WO2020001130A1 - 扫地机器人故障诊断 - Google Patents

扫地机器人故障诊断 Download PDF

Info

Publication number
WO2020001130A1
WO2020001130A1 PCT/CN2019/082505 CN2019082505W WO2020001130A1 WO 2020001130 A1 WO2020001130 A1 WO 2020001130A1 CN 2019082505 W CN2019082505 W CN 2019082505W WO 2020001130 A1 WO2020001130 A1 WO 2020001130A1
Authority
WO
WIPO (PCT)
Prior art keywords
audio
correlation
working
sample
sample audio
Prior art date
Application number
PCT/CN2019/082505
Other languages
English (en)
French (fr)
Inventor
郭斌
苏辉
蒋海青
Original Assignee
杭州萤石软件有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 杭州萤石软件有限公司 filed Critical 杭州萤石软件有限公司
Publication of WO2020001130A1 publication Critical patent/WO2020001130A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass
    • G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/24—Floor-sweeping machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L9/00—Details or accessories of suction cleaners, e.g. mechanical means for controlling the suction or for effecting pulsating action; Storing devices specially adapted to suction cleaners or parts thereof; Carrying-vehicles specially adapted for suction cleaners
    • A47L9/28—Installation of the electric equipment, e.g. adaptation or attachment to the suction cleaner; Controlling suction cleaners by electric means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass

Definitions

  • the present application relates to the technical field of sweeping robots, and in particular, to a fault diagnosis method of a sweeping robot, a sweeping robot, and a storage medium.
  • the sweeping robot mainly uses the internal power source to generate suction at the suction ports of various air ducts, and then sucks the dust and particles on the ground into the dust collection device through the suction.
  • the drive and driven wheels can entangle hair
  • the side brush and roller brush can entangle not only hair but also objects such as wire harnesses.
  • a small amount of entanglement of foreign objects such as hair or harnesses will not affect the normal operation of the cleaning robot.
  • it may affect the normal operation of the cleaning robot. For example, when there are many foreign objects, the cleaning effect of the cleaning robot is poor. Therefore, it is necessary to diagnose the fault caused by the foreign object entanglement to ensure the normal operation of the cleaning robot.
  • the present application provides a fault diagnosis method of a cleaning robot and a cleaning robot.
  • the first aspect of the present application provides a cleaning robot fault diagnosis method, the method is applied to the cleaning robot, the method includes: acquiring a first working audio when the cleaning robot is working; combining the first working audio with a previously stored address The first sample audio of the cleaning robot is compared to obtain a correlation between the first working audio and the first sample audio. Based on the correlation, it is determined whether the cleaning robot has a fault.
  • a second aspect of the present application provides a cleaning robot, which includes an audio acquisition module, a memory, and a processor.
  • the audio acquisition module is configured to acquire a first working audio of the cleaning robot while working;
  • the memory is configured to store a first sample audio of the cleaning robot;
  • the processor is configured to convert the first The working audio is compared with the first sample audio to obtain a correlation between the first working audio and the first sample audio, and whether the cleaning robot is faulty is determined according to the correlation.
  • a third aspect of the present application provides a computer storage medium having stored thereon a computer program that, when executed by a processor, implements the steps of any of the methods provided in the first aspect of the present application.
  • the cleaning robot fault diagnosis method and the cleaning robot provided by the present application obtain the first working audio of the cleaning robot while working, and then compare the first working audio with the first sample audio of the cleaning robot stored in advance to obtain the first The correlation between the working audio and the first sample audio, so as to determine whether the cleaning robot has a fault according to the correlation. In this way, when the foreign object is entangled, the sound of the cleaning robot during work changes, so the application can diagnose the fault caused by the abnormal entanglement according to the sound change, and has good adaptability.
  • FIG. 1 is a flowchart of Embodiment 1 of a fault diagnosis method for a cleaning robot provided by this application; FIG.
  • FIG. 2 is a flowchart of a second embodiment of a fault diagnosis method for a cleaning robot provided by this application;
  • FIG. 3 is a flowchart of a third embodiment of a fault diagnosis method for a cleaning robot provided by this application;
  • Embodiment 4 is a flowchart of Embodiment 4 of a fault diagnosis method for a cleaning robot provided by this application;
  • Embodiment 5 is a flowchart of Embodiment 5 of a fault diagnosis method for a cleaning robot provided by this application;
  • Embodiment 6 is a flowchart of Embodiment 6 of a fault diagnosis method for a cleaning robot provided by this application;
  • FIG. 7 is a hardware structural diagram of a cleaning robot according to an exemplary embodiment of the present application.
