the vehicle V, and the inquiry information is provided within the range known to the owner, etc. of the vehicle V.

[0017] The sound acquisition unit 14 is constructed by the cooperation of the abnormal sound diagnosis support application with the SoC, ROM, RAM, microphone, etc., and acquires the time-axis data of sound (sound pressure) when the reproduction test is executed. The vehicle state acquisition unit 15 is constructed by the cooperation of the abnormal sound diagnosis support application with the SoC, ROM, RAM, display unit 11, communication module 12, etc., and acquires information indicating the state of the vehicle V (hereinafter, "vehicle state information") in synchronization with the acquisition of the time-axis data of the sound by the sound acquisition unit 14 when the reproduction test is executed. The vehicle state information includes a plurality of physical quantities corresponding to the items of the above-described inquiry information (for example, vehicle speed, engine speed, motor speed, ON / OFF times of the brake lamp switch, steering angle, SOC of the high-voltage battery of a hybrid vehicle or an electric vehicle, etc.). Further, the vehicle state information includes those calculated or detected by the electronic control device and various sensors of the vehicle V and acquired via the communication module 12, and those input by an operator or the like from the display unit 11 based on the inquiry information before the start of the reproduction test or the like. The arithmetic processing unit 16 is constructed by the cooperation of the abnormal sound diagnosis support application with the SoC, ROM, RAM, etc., and executes the analysis processing of the time-axis data of the sound acquired by the sound acquisition unit 14. The extraction unit 17 is constructed by the cooperation of the abnormal sound diagnosis support application with the SoC, ROM, RAM, etc., and narrows down the result of the analysis processing of the arithmetic processing unit 16 based on the above-described inquiry information, etc. The display control unit 18 is constructed by the cooperation of the abnormal sound diagnosis support application with the SoC, ROM, RAM, etc., and controls the display unit 11.

[0018] The server 20 of the abnormal noise diagnosis system 1 is a computer (information processing device) including a CPU, ROM, RAM, input / output devices, etc., and in this embodiment, it is installed and managed by, for example, an automobile manufacturer that manufactures the vehicle V. In the server 20, an abnormal noise diagnosis unit 21 for diagnosing abnormal noises generated in the vehicle V is constructed by the cooperation of hardware such as a CPU, ROM, and RAM and a pre-installed abnormal noise diagnosis application (program). The abnormal noise diagnosis unit 21 includes a neural network (convolutional neural network) constructed by supervised learning (machine learning) to diagnose the cause of the abnormal noise generated in the vehicle V and the parts that have become the source of the abnormal noise based on the inquiry information, sound time-axis data, etc. acquired by the mobile terminal 10. The teacher data used for constructing the abnormal noise diagnosis unit 21 includes the time-axis data of the sound acquired for the time range including the timing when the abnormal noise occurs and the content (value) of each item of the above inquiry information for each of a plurality of abnormal noises known to occur in the vehicle V. Further, in the server 20, when it is determined that a new abnormal noise has occurred in the vehicle V, re-learning of the abnormal noise diagnosis unit 21 is executed using the time-axis data of the sound acquired for the new abnormal noise and the content of each item of the above inquiry information as teacher data. As the technology for constructing the abnormal noise diagnosis unit 21, for example, those described in the following papers (1)-(5) or a combination thereof can be used.

[0019] (1) “CNN with filterbanks learned using convolutional RBM + fusion with GTSC and mel energies” and “CNN with filterbanks learned using convolutional RBM + fusion with GTSC” described in “Unsupervised Filterbank Learning Using Convolutional Restricted Boltzmann Machine for Environmental Sound Classification” (2) "EnvNet-v2 (tokozume2017a) + data augmentation + Between-Class learning" and "EnvNet-v2 (tokozume2017a) + Between-Class learning" described in "LEARNING FROM BETWEEN-CLASS EXAMPLES FOR DEEP SOUND RECOGNITION" (3) "CNN working with phase encoded mel filterbank energies (PEFBEs), fusion with Mel energies" described in "Novel Phase Encoded Mel Filterbank Energies for Environmental Sound Classification" (4) "CNN pretrained on AudioSet" described in "Knowledge Transfer from Weakly Labeled Audio using Convolutional Neural Network for Sound Events and Scenes" (5) "Fusion of GTSC & TEO-GTSC with CNN" described in "Novel TEO-based Gammatone Features for Environmental Sound Classification"

[0020] Furthermore, the server 20 includes a storage device 22 that stores a database containing information about a plurality of abnormal sounds that have been found to occur in the vehicle for each vehicle type. The database associates and stores information such as the time-axis data of the sound, the cause of the abnormal sound, the component that is the source of the sound, the content of the inquiry information provided by the owner, etc., and the countermeasures for eliminating the abnormal sound for each of the plurality of abnormal sounds. In addition, the server 20 updates the database based on information obtained from a large number of vehicles including the vehicle V, and information about newly discovered abnormal sounds transmitted from automobile manufacturers (developers, etc.), vehicle dealerships, repair shops, etc.

[0021] Next, the abnormal noise diagnosis procedure by the abnormal noise diagnosis system 1 will be described.

[0022] When an operator at a vehicle dealership, repair shop, etc. is requested by the owner of the vehicle V or the like to eliminate abnormal noise, the operator listens to the inquiry information from the owner or the like, or obtains the inquiry information from the server 20, and then executes a reproduction test to obtain the information necessary for diagnosing the abnormal noise. When executing the reproduction test, the operator (user) starts the above-described abnormal noise diagnosis support application on the mobile terminal 10 and taps the recording button displayed on the display unit 11. Further, the operator inputs the necessary information among the inquiry information provided by the owner or the like into the input screen displayed on the display unit 11, and connects the mobile terminal 10 to the electronic control unit of the target vehicle. As described above, the mobile terminal 10 and the electronic control unit of the target vehicle may be connected by short-range wireless communication or may be connected via a cable (dongle). Then, when the operator turns on the start switch (IG switch) of the vehicle V, the mobile terminal 10 acquires vehicle information such as the chassis number or vehicle identification number of the vehicle V from the electronic control unit. However, the vehicle information may be input to the mobile terminal 10 by the operator.