  • first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other.
  • first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information.
  • word “if” as used herein can be interpreted as “at” or "when” or "in response to determination”.
  • the fault diagnosis method of the sweeping robot based on the driving current of the motor is not suitable for diagnosing faults caused by abnormal winding, and has poor applicability.
  • the present application provides a floor cleaning robot fault diagnosis method and a floor cleaning robot, so as to solve the problem that the existing fault diagnosis method is not suitable for diagnosing faults caused by abnormal winding and has poor applicability.
  • FIG. 1 is a flowchart of Embodiment 1 of a fault diagnosis method for a cleaning robot provided by this application.
  • the method provided in this embodiment may include:
  • fault diagnosis when a fault diagnosis instruction is received, fault diagnosis is triggered.
  • the fault diagnosis instruction may be sent by the user to the cleaning robot through the client.
  • the fault diagnosis instruction may be generated when a specified button on the cleaning robot is performed with a specified operation.
  • fault diagnosis may be performed according to a preset diagnosis period.
  • when it is detected that the running time of the cleaning robot reaches a specified time fault diagnosis may be performed.
  • the triggering manner of the fault diagnosis is not limited.
  • a first working audio of a specified duration may be recorded.
  • the specified duration is set according to actual needs.
  • the specified duration may be 1Min, 5Min, or the like.
  • the first sample audio of the pre-stored cleaning robot may be pre-stored in the cleaning robot at the factory.
  • the first sample audio may include at least one abnormal sample audio when the cleaning robot works abnormally.
  • the first sample audio includes abnormal sample audio when three cleaning robots work abnormally. For easy differentiation, they are abnormal sample audio 1, abnormal sample audio 2 and abnormal sample audio 3.
  • the first working audio is compared with the three abnormal sample audios to obtain the correlation between the first working audio and the abnormal sample audio 1, and the first working audio and the abnormal sample audio 2 are obtained. , The correlation between the first working audio and the abnormal sample audio 3.
  • step S102 may include: extracting the Mel frequency cepstrum MFCC parameters of the first working audio and the first sample audio, and then according to the first working audio, The MFCC parameter and the MFCC parameter of the first sample audio determine the correlation between the first working audio and the first sample audio. It should be noted that at this time, the correlation characterizes the degree of difference between the first working audio and the first sample audio.
  • the absolute value of the difference between the MFCC parameters of the first working audio and the MFCC parameters of the first sample audio may be determined as Correlation between the first working audio and the first sample audio.
  • step S103 may include: when the correlation between the first working audio and any abnormal sample audio is less than or equal to the first specified value, determining that the cleaning robot is faulty, and when the first working audio and all abnormalities When the correlation between the sample audio is greater than the first specified value, it is determined that the cleaning robot is not faulty.
  • the cleaning robot is determined to be faulty; when any of the three correlations is greater than the first specified value, the cleaning is determined The robot is not malfunctioning.
  • the method provided in this embodiment obtains the first working audio by using the first working audio of the cleaning robot and comparing the first working audio with the first sample audio of the cleaning robot stored in advance. Correlation between the audio, so as to determine whether the cleaning robot is faulty according to the above correlation. In this way, when the foreign object is entangled, the sound of the cleaning robot during work will change. Therefore, the method can diagnose faults caused by abnormal entanglement and has good adaptability.
  • FIG. 2 is a flowchart of Embodiment 2 of a fault diagnosis method for a cleaning robot provided by this application. This embodiment relates to a specific process of how to obtain the correlation between the working audio and the sample audio. Referring to FIG. 2, the method provided in this embodiment, step S102, may include:
  • the energy value of the audio may be calculated according to a first formula, and the first formula is:
  • E is the energy value of the audio
  • ai is the sampling value of the i-th sampling point in the audio
  • v is the average value of the sampling values of all the sampling points in the audio.
  • sampling value may be a sampling value in the time domain or a sampling value in the frequency domain.
  • audio is a time domain signal
  • the energy value can be calculated based on the time domain signal; or the time domain signal is Fourier transformed to obtain a frequency domain signal, and the energy value is calculated based on the frequency domain signal.
  • S202 Calculate an absolute value of a difference between the energy value of the first working audio and the energy value of the first sample audio, and use the absolute value as the difference between the first working audio and the first sample audio.
  • the correlation between the working audio and the sample audio represents the degree of difference between the working audio and the sample audio.
  • the correlation calculated in this embodiment represents the degree of difference between the first working audio and the first sample audio. Further, fault diagnosis may be performed based on the correlation. The specific implementation principle and implementation process of the fault diagnosis will be described in detail in the following embodiments, and will not be repeated here.
  • the energy value of the first working audio is 30, the energy value of the abnormal sample audio 1 is 90, the energy value of the abnormal sample audio 2 is 75, and the energy value of the abnormal sample audio 3 is The energy value is 87.
  • the correlation between the first working audio and the abnormal sample audio 1 is 60, and the correlation between the first working audio and the abnormal sample audio 2 is 45.
  • the correlation between audio and abnormal sample audio 3 is 57.
  • the method provided in this embodiment provides a method for calculating the correlation between the working audio and the sample audio.
  • the correlation between the working audio and the sample audio time can be calculated more accurately, and then based on the correlation Troubleshooting.
  • step S102 may include:
  • the correlation degree indicates the degree of difference between the working audio and the sample audio.
  • the energy error is calculated according to the following formula:
  • D is the energy error between the first working audio and the first sample audio
  • X (t) is the first working audio and the sampling window is t
  • a (t) is the first sample audio and the sampling window is t
  • C is constant.
  • the correlation calculated in this embodiment represents the degree of difference between the first working audio and the first sample audio. Further, fault diagnosis may be performed based on the correlation. The specific implementation principle and implementation process of the fault diagnosis will be described in detail in the following embodiments, and will not be repeated here.
  • the method provided in this embodiment provides another method for calculating the correlation between the working audio and the sample audio.
  • the correlation between the working audio and the sample audio time can be calculated more accurately, and then based on the correlation Perform troubleshooting.
  • FIG. 3 is a flowchart of Embodiment 3 of a fault diagnosis method for a cleaning robot provided by this application. Based on the above embodiment, please refer to FIG. 3.
  • the first sample audio includes the audio when the cleaning robot works normally.
  • Step S103 may include:
  • the correlation characterizes the degree of difference between the working audio and the sample audio, that is, the smaller the correlation, The smaller the difference between the working audio and the sample audio, the more similar the working audio is to the sample audio.
  • the correlation between the first working audio and the first sample audio is less than the first specified value, it means that the first working audio is similar to the first sample audio, and the first sample audio is the normal work of the cleaning robot. Audio, therefore, at this time, it is determined that the cleaning robot is not malfunctioning.
  • the correlation between the first working audio and the first sample audio is greater than or equal to the first specified value, it indicates that the difference between the first working audio and the first sample audio is large, and the two are not similar. At this point, it is determined that there is a malfunction.
  • the first specified value is set according to actual needs.
  • the specific value of the first specified value is not limited.
  • the first specified value may be 5, 10, or the like.
  • the following uses the first specified value as an example for description.
  • the correlation between the first working audio and the first sample audio is calculated as 50, which indicates that the first working audio is significantly different from the first sample audio, and the first sample audio is when the cleaning robot works normally. Audio, therefore, at this time, it is determined that the cleaning robot is faulty.
  • the correlation between the first working audio and the first sample audio is calculated to be 3. At this time, the difference between the first working audio and the first sample audio is small. At this time, it is determined that the cleaning robot does not exist malfunction.
  • the sample audio of the cleaning robot during normal work is stored in advance, and then the working audio of the cleaning robot is obtained when the cleaning robot is actually working, and the working audio is compared with the sample audio to obtain the interval between the two. Correlation, and the correlation characterizes the degree of difference between the two. In this way, when the correlation between the two is less than the first specified value, it is determined that there is no fault in the cleaning robot, and when the correlation between the two is greater than or equal to the first specified value, it is determined that the cleaning robot is faulty. In this way, faults caused by foreign matter entanglement can be diagnosed, and the applicability is good.