[0023] Furthermore, the operator places or fixes the mobile terminal 10 at an appropriate position in the vehicle interior. Also, when an external microphone is connected to the mobile terminal 10, the external microphone is installed at a location suitable for recording, such as in the engine room. Next, the operator taps the recording start button displayed on the display unit 11 and drives (operates) the vehicle V on a roadway or a test bench to reproduce the driving state in which abnormal noise has occurred based on the consultation information from the owner of the vehicle V or the like. While the vehicle V is driving (operating), the sound acquisition unit 14 of the mobile terminal 10 acquires the time-axis data of the sound emitted from the vehicle V at predetermined intervals (microscopic intervals), and the vehicle state acquisition unit 15 acquires the vehicle state information from the electronic control unit of the vehicle V at predetermined intervals (microscopic intervals) in synchronization with the acquisition of the time-axis data of the sound by the sound acquisition unit 14. The sound acquisition unit 14 and the vehicle state acquisition unit 15 acquire the time-axis data of the sound and the vehicle state information until the recording stop button displayed on the display unit 11 is tapped by the operator in response to the stop of the vehicle V or the like. When the acquisition of the time-axis data of the sound and the vehicle state information is completed, the arithmetic processing unit 16 and the extraction unit 17 of the mobile terminal 10 execute the analysis processing of the time-axis data of the sound.

[0024] FIG. 3 is a flowchart showing a series of processes executed by the mobile terminal 10 in diagnosing abnormal noise, and FIG. 4 is a flowchart showing the details of the process in step S150 of FIG. 3.

[0025] As shown in FIG. 3, after the reproduction test is completed, the arithmetic processing unit 16 of the mobile terminal 10 acquires the time-axis data of the sound acquired by the sound acquisition unit 14 (step S100). Further, the arithmetic processing unit 16 performs STFT (Short-Time Fourier Transform) on the acquired time-axis data of the sound to acquire a spectrogram (acoustic spectrogram) showing the relationship between time, frequency, and sound pressure (step S110). Also, as shown in FIG. 5, the display control unit 18 of the mobile terminal 10 causes the display unit 11 to display the spectrogram (color map) acquired by the arithmetic processing unit 16 (step S120). In the present embodiment, the spectrogram shows the relationship between time and sound pressure level for each frequency by using the horizontal axis as the time axis, the vertical axis as the frequency axis, and color-coding the sound pressure level.

[0026] When the spectrogram is displayed on the display unit 11 of the mobile terminal 10, the operator taps the selection instruction button displayed on the display unit 11 to cause the mobile terminal 10 to extract (select) the range to be analyzed by the abnormal sound diagnosis unit 21 (server 20) in the spectrogram (hereinafter referred to as the "analysis range"), or the operator selects (designates) the analysis range with his or her fingertip on the display unit 11. When the operator instructs the mobile terminal 10 to extract the analysis range (step S130: YES), the extraction unit 17 of the mobile terminal 10 acquires the inquiry information acquired by the inquiry information acquisition unit 13 and the vehicle state information acquired by the vehicle state acquisition unit 15 (step S140), and extracts the analysis range of the spectrogram based on at least one of the acquired inquiry information and vehicle state information (step S150).

[0027] In step S150, as shown in FIG. 4, the extraction unit 17 determines whether or not an onomatopoeia is selected in the interview information acquired in step S140 (step S151). If it is determined that an onomatopoeia is selected in the interview information (step S151: YES), the extraction unit 17 acquires, as an estimated frequency range of the abnormal noise generated by the vehicle V, the frequency range corresponding to the selected onomatopoeia (step S152). In the present embodiment, the extraction unit 17 derives, as the estimated frequency range, the frequency range corresponding to the onomatopoeia included in the interview information from the table shown in FIG. 6. Further, if it is determined that no onomatopoeia is selected in the interview information (step S151: NO), the process of step S152 is skipped.

[0028] The table in FIG. 6 is created in advance based on experimental and analysis results so as to associate each of a plurality of selectable onomatopoeias as interview information with the corresponding frequency range of the abnormal noise, and is stored in the auxiliary storage device M of the mobile terminal 10. Further, in the table of FIG. 6, each of the plurality of onomatopoeias is associated with the corresponding characteristics of the abnormal noise and the onomatopoeias of other abnormal noises similar to the corresponding abnormal noise. Also, in the present embodiment, the table in FIG. 6 is updated by the server 20 at the timing when a new abnormal noise occurs in the vehicle V or periodically. That is, the server 20 updates the table in FIG. 6 based on information acquired from a large number of vehicles including the vehicle V, information on abnormal noises newly found to occur in the vehicle V transmitted from automobile manufacturers (developers, etc.), vehicle dealerships, repair shops, etc., and transmits a notification indicating that the table has been updated to the mobile terminal 10. Thereby, workers at vehicle dealerships, repair shops, etc. can download the latest table from the server 20 to the mobile terminal 10 and store it in the auxiliary storage device M when diagnosing abnormal noises.

[0029] After the processing of step S151 or S152, the extraction unit 17 determines whether the inquiry information obtained in step S140 includes physical quantities (such as specific numerical values) such as vehicle speed and engine speed that indicate the state of the vehicle V when abnormal noise occurs (step S153). If it is determined that the inquiry information includes physical quantities (step S153: YES), the extraction unit 17 acquires the occurrence time zone when abnormal noise occurred in the vehicle V based on the inquiry information and the vehicle state information obtained in step S140 (step S154).