  • FIG. 4 is a flowchart of Embodiment 4 of a fault diagnosis method for a cleaning robot provided by this application.
  • the method may further include:
  • the designated component includes at least one of the following components: a driving wheel, a driven wheel, a side brush, a roller brush, and a fan.
  • the following description uses the specified components including a driving wheel and a driven wheel as an example.
  • this step S401 only the driving wheel can be started first, and the audio when the driving wheel works is obtained as the second working audio, and then only the driven wheel is started to obtain the driven wheel The working audio is used as the second working audio.
  • the method shown in FIG. 2 can be used to calculate the correlation between the second working audio and the second sample audio.
  • S403. Determine whether there is a fault in the specified component according to a correlation between the second working audio and the second sample audio.
  • the second sample audio may include normal sample audio when the specified component of the cleaning robot works normally, and the correlation between the second work audio and the second sample audio is equal to The absolute value of the difference between the energy value of the second working audio and the energy value of the second sample audio, or the energy error between the second working audio and the second sample audio.
  • the correlation between the second working audio and the second sample audio characterizes the difference between the two.
  • the second sample audio of the specified component stored in advance may include the normal sample audio when the specified component works normally and the abnormal sample audio when the specified component works abnormally, and
  • the correlation between the second working audio and the second sample audio is equal to the absolute value of the difference between the energy value of the second working audio and the energy value of the second sample audio or the energy between the second working audio and the second sample audio
  • the specific implementation process of this step may include:
  • the correlation between the working audio of the driving wheel and the normal sample audio is calculated as 10, and the working audio of the driving wheel is abnormal.
  • the correlation between the sample audio is 50.
  • the correlation between the working audio of the driven wheel and the normal sample audio is 30, and the correlation between the working audio of the driven wheel and the abnormal sample audio is 5, at this time, because the driven wheel The difference between the working audio and the abnormal sample audio is small, and it is determined that the driven wheel is faulty.
  • the second working audio of the specified part of the cleaning robot is obtained by obtaining the second working audio of the cleaning robot, and then the second working audio is compared with the second sample audio of the specified part stored in advance. Yes, the correlation between the second working audio and the second sample audio is obtained, so that it can be determined whether the specified component is faulty according to the correlation between the second working audio and the second sample audio. In this way, when the cleaning robot has a fault, it can be further clearly specified whether there is a fault in the component, and the faulty component can be identified.
  • FIG. 5 is a flowchart of Embodiment 5 of a fault diagnosis method for a cleaning robot provided by this application.
  • the method provided in this embodiment may include:
  • the correlation between the first working audio and the first sample audio may be equal to an absolute value of a difference between the energy value of the first working audio and the energy value of the first sample audio, or An energy error between the first working audio and the first sample audio.
  • the first sample audio includes audio when the cleaning robot works normally.
  • step S503 Determine whether the correlation between the first working audio and the first sample audio is less than a first specified value. If yes, perform step S504; if no, perform step S505.
  • the correlation between the second working audio and the second sample audio may be equal to an absolute value of a difference between the energy value of the second working audio and the energy value of the second sample audio, or the first The energy error between a working audio and the first sample audio.
  • the second sample audio includes normal sample audio when the specified component works normally and abnormal sample audio when the specified component works abnormally.
  • the first correlation is the correlation between the second working audio and the normal sample audio
  • the second correlation is the correlation between the second working audio data and the abnormal sample audio.
  • the method provided in this embodiment can not only determine whether there is a fault in the cleaning robot, but also can further determine whether there is a fault in a specified component when determining that the cleaning robot has a fault, so as to clarify the location where the fault occurs.
  • FIG. 6 is a flowchart of Embodiment 6 of a fault diagnosis method for a cleaning robot provided by this application. Referring to FIG. 6, the method provided in this embodiment may include:
  • step S601 For the specific implementation process and implementation principle of step S601, reference may be made to the introduction in the prior art, and details are not described herein again.
  • S602 Compare the first working audio with a first sample audio of the cleaning robot stored in advance to obtain a correlation between the first working audio and the first sample audio.
  • the correlation between the first working audio and the first sample audio may be equal to the number of correlations between the first working audio and the first sample audio.
  • the first sample audio includes audio when the cleaning robot works normally.
  • the number of correlations between the first working audio and the first sample audio is calculated using the following formula:
  • c is the number of correlations between the first working audio and the first sample audio; x (t) is the first working audio and the sampling window is t; A (t) is the first sample audio and the sampling window is t.
  • the correlation between the working audio and the sample audio is equal to the number of correlations between the working audio and the sample audio, and the correlation characterizes the similarity between the working audio and the sample audio. That is, the greater the correlation, the more similar the working audio and the sample audio.
  • step S603. Determine whether the correlation between the first working audio and the first sample audio is greater than or equal to a second specified value. If yes, go to step S604; if no, go to step S605.
  • the correlation between the first working audio and the first sample audio is greater than or equal to a second specified value, it indicates that the first working audio is similar to the first sample audio, and the first sample audio is sweeping. Audio when the robot is working normally, so at this time, make sure that the cleaning robot is not malfunctioning.
  • S605 Determine that the cleaning robot is faulty, and obtain a second working audio when a specified component of the cleaning robot works.
  • the second working audio compares the second working audio with a second sample audio of the specified component that is stored in advance to obtain a correlation between the second working audio and the second sample audio.
  • the correlation between the second working audio and the second sample audio may be equal to the number of correlations between the second working audio and the second sample audio.
  • the second sample audio includes normal sample audio when the specified component works normally and abnormal sample audio when the specified component works abnormally.
  • step S602 For the specific calculation principle of the correlation number, refer to the description in step S602, and details are not described herein again.
  • the first correlation is the correlation between the second working audio and the normal sample audio
  • the second correlation is the correlation between the second working audio data and the abnormal sample audio.
  • the correlation number indicates the degree of similarity between the working audio and the sample audio.
  • the larger the correlation number the more similar the working audio and the sample audio are. Therefore, in this example, when the correlation between the second working audio and the normal sample audio is greater than the correlation between the second working audio data and the abnormal sample audio, it is determined that the state of the designated component is the state corresponding to the normal sample audio, that is, It is determined that the specified part is not faulty; on the contrary, it is determined that the specified part is faulty.
  • the method provided in this embodiment can not only determine whether there is a fault in the cleaning robot, but also can further determine the location where the fault occurs when determining that there is a fault in the cleaning robot.
  • FIG. 7 is a hardware structural diagram of a cleaning robot according to an exemplary embodiment of the present application.
  • the cleaning robot provided in this embodiment may include an audio acquisition module 710, a memory 720, and a processor 730.
  • the audio collection module 710 is configured to obtain a first working audio of the cleaning robot while working
  • the memory 720 is configured to store a first sample audio of the cleaning robot
  • the processor 730 is configured to Comparing the first working audio with the first sample audio to obtain a correlation between the first working audio and the first sample audio, and determining the cleaning robot according to the correlation Whether there is a fault.
  • the cleaning robot provided in this embodiment may be used to execute the technical solution of the method embodiment shown in FIG. 1, and the implementation principles and technical effects thereof are similar, and details are not described herein again.
  • the memory 720 is further configured to store a second sample audio of a specified component of the cleaning robot; in this case, the audio collection module 710 is further configured to determine the cleaning robot on the processor 730 When there is a fault, obtaining a second working audio when a specified component of the cleaning robot works; the processor 730 is further configured to perform the second working audio with a second sample audio of the specified component stored in advance; Compare to obtain the correlation between the second working audio and the second sample audio, and determine whether the specified component exists according to the correlation between the second working audio and the second sample audio. malfunction.
  • comparing the working audio with the sample audio to obtain the correlation between the working audio and the sample audio includes: calculating the energy values of the working audio and the sample audio separately; and calculating the energy values of the working audio.
  • An absolute value of a difference from an energy value of the sample audio, and the absolute value is used as a correlation between the working audio and the sample audio.
  • the correlation between the working audio and the sample audio represents the degree of difference between the working audio and the sample audio.
  • comparing the working audio with the sample audio to obtain the correlation between the working audio and the sample audio including: calculating an energy error between the working audio and the sample audio, and using the energy error as the The correlation between the working audio and the sample audio.
  • the correlation between the working audio and the sample audio represents the degree of difference between the working audio and the sample audio.
  • the sample audio includes the audio of the cleaning robot during normal operation; determining whether there is a fault according to the correlation between the work audio and the sample audio, including: when the correlation between the work audio and the sample audio is less than At the first specified value, it is determined that there is no fault; when the correlation between the working audio and the sample audio is greater than or equal to the first specified value, it is determined that there is a fault.