[0030] In step S154, the extraction unit 17 acquires, as the occurrence time zone, the time zone within the acquisition time range of the time axis data of the sound in which the physical quantity of the vehicle state information matches the physical quantity included in the inquiry information. For example, when the vehicle speed range as the physical quantity included in the inquiry information and the vehicle speed (waveform) as the physical quantity included in the vehicle state information are as shown in FIG. 7 respectively, the vehicle speed of the vehicle state information is included in the vehicle speed range of the inquiry information in the time zone from time t1 to time t2 and in the time zone from time t3 to time t4, and the physical quantity of the vehicle state information matches the physical quantity included in the inquiry information in these time zones. In such a case, the extraction unit 17 acquires the time zone from time t1 to time t2 and the time zone from time t3 to time t4 as the occurrence time zone.

[0031] Furthermore, for each of a plurality of frequencies in the spectrogram, the extraction unit 17 extracts a characteristic frequency at which the sound pressure changes by a predetermined threshold value (predetermined value) or more between the occurrence time band (the time band in which the physical quantity of the vehicle state information matches the physical quantity included in the inquiry information) acquired in step S154 and the time band in which the physical quantity of the vehicle state information does not match the physical quantity included in the inquiry information (step S155). For example, as shown in FIG. 8, when the time band from time t1 to time t2 and the time band from time t3 to time t4 are the occurrence time bands, the extraction unit 17, in step S155, for each of a plurality of frequencies in the spectrogram, calculates the difference between the average value of the sound pressure in the occurrence time band from time t1 to time t2 and the average value of the sound pressure in the time band from time t2 to time t3 in which the physical quantity of the vehicle state information does not match the physical quantity included in the inquiry information, and the difference between the average value of the sound pressure in the occurrence time band from time t3 to time t4 and the average value of the sound pressure in the time band from time t2 to time t3. Furthermore, in step S155, the extraction unit 17 extracts a characteristic frequency (see the range indicated by the dashed-dotted line in FIG. 8) at which the difference in the average value of the sound pressure is equal to or greater than the above threshold value for each of a plurality of frequencies in the spectrogram.

[0032] Note that the processes of steps S154 and S155 are both skipped when it is determined that the inquiry information does not include a physical quantity (specific numerical value, etc.) (step S153: NO). Also, when there is no characteristic frequency at which the difference in the average value of the sound pressure is equal to or greater than the above threshold value, the extraction of the characteristic frequency is not performed in step S155.

[0033] Furthermore, after the process of step S153 or S155, the extraction unit 17 determines whether the driving state of the vehicle V when an abnormal sound occurred is included in the inquiry information acquired in step S140 (step S156). When it is determined that the driving state is included in the inquiry information (step S156: YES), the extraction unit 17 acquires the occurrence time band in which the abnormal sound occurred in the vehicle V based on the inquiry information and the vehicle state information acquired in step S140 (step S157).

[0034] In step S157, the extraction unit 17 refers to the table shown in FIG. 9 to obtain the physical quantity of the vehicle state information corresponding to the driving state of the interview information, and among the acquisition time ranges of the time-axis data of the sound, the physical quantity obtained by referring to the table is the time zone in which the change corresponding to the driving state of the interview information is shown is obtained as the occurrence time zone. The table in FIG. 9 is created in advance so as to associate each of a plurality of selectable driving states as interview information with a physical quantity indicating a change corresponding to the driving state, and is stored in the auxiliary storage device M of the mobile terminal 10. For example, when the driving state included in the interview information is "braking", the extraction unit 17 refers to the table shown in FIG. 9 to obtain "the ON / OFF time of the brake lamp switch" from the vehicle state information, and the time zone from the ON time of the brake lamp switch (time t10 in FIG. 10) to the OFF time (time t20 in FIG. 10) is obtained as the occurrence time zone. That is, the occurrence time zone acquired in step S157 is the time zone in which the state of the vehicle V during the reproduction test matches the driving state included in the interview information.

[0035] Furthermore, for each of a plurality of frequencies in the spectrogram, the extraction unit 17 extracts a characteristic frequency in which the sound pressure changes by a predetermined threshold value (predetermined value) or more between the occurrence time zone acquired in step S157 (the time zone in which the physical quantity of the vehicle state information matches the physical quantity included in the interview information) and the time zone in which the physical quantity of the vehicle state information does not match the physical quantity included in the interview information) (step S158). The process of step S158 is executed by the same procedure as the process of step S155 described above. Also, the processes of steps S157 and S158 are both skipped when it is determined that the interview information does not include a driving state (step S156: NO). Also, when there is no characteristic frequency in which the difference in the average value of the sound pressure is equal to or greater than the above threshold value, the extraction of the characteristic frequency is not performed in step S158.

[0036] After the processing of step S156 or S158, the extraction unit 17 extracts the analysis range of the spectrogram obtained by the arithmetic processing unit 16 based on the estimated frequency range, generation time zone, and characteristic frequency acquired or extracted in steps S152 - S158 (step S159). That is, in step S159, the extraction unit 17 determines a range corresponding to the estimated frequency range acquired in step S152 of the spectrogram, a range corresponding to the generation time zone acquired in step S154 of the spectrogram and including the characteristic frequency extracted in step S155, and a range corresponding to the generation time zone acquired in step S157 of the spectrogram and including the characteristic frequency extracted in step S158, and extracts at least any one of these ranges as the above-mentioned analysis range.

[0037] When the analysis range of the spectrogram is extracted in step S150 (steps S151 - S159), the display control unit 18 causes only the analysis range extracted by the extraction unit 17 to be displayed on the display unit 11 by, for example, graying out the portions of the spectrogram displayed on the display unit 11 that were not extracted by the extraction unit 17 (step S160). Also, when a plurality of analysis ranges are extracted by the extraction unit 17 in step S150 (step S159), the display control unit 18 causes only one analysis range to be displayed on the display unit 11 according to a predetermined constraint, and causes the plurality of analysis ranges to be displayed on the display unit 11 in order in response to a swipe of the display unit 11 by the operator. Further, in the present embodiment, when an analysis range corresponding to the estimated frequency range acquired based on the onomatopoeia is extracted, the onomatopoeia, frequency range, and characteristics included in the table of FIG. 6 are displayed on the display unit 11 together with the analysis range. This makes it possible to provide useful information to the operator.

[0038] Note that depending on the content of the interview information and the vehicle state information, the analysis range may not be extracted by the extraction unit 17 in step S150. In this case, the display control unit 18 causes the display unit 11 to display a message such as "The analysis range could not be selected." to prompt the operator to select the analysis range. Also, instead of graying out the portions not extracted by the extraction unit 17, the analysis range extracted by the extraction unit 17 may be enlarged and displayed on the display unit 11.

[0039] On the other hand, when the operator selects (designates) the analysis range of the spectrogram with his or her fingertips on the display unit 11 mainly using the color-coded sound pressure level, etc. as a clue (step S130: NO), the display control unit 18 acquires the analysis range selected by the operator (step S135), and by graying out the portions not selected by the operator, only the analysis range selected by the operator is displayed on the display unit 11 (step S160). After displaying the analysis range on the display unit 11, the display control unit 18 determines whether the selection end button displayed on the display unit 11 has been tapped by the operator (step S170). If it is determined that the selection end button has not been tapped by the operator (step S170: NO), the process of step S135 is executed again. That is, if it is determined that the selection end button has not been tapped by the operator, the analysis range extracted by the extraction unit 17 may be further narrowed down by the operator. Therefore, if it is determined that the selection end button has not been tapped by the operator (step S170: NO), the analysis range selected by the operator is confirmed again in step S135.

[0040] When the selection completion button displayed on the display unit 11 is tapped by the operator, information necessary for diagnosing abnormal noises is transmitted from the communication module 12 of the mobile terminal 10 to the server 20 (step S180). The information transmitted from the mobile terminal 10 to the server 20 in step S180 includes the time-axis data of the sound acquired by the sound acquisition unit 14, the inquiry information acquired by the inquiry information acquisition unit 13, and the information defining the analysis range finally displayed on the display unit 11. Further, the information defining the final analysis range includes at least any one of the estimated frequency range, the occurrence time zone, and the characteristic frequency acquired or extracted by the extraction unit 17 through the processes of steps S151 - S158, and the information defining the range selected by the operator from among the analysis ranges extracted by the extraction unit 17, or the information defining the range selected by the operator.

[0041] When the information necessary for diagnosing abnormal noises is transmitted from the mobile terminal 10 to the server 20, the abnormal noise diagnosis unit 21 of the server 20 diagnoses the cause of the abnormal noise generated in the vehicle V based on the information provided from the mobile terminal 10, and transmits the diagnosis result to the mobile terminal 10. The diagnosis result includes the cause of the abnormal noise generated in the vehicle V, the component that has become the source of the abnormal noise, and the countermeasures for eliminating the abnormal noise read from the storage device 22. Further, when the diagnosis result from the server 20 is received by the mobile terminal 10 (step S190), the diagnosis result is displayed on the display unit 11 (step S200), and the series of processes shown in FIG. 3 executed on the mobile terminal 10 ends when diagnosing the abnormal noise. By executing the series of processes shown in FIG. 3, the operator can accurately explain the diagnosis result to the owner of the vehicle V or the like and promptly proceed with measures against the abnormal noise.

[0042] As described above, the arithmetic processing unit 16 of the mobile terminal 10 that constitutes the abnormal noise diagnosis system 1 obtains a spectrogram showing the relationship between time, frequency, and sound pressure from the time-axis data of the sound emitted from the vehicle V as the object acquired by the sound acquisition unit 14 (steps S100 - S120). The extraction unit 17 of the mobile terminal 10 obtains an estimated frequency range of the abnormal noise generated in the vehicle V based on the inquiry information and the like acquired by the inquiry information acquisition unit 13 (steps S150, S152). Further, the extraction unit 17 extracts an analysis range corresponding to the estimated frequency range of the spectrogram (steps S150, S159). The abnormal noise diagnosis unit 21 of the server 20 diagnoses the cause of the abnormal noise generated in the vehicle V based on the information indicating the analysis range extracted in step S159 (steps S180 - S190). Also, the extraction unit 17 of the mobile terminal 10 obtains the occurrence time zone in which the abnormal noise occurred in the vehicle V based on the inquiry information and the like acquired by the inquiry information acquisition unit 13 (steps S150, S154). Further, the extraction unit 17 extracts an analysis range corresponding to the occurrence time zone of the spectrogram (relationship between time and sound pressure) (steps S150, S159). The abnormal noise diagnosis unit 21 of the server 20 diagnoses the cause of the abnormal noise generated in the vehicle V based on the information indicating the analysis range extracted in step S159 (steps S180 - S190).

[0043] In this way, by selecting on the mobile terminal 10 side (system side) the range of the spectrogram to be analyzed by the abnormal noise diagnosis unit 21 based on the inquiry information, it becomes possible to ensure good accuracy of the diagnosis result of the cause of the abnormal noise. Also, the operator using the abnormal noise diagnosis system 1 does not need to select the range of the spectrogram to be analyzed by the abnormal noise diagnosis unit 21 himself / herself. As a result, even an operator with little experience using the abnormal noise diagnosis system 1 can easily obtain an accurate diagnosis result of the abnormal noise generated in the vehicle V.

[0044] Furthermore, the mobile terminal 10 that constitutes the abnormal noise diagnosis system 1 includes an auxiliary storage device M that stores the table of FIG. 6 that associates onomatopoeia with a frequency range for each of a plurality of abnormal noises generated in the vehicle V. Furthermore, the inquiry information includes onomatopoeia similar to the abnormal noise generated in the vehicle V. Also, the extraction unit 17 of the mobile terminal 10 acquires, as an estimated frequency range, the frequency range corresponding to the onomatopoeia included in the inquiry information from the table (information) of FIG. 6 stored in the auxiliary storage device M (step S152). Thereby, an operator of the abnormal noise diagnosis system 1 or the owner of the vehicle V can easily obtain an accurate diagnosis result of the abnormal noise by selecting onomatopoeia similar to the abnormal noise generated in the vehicle V.