  • the second sample audio includes a normal sample audio when the designated component works normally and an abnormal sample audio when the designated component works abnormally.
  • the determining whether the specified component is faulty according to the correlation between the second working audio data and the second sample audio includes: comparing a first correlation and a second correlation, wherein the first A correlation is a correlation between the second working audio and the normal sample audio, and the second correlation is a correlation between the second working audio data and the abnormal sample audio; when When the first correlation is greater than or equal to the second correlation, it is determined that the designated component is faulty; when the first correlation is less than the second correlation, it is determined that there is no fault in the designated component.
  • comparing the working audio with the sample audio to obtain the correlation between the working audio and the sample audio including: calculating the number of correlations between the work audio and the sample audio, and using the number of correlations as A correlation between the working audio and the sample audio.
  • the correlation between the working audio and the sample audio represents a degree of similarity between the working audio and the sample audio.
  • the sample audio includes the audio when the robot is working normally; determining whether there is a fault according to the correlation between the work audio and the sample audio, including: when the correlation between the work audio and the sample audio is greater than When it is equal to the second specified value, it is determined that there is no fault; when the correlation between the working audio and the sample audio is less than the second specified value, it is determined that there is a fault.
  • the second sample audio includes normal sample audio when the specified component works normally and abnormal sample audio when the specified component works abnormally; and the second sample audio according to the second working audio data and the second sample audio
  • the degree of correlation between the two components to determine whether the specified component is faulty including: comparing a first degree of correlation with a second degree of correlation; wherein the first degree of correlation is between the second working audio and the normal sample audio