[0045] Also, the mobile terminal 10 that constitutes the abnormal noise diagnosis system 1 includes a vehicle state acquisition unit 15 that acquires vehicle state information indicating the state of the vehicle V in synchronization with the acquisition of the time-axis data of the sound by the sound acquisition unit 14 when the reproduction test is executed. Furthermore, the inquiry information includes physical quantities indicating the state of the vehicle V when the abnormal noise occurred, the driving state of the vehicle V, and the like. Also, the extraction unit 17 acquires, as the occurrence time zone, the time zone in which the physical quantity (for example, vehicle speed) of the vehicle state information acquired by the vehicle state acquisition unit 15 matches the physical quantity (for example, vehicle speed range) included in the inquiry information within the acquisition time range of the time-axis data of the sound (step S154). In addition, the extraction unit 17 acquires, as the occurrence time zone, the time zone in which the state of the vehicle V during the reproduction test indicated by the vehicle state information (physical quantity) acquired by the vehicle state acquisition unit 15 matches the driving state included in the inquiry information within the acquisition time range of the time-axis data of the sound (step S157). Thereby, the occurrence time zone can be appropriately acquired, so that it is possible to further improve the accuracy of the diagnosis result of the cause of the abnormal noise.

[0046] Furthermore, the extraction unit 17 extracts characteristic frequencies at which the sound pressure changes by a predetermined threshold value (predetermined value) or more between the occurrence time zone, which is the time zone in which the physical quantity of the vehicle state information matches the physical quantity included in the interview information, and the time zone in which the physical quantity of the vehicle state information does not match the physical quantity included in the interview information (steps S155, S158). Thereby, it becomes possible to appropriately narrow down the frequency range of the spectrogram to be analyzed by the abnormal sound diagnosis unit 21 of the server 20 based on the interview information and the like.

[0047] In addition, the interview information and the vehicle state information in the abnormal sound diagnosis system 1 include, as information indicating the state of the vehicle V, a physical quantity that changes when the vehicle is running and the driving state of the vehicle V. Thereby, it becomes possible to accurately diagnose the cause of the abnormal sound generated in the vehicle V. However, the interview information and the vehicle state information may include only either one of the physical quantity that changes when the vehicle V is running and the driving state of the vehicle V.

[0048] Furthermore, the mobile terminal 10 constituting the abnormal sound diagnosis system 1 includes a display unit 11 that displays a range corresponding to the estimated frequency range of the spectrogram extracted by the extraction unit 17 in step S159, and allows an operator to select a desired range of the spectrogram displayed on the display unit 11 (step S130: NO, step S135). Thereby, the operator who is a user of the abnormal sound diagnosis system 1 can confirm the extraction result by the extraction unit 17 from the spectrogram (analysis range) displayed on the display unit 11 and can further narrow down the analysis range. In addition, an operator with little experience in using the abnormal sound diagnosis system 1 can learn an effective way of selecting the spectrogram on the display unit 11 by confirming the extraction result by the extraction unit 17 and the diagnosis result by the abnormal sound diagnosis unit 21 of the server 20.

[0049] In addition, the abnormal sound diagnosis unit 21 of the server 20 diagnoses the cause of the abnormal sound based on the time-axis data of the sound acquired by the sound acquisition unit 14, the inquiry information acquired by the inquiry information acquisition unit 13, and at least any one of the estimated frequency range, occurrence time zone, and characteristic frequency acquired or extracted by the extraction unit 17 through the processes of steps S151 - S158, or information defining a range selected by an operator from among the analysis ranges extracted by the extraction unit 17. Thereby, it becomes possible to accurately diagnose the cause of the abnormal sound. That is, providing at least any one of the estimated frequency range, occurrence time zone, and characteristic frequency acquired or extracted by the extraction unit 17, or information defining the final analysis range to the abnormal sound diagnosis unit 21 is extremely useful for improving the diagnosis accuracy of the abnormal sound. Then, by constructing the abnormal sound diagnosis unit 21 by supervised learning so as to diagnose the cause of the abnormal sound based on the provided information, the diagnosis accuracy of the abnormal sound can be further improved.

[0050] Furthermore, the abnormal sound diagnosis system 1 includes a mobile terminal 10 including an inquiry information acquisition unit 13, a sound acquisition unit 14, a vehicle state acquisition unit 15, an arithmetic processing unit 16, and an extraction unit 17, and a server 20 as an information processing device that includes an abnormal sound diagnosis unit 21 and exchanges information with the mobile terminal 10 through communication. Thereby, it becomes possible to easily acquire the time-axis data of the sound emitted from the vehicle V, and at the same time, the load on the mobile terminal 10 can be reduced and an accurate diagnosis result can be obtained by the server 20.

[0051] Note that the abnormal sound diagnosis support application (program) installed in the mobile terminal 10 may be installed in a tablet terminal, a laptop personal computer, a desktop personal computer, or the like, and the tablet terminal or the like may be used instead of the mobile terminal 10. Further, when using a desktop personal computer, after acquiring the time-axis data of the sound and the vehicle state information from the vehicle V by a smartphone or the like, the data may be transferred from the smartphone or the like to the personal computer. Furthermore, the abnormal sound diagnosis application installed in the server 20 may be installed in the mobile terminal 10, a tablet terminal, a laptop personal computer, a desktop personal computer, or the like. That is, the abnormal sound diagnosis system 1 may be configured by a single information processing device.

[0052] Also, the arithmetic processing unit 16 of the mobile terminal 10 acquires a spectrogram showing the relationship between time, frequency, and sound pressure from the time-axis data of the sound emitted from the vehicle V acquired by the sound acquisition unit 14, but is not limited thereto. That is, the arithmetic processing unit 16 may acquire only the relationship between time and sound pressure from the time-axis data of the sound. Furthermore, the object of the abnormal sound diagnosis system 1 is not limited to the vehicle V. That is, the abnormal sound diagnosis system 1 may be applied to the diagnosis of abnormal sounds generated in railway vehicles, ships, aircraft, industrial machines, etc.

[0053] Incidentally, in the vehicle V, there are cases where onomatopoeias are the same among a plurality of different abnormal noises with different generation locations in the vehicle V, despite different frequency ranges. Based on this, in the abnormal noise diagnosis system 1, the inquiry information input to the mobile terminal 10 may include the generation location of the abnormal noise in the vehicle V so that an operator, owner, or the like can specify the generation location of the abnormal noise. That is, as shown in FIG. 11, the input screen (inquiry form) of the inquiry information displayed on the display unit 11 of the mobile terminal 10 (or the above website) may include an input field for specifying (selecting) the generation location of the abnormal noise. In this case, the generation location of the abnormal noise is selected by an operator, owner, or the like from a drop-down list including a plurality of vehicle parts such as the engine, power train, body, brakes, doors, and interior.

[0054] FIG. 12 is an explanatory diagram showing a table that can be applied in step S152 of FIG. 3 when the generation location of the abnormal noise is included in the inquiry information. The table shown in FIG. 12 is also created in advance so as to associate each of a plurality of selectable onomatopoeias as inquiry information with the corresponding frequency range of the abnormal noise, the corresponding characteristics of the abnormal noise, and the onomatopoeias of other abnormal noises similar to the corresponding abnormal noise, and is stored in the auxiliary storage device M of the mobile terminal 10. Further, the table shown in FIG. 12 is created so as to associate at least any one of a plurality of onomatopoeias (in the example of FIG. 12, for example, "katakata" and "karakara") with a plurality of possible generation locations (for example, "engine" and "body") where the abnormal noise corresponding to the onomatopoeia may occur, and the frequency range of the abnormal noise corresponding to the onomatopoeia at each of the plurality of generation locations.

[0055] Furthermore, in the table shown in FIG. 12, for the onomatopoeia associated with a plurality of occurrence locations, the frequency range from the minimum frequency (in the example of FIG. 12, "0.5 kHz" of "engine") to the maximum frequency (in the example of FIG. 12, "5 kHz" of "body") of the frequency range of the plurality of occurrence locations is associated as the frequency range when the occurrence location of the abnormal sound is not specified (selected) by the operator, owner, etc. (when the occurrence location is unknown). Such a table in FIG. 12 is also updated by the server 20 based on information obtained from a large number of vehicles at the timing when a new abnormal sound occurs in the vehicle V or periodically, and information on abnormal sounds newly found to occur in the vehicle V transmitted from automobile manufacturers (developers, etc.), vehicle dealerships, repair shops, etc.

[0056] And when the inquiry information includes the occurrence location of the abnormal sound and at least one of the plurality of onomatopoeia is associated with a plurality of occurrence locations and a plurality of frequency ranges, in step S152 of FIG. 3, the frequency range corresponding to the onomatopoeia and the occurrence location specified (selected) in the inquiry information is obtained as the estimated frequency range of the abnormal sound that occurred in the vehicle V from the table shown in FIG. 12. That is, when "katakata" is specified (selected) as the onomatopoeia and "engine" is specified (selected) as the occurrence location by the operator, owner, etc., in step S152 of FIG. 3, as can be seen from FIGS. 12 and 13, a range of 0.5 - 4 kHz is obtained as the estimated frequency range. Also, when "katakata" is specified (selected) as the onomatopoeia and the occurrence location is not specified (selected) by the operator, owner, etc., in step S152 of FIG. 3, as can be seen from FIG. 13, a range of 0.5 - 5 kHz is obtained as the estimated frequency range.

[0057] Thus, in the abnormal noise diagnosis system 1, in addition to onomatopoeia, it is possible to specify the location where the abnormal noise occurs, and it is also possible to associate a plurality of occurrence locations and a plurality of frequency ranges with at least any one of the plurality of onomatopoeia. This makes it possible to further improve the accuracy of the diagnosis result of the abnormal noise generated in the vehicle V by the abnormal noise diagnosis unit 21 of the server 20. Also, the table in FIG. 12 is updated by the server 20 over time. Therefore, for onomatopoeia that were not initially associated with a plurality of occurrence locations (where the occurrence locations are "common"), it is possible to later associate a plurality of occurrence locations and a plurality of frequency ranges. This makes it possible to further improve the accuracy of the diagnosis result of the abnormal noise by the abnormal noise diagnosis unit 21.

[0058] As described above, the abnormal noise diagnosis system of the present disclosure is an abnormal noise diagnosis system (1) for diagnosing abnormal noise generated in an object (V), including a sound acquisition unit (14) that acquires sound data emitted from the object (V), an inquiry information acquisition unit (13) that acquires inquiry information regarding the abnormal noise generated in the object (V), an arithmetic processing unit (16, S110) that acquires a spectrogram showing the relationship between time, frequency, and sound pressure from the sound data, an extraction unit (17, S150, S152, S159) that acquires an estimated frequency range of the abnormal noise generated in the object (V) based on the inquiry information acquired by the inquiry information acquisition unit (13) and extracts a range corresponding to the estimated frequency range of the spectrogram acquired by the arithmetic processing unit (16), and a diagnosis unit (20, 21) that diagnoses the cause of the abnormal noise generated in the object (V) based on the range extracted by the extraction unit (17) of the spectrogram.

[0059] The abnormal sound diagnosis system of the present disclosure acquires a spectrogram showing the relationship between time, frequency, and sound pressure from the sound data emitted from the object, and acquires an estimated frequency range of the abnormal sound generated in the object based on the inquiry information acquired by the inquiry information acquisition unit. Further, the abnormal sound diagnosis system extracts a range corresponding to the estimated frequency range of the spectrogram, and diagnoses the cause of the abnormal sound generated in the object based on the extracted range. In this way, by selecting on the system side the range of the spectrogram to be analyzed by the diagnosis unit based on the inquiry information, it becomes possible to ensure good accuracy of the diagnosis result of the cause of the abnormal sound. Further, the user of the abnormal sound diagnosis system does not have to select the range of the spectrogram to be analyzed by the diagnosis unit himself / herself. As a result, even a user with little experience in using the abnormal sound diagnosis system can easily obtain an accurate diagnosis result of the abnormal sound generated in the object.