  • the second correlation is the correlation between the second working audio data and the abnormal sample audio; when the first correlation is greater than the second correlation, determining the There is no fault in the designated component; when the first correlation is less than or equal to the second correlation, it is determined that the designated component is faulty.
  • the present application also provides a computer storage medium on which a computer program is stored.
  • the program is executed by a processor, the steps of any fault diagnosis method for a cleaning robot provided by the present application.
  • computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices), magnetic disks (such as internal Hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks.
  • semiconductor memory devices such as EPROM, EEPROM, and flash memory devices
  • magnetic disks such as internal Hard disks or removable disks
  • magneto-optical disks such as CD ROM and DVD-ROM disks.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)

Abstract

一种扫地机器人故障诊断方法和扫地机器人。扫地机器人故障诊断方法包括：获取扫地机器人工作时的第一工作音频(S101)；将第一工作音频与预先存储的扫地机器人的第一样本音频进行比对，得到第一工作音频与第一样本音频之间的相关度(S102)；根据相关度，确定扫地机器人是否存在故障(S103)。

Description

扫地机器人故障诊断
相关申请的交叉引用
本专利申请要求于2018年6月29日提交的、申请号为2018107133515、发明名称为“一种扫地机器人故障诊断方法和扫地机器人”的中国专利申请的优先权，该申请的全文以引用的方式并入本文中。
技术领域
本申请涉及扫地机器人技术领域，尤其涉及一种扫地机器人故障诊断方法、扫地机器人及存储介质。
背景技术
扫地机器人作为一款可以代替用户清扫地面的机器，主要是通过内部的动力源，在各个风道的吸口处产生吸力，进而通过吸力的作用将地面上的灰尘及颗粒物等吸入集尘装置中。
扫地机器人工作时，某些部件可能会缠绕异物。例如，驱动轮和从动轮会缠绕毛发，边刷和滚刷不仅会缠绕毛发，还会缠绕线束等物体。毛发或线束等异物的少量缠绕不会影响扫地机器人正常工作。但一旦异物累积较多时，就可能会影响扫地机器人正常工作。例如，异物较多时，致使扫地机器人的清扫效果较差。因此，需要针对异物缠绕引起的故障进行诊断，以保证扫地机器人正常工作。
发明内容
有鉴于此，本申请提供一种扫地机器人故障诊断方法和扫地机器人。
本申请第一方面提供一种扫地机器人故障诊断方法，所述方法应用于扫地机器人，所述方法包括：获取扫地机器人工作时的第一工作音频；将所述第一工作音频与预先存储的所述扫地机器人的第一样本音频进行比对，得到所述第一工作音频与所述第一样本音频之间的相关度；根据所述相关度，确定所述扫地机器人是否存在故障。
本申请第二方面提供一种扫地机器人，所述扫地机器人包括：音频采集模块、存储 器和处理器。其中，所述音频采集模块用于获取扫地机器人工作时的第一工作音频；所述存储器，用于存储所述扫地机器人的第一样本音频；所述处理器，用于将所述第一工作音频与所述第一样本音频进行比对，得到所述第一工作音频与所述第一样本音频之间的相关度，并根据所述相关度确定所述扫地机器人是否存在故障。
本申请第三方面提供一种计算机存储介质，其上存储有计算机程序，所述程序被处理器执行时实现本申请第一方面提供的任一所述方法的步骤。
本申请提供的扫地机器人故障诊断方法和扫地机器人，通过获取扫地机器人工作时的第一工作音频，进而将第一工作音频与预先存储的扫地机器人的第一样本音频进行比对，得到第一工作音频与第一样本音频之间的相关度，从而根据上述相关度确定扫地机器人是否存在故障。这样，由于异物缠绕时，会导致扫地机器人工作时的声音发生变化，因此，本申请可以根据声音变化诊断因异常缠绕引起的故障，适应性较好。
附图说明
图1为本申请提供的扫地机器人故障诊断方法实施例一的流程图；
图2为本申请提供的扫地机器人故障诊断方法实施例二的流程图；
图3为本申请提供的扫地机器人故障诊断方法实施例三的流程图；
图4为本申请提供的扫地机器人故障诊断方法实施例四的流程图；
图5为本申请提供的扫地机器人故障诊断方法实施例五的流程图；
图6为本申请提供的扫地机器人故障诊断方法实施例六的流程图；
图7为本申请一示例性实施例示出的扫地机器人的硬件结构图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施 例中所描述的实施方式并不代表与本申请相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本申请的一些方面相一致的装置和方法的例子。
在本申请使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本申请可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本申请范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