[0060] Further, the abnormal sound diagnosis system (1) may include a storage device (M) that associates and stores onomatopoeia and a frequency range for each of the plurality of abnormal sounds generated in the object (V). The inquiry information may include the onomatopoeia similar to the abnormal sound generated in the object (V). The extraction unit (17) may acquire, as the estimated frequency range, the frequency range corresponding to the onomatopoeia included in the inquiry information from the information stored in the storage device (M) (S150, S152). Thereby, the user of the abnormal sound diagnosis system, the owner of the object, etc. can easily obtain an accurate diagnosis result by selecting onomatopoeia close to the abnormal sound generated in the object.

[0061] Furthermore, the interview information may include the location where the abnormal sound occurs, and the storage device (M) may store by associating at least one of the plurality of onomatopoeic words with the plurality of the occurrence locations and the frequency range of the abnormal sound at each of the plurality of the occurrence locations, and the extraction unit (17) may acquire, as the estimated frequency range, the frequency range corresponding to the onomatopoeic word and the occurrence location included in the interview information from the information stored in the storage device (M) (S150, S152). Thereby, it becomes possible to further improve the accuracy of the diagnosis result of the abnormal sound generated in the object by the diagnosis unit.

[0062] In addition, the abnormal sound diagnosis system (1) may include a display unit (11) that displays a range corresponding to the estimated frequency range of the spectrogram extracted by the extraction unit (17), and may allow a user to select a desired range of the spectrogram displayed on the display unit (11) (S130: NO, S135). Thereby, the user of the abnormal sound diagnosis system can confirm the extraction result by the extraction unit from the spectrogram displayed on the display unit and can narrow down the further analysis range. In addition, a user with little experience in using the abnormal sound diagnosis system can learn an effective way of selecting the spectrogram on the display unit by confirming the extraction result by the extraction unit and the diagnosis result by the diagnosis unit.

[0063] In addition, the diagnosis unit (21) may diagnose the cause of the abnormal sound based on the sound data acquired by the sound acquisition unit (14), the interview information acquired by the interview information acquisition unit (13), and the range selected by the user from the estimated frequency range or the range corresponding to the estimated frequency range of the spectrogram displayed on the display unit (11). Thereby, it becomes possible to accurately diagnose the cause of the abnormal sound.

[0064] Furthermore, the diagnosis unit (21) may be constructed by supervised learning so as to diagnose the cause of the abnormal sound based on the given information. Thereby, it becomes possible to further improve the diagnosis accuracy of the abnormal sound.

[0065] Further, the abnormal sound diagnosis system (1) may include a mobile terminal (10) including the inquiry information acquisition unit (13), the sound acquisition unit (14), the arithmetic processing unit (16), and the extraction unit (17), and an information processing apparatus (20) including the diagnosis unit (21) and communicating with the mobile terminal (10) to exchange information. Thereby, it is possible to easily acquire sound data, reduce the load on the mobile terminal, and obtain an accurate diagnosis result by the information processing apparatus.

[0066] Moreover, another abnormal sound diagnosis system of the present disclosure is an abnormal sound diagnosis system (1) for diagnosing an abnormal sound generated in an object, including a sound acquisition unit (14) for acquiring sound data emitted from the object (V), an inquiry information acquisition unit (13) for acquiring inquiry information regarding the abnormal sound generated in the object (V), an arithmetic processing unit (16) for acquiring at least the relationship between time and sound pressure from the sound data, an extraction unit (17, S154 - S155, S157 - S158, S159) for acquiring a generation time zone in which the abnormal sound is generated in the object (V) based on the inquiry information acquired by the inquiry information acquisition unit (13) and extracting a range corresponding to the generation time zone of the relationship between time and sound pressure acquired by the arithmetic processing unit (16), and a diagnosis unit (21) for diagnosing the cause of the abnormal sound generated in the object (V) based on the range extracted by the extraction unit (17) of the relationship between time and sound pressure.

[0067] Other abnormal sound diagnosis systems of the present disclosure acquire at least the relationship between time and sound pressure from the sound data emitted from the object, and acquire the time zone in which the abnormal sound occurred in the object based on the inquiry information acquired by the inquiry information acquisition unit. Further, the abnormal sound diagnosis system extracts a range corresponding to the occurrence time zone of the relationship between time and sound pressure, and diagnoses the cause of the abnormal sound generated in the object based on the extracted range. In this way, by selecting on the system side the range of the relationship between time and sound pressure to be analyzed by the diagnosis unit based on the inquiry information, it is possible to ensure good accuracy of the diagnosis result of the cause of the abnormal sound. Further, the user of the abnormal sound diagnosis system does not have to select the range of the relationship between time and sound pressure to be analyzed by the diagnosis unit himself / herself. As a result, even a user with little experience in using the abnormal sound diagnosis system can easily obtain an accurate diagnosis result of the abnormal sound generated in the object.

[0068] Further, the abnormal sound diagnosis system (1) may include a state acquisition unit (15) that acquires the state of the object (V) in synchronization with the acquisition of the sound data by the sound acquisition unit (14). The inquiry information may include the state of the object (V) when the abnormal sound occurred. The extraction unit (17) may acquire, as the occurrence time zone, a time zone in which the state of the object (V) acquired by the state acquisition unit (15) matches the state of the object (V) included in the inquiry information among the acquisition time range of the sound data (S154, S157). Thereby, since the occurrence time zone can be appropriately acquired, it is possible to further improve the accuracy of the diagnosis result of the cause of the abnormal sound.

[0069] Furthermore, the arithmetic processing unit (16) may acquire a spectrogram showing the relationship between time, frequency, and sound pressure from the sound data, and the extraction unit (17) may determine that the state of the object (V) acquired by the state acquisition unit (15) matches the state of the object (V) included in the interview information. It is also possible to extract the frequencies at which the sound pressure changes by a predetermined value or more between the time zone and the time zone in which the state of the object (V) acquired by the state acquisition unit (15) does not match the state of the object (V) included in the interview information (S155, S158). This makes it possible to appropriately narrow down the frequency range of the spectrogram to be analyzed by the diagnosis unit based on the interview information.

[0070] Further, the object (V) may be a vehicle, and the state of the object (V) may include at least one of a physical quantity that changes when the vehicle travels and the driving state of the vehicle. This makes it possible to accurately diagnose the cause of abnormal sounds generated in the vehicle.

[0071] Furthermore, the abnormal sound diagnosis system (1) may include a display unit (11) that displays a range corresponding to the occurrence time zone of the relationship between the time and the sound pressure extracted by the extraction unit (17), and allows the user to select a desired range of the relationship between the time and the sound pressure displayed on the display unit (11) (S130: NO, S135). This enables the user of the abnormal sound diagnosis system to confirm the extraction result by the extraction unit from the relationship between the time and the sound pressure displayed on the display unit and to further narrow down the range. In addition, users with little experience using the abnormal sound diagnosis system can learn an effective way to select the relationship between the time and the sound pressure on the display unit by confirming the extraction result by the extraction unit and the diagnosis result by the diagnosis unit.

[0072] Further, the diagnosis unit (21) may diagnose the cause of the abnormal sound based on the sound data acquired by the sound acquisition unit (14), the interview information acquired by the interview information acquisition unit (13), the occurrence time zone, or the time range selected by the user from the range corresponding to the occurrence time zone of the relationship between the time and the sound pressure displayed on the display unit (11). This makes it possible to accurately diagnose the cause of the abnormal sound.

[0073] Furthermore, the diagnosis unit (21) may be constructed by supervised learning so as to diagnose the cause of the abnormal sound based on the given information. This makes it possible to further improve the diagnostic accuracy of the abnormal sound.

[0074] In addition, the abnormal sound diagnosis system (1) may include a mobile terminal (10) including the interview information acquisition unit (13), the sound acquisition unit (14), the arithmetic processing unit (16), and the extraction unit (17), and an information processing device (20) including the diagnosis unit (21) and communicating with the mobile terminal (10) to exchange information. This makes it possible to easily acquire sound data, reduce the load on the mobile terminal, and obtain an accurate diagnostic result by the information processing device.

[0075] It goes without saying that the invention of the present disclosure is not limited to the above-described embodiments, and various modifications can be made within the scope of the extension of the present disclosure. Furthermore, the above-described embodiments are merely specific forms of the invention described in the summary section of the invention, and do not limit the elements of the invention described in the summary section of the invention.

Industrial Applicability

[0076] The invention of the present disclosure is extremely useful for diagnosing abnormal sounds generated in objects such as vehicles.

Explanation of Signs

[0077] 1 Abnormal sound diagnosis system, 10 Mobile terminal, 11 Display unit, 12 Communication module, 13 Inquiry information acquisition unit, 14 Sound acquisition unit, 15 Vehicle state acquisition unit, 16 Arithmetic processing unit, 17 Extraction unit, 18 Display control unit, 20 Server, 21 Abnormal sound diagnosis unit, 22 Memory device, V Vehicle.

Claims

1. A abnormal sound diagnosis system for diagnosing abnormal sounds generated in an object, a sound acquisition unit that acquires data of sounds emitted from the object; an inquiry information acquisition unit that acquires inquiry information regarding the abnormal sound generated in the object; an arithmetic processing unit that acquires a spectrogram showing the relationship between time, frequency, and sound pressure from the sound data; an extraction unit that acquires an estimated frequency range of the abnormal sound generated in the object based on the inquiry information acquired by the inquiry information acquisition unit, and extracts a range corresponding to the estimated frequency range of the spectrogram acquired by the arithmetic processing unit; a diagnosis unit that diagnoses the cause of the abnormal sound generated in the object based on the range extracted by the extraction unit of the spectrogram; An abnormal sound diagnosis system comprising:

2. The abnormal sound diagnosis system according to claim 1, further comprising a storage device that associates and stores onomatopoeia and a frequency range for each of a plurality of the abnormal sounds generated in the object, the inquiry information includes the onomatopoeia similar to the abnormal sound generated in the object, The extraction unit acquires, as the estimated frequency range, the frequency range corresponding to the onomatopoeia included in the inquiry information from the information stored in the storage device. An abnormal sound diagnosis system.

3. The abnormal sound diagnosis system according to claim 2, the inquiry information includes the location where the abnormal sound occurs, the storage device stores, for at least one of a plurality of the onomatopoeia, a plurality of the occurrence locations and the frequency range of the abnormal sound at each of the plurality of the occurrence locations in association with each other, The extraction unit acquires, as the estimated frequency range, the frequency range corresponding to the onomatopoeia and the occurrence location included in the inquiry information from the information stored in the storage device. An abnormal sound diagnosis system.

4. In the abnormal sound diagnosis system according to any one of claims 1 to 3, further comprising a display unit that displays a range corresponding to the estimated frequency range of the spectrogram extracted by the extraction unit, and an abnormal sound diagnosis system that allows a user to select a desired range of the spectrogram displayed on the display unit.

5. In the abnormal sound diagnosis system according to claim 4, the diagnosis unit diagnoses the cause of the abnormal sound based on the sound data acquired by the sound acquisition unit, the interview information acquired by the interview information acquisition unit, and the range selected by the user from the estimated frequency range or the range corresponding to the estimated frequency range of the spectrogram displayed on the display unit. An abnormal sound diagnosis system.

6. In the abnormal sound diagnosis system according to claim 5, the diagnosis unit is an abnormal sound diagnosis system constructed by supervised learning so as to diagnose the cause of the abnormal sound based on the given information.

7. In the abnormal sound diagnosis system according to any one of claims 1 to 3, An abnormal sound diagnosis system comprising a mobile terminal including the interview information acquisition unit, the sound acquisition unit, the arithmetic processing unit, and the extraction unit, and an information processing device including the diagnosis unit and communicating with the mobile terminal to exchange information.

Images