可通过获取扫地机器人工作时电机的驱动电流，在获取到的驱动电流大于预设阈值时进行报警。但是，少量的异物缠绕一般不会造成电机的驱动电流的变化。因此，基于电机的驱动电流实现的扫地机器人故障诊断方法，并不适用于诊断因异常缠绕引起的故障，适用性较差。
本申请提供一种扫地机器人故障诊断方法和扫地机器人，以解决现有的故障诊断方法不适用于诊断因异常缠绕引起的故障，适用性较差的问题。
下面给出几个具体的实施例，用于详细介绍本申请的技术方案，下面这几个具体的实施例可以相互结合，对于相同或相似的概念或过程可能在某些实施例中不再赘述。
图1为本申请提供的扫地机器人故障诊断方法实施例一的流程图。请参照图1，本实施例提供的方法，可以包括：
S101、获取扫地机器人工作时的第一工作音频。
需要说明的是，在本申请一可能的实现方式中，可以是在接收到故障诊断指令时，触发故障诊断。例如，该故障诊断指令可以是用户通过客户端发送给扫地机器人的。再例如，该故障诊断指令可以是扫地机器人上的指定按键被执行指定操作时生成的。当前，在本申请另一可能的实现方式中，可以按照预设的诊断周期进行故障诊断。此外，在本申请再一可能的实现方式中，可以在检测到扫地机器人的运行时长达到指定时长时，进行故障诊断。本实施例中，不对故障诊断的触发方式进行限定。
具体的，本步骤S101中，在扫地机器人工作时，可录制指定时长的第一工作音频。 该指定时长是根据实际需要设定的，例如，该指定时长可以为1Min，5Min等。
S102、将上述第一工作音频与预先存储的上述扫地机器人的第一样本音频进行比对，得到上述第一工作音频与上述第一样本音频之间的相关度。
具体的，预先存储的扫地机器人的第一样本音频可以是出厂时预先存储在扫地机器人中的。
可选地，在本申请一可能的实现方式中，第一样本音频可以包括至少一个扫地机器人异常工作时的异常样本音频。例如，一实施例中，第一样本音频包括三个扫地机器人异常工作时的异常样本音频。为便于区分，分别即为异常样本音频1、异常样本音频2和异常样本音频3。本步骤S102中，就将第一工作音频分别与这三个异常样本音频进行比对，得到第一工作音频与异常样本音频1之间的相关度、第一工作音频与异常样本音频2之间的相关度、第一工作音频与异常样本音频3之间的相关度。
需要说明的是，在一实施例中，该步骤S102的具体实现过程，可以包括：分别提取第一工作音频和第一样本音频的梅尔频率倒谱MFCC参数，进而根据第一工作音频的MFCC参数和第一样本音频的MFCC参数，确定第一工作音频和第一样本音频之间的相关度。需要说明的是，此时，该相关度表征第一工作音频和第一样本音频之间的差异程度。
具体的，有关提取MFCC参数的具体实现过程和实现原理可以参见相关技术中的描述，此处不再赘述。进一步地，当提取到第一工作音频的MFCC参数和第一样本音频的MFCC参数时，可以将第一工作音频的MFCC参数和第一样本音频的MFCC参数的差值的绝对值确定为第一工作音频与第一样本音频之间的相关度。
S103、根据上述相关度，确定上述扫地机器人是否存在故障。
结合上面的例子，当第一样本音频包括至少一个扫地机器人异常工作时的异常样本音频，且第一样本音频与第一工作音频之间的相关度表征两者之间的差异程度时，该步骤S103的具体实现过程，可以包括：当第一工作音频与任一异常样本音频之间的相关度小于或等于第一指定值时，确定扫地机器人存在故障，当第一工作音频与所有异常样本音频之间的相关度均大于第一指定值时，确定扫地机器人不存在故障。
结合上面的例子，例如，当第一工作音频与异常样本音频1之间的相关度、第一工作音频与异常样本音频2之间的相关度和第一工作音频与异常样本音频3之间的相关度这三个相关度中，存在至少一个相关度小于或等于第一指定值时，确定扫地机器人故障； 当这三个相关度中，任何一个相关度均大于第一指定值时，确定扫地机器人不存在故障。
本实施例提供的方法，通过获取扫地机器人工作时的第一工作音频，进而将第一工作音频与预先存储的扫地机器人的第一样本音频进行比对，得到第一工作音频与第一样本音频之间的相关度，从而根据上述相关度，确定扫地机器人是否存在故障。这样，由于异物缠绕时，会导致扫地机器人工作时的声音发生变化，因此，应用该方法，可诊断因异常缠绕引起的故障，适应性较好。
图2为本申请提供的扫地机器人故障诊断方法实施例二的流程图。本实施例涉及的是如何得到工作音频和样本音频之间的相关度的具体过程。请参照图2，本实施例提供的方法，步骤S102，可以包括：
S201、分别计算第一工作音频和第一样本音频的能量值。
具体的，本步骤S201中，可按照第一公式计算音频的能量值，第一公式为：
E＝∑(ai-v) 2
其中，E为音频的能量值；ai为上述音频中第i个采样点的采样值；v为上述音频中所有采样点的采样值的平均值。
需要说明的是，上述采样值可以是时域下的采样值或频域下的采样值。本实施例中，不对此作出限定。例如，音频为时域信号，可以基于该时域信号计算能量值；或者是，将该时域信号进行傅里叶变换，得到频域信号，进而基于该频域信号计算能量值。
S202、计算上述第一工作音频的能量值与上述第一样本音频的能量值之间的差值的绝对值，并将上述绝对值作为上述第一工作音频与上述第一样本音频之间的相关度；其中，上述工作音频与上述样本音频之间的相关度表征上述工作音频与上述样本音频之间的差异程度。
需要说明的是，本实施例计算得到的相关度，表征第一工作音频与第一样本音频之间的差异程度。进一步地，可基于该相关度进行故障诊断。有关故障诊断的具体实现原理和实现过程将在下面的实施例中详细介绍，此处不再赘述。
结合上面的例子，例如，在一实施例中，计算得到第一工作音频的能量值为30，异常样本音频1的能量值为90，异常样本音频2的能量值为75，异常样本音频3的能量值为87，这样，本步骤中，计算得到第一工作音频与异常样本音频1之间的相关度为60，第一工作音频与异常样本音频2之间的相关度为45，第一工作音频与异常样本音频 3之间的相关度为57。
结合上面的例子，再例如，本例中，假设第一指定值为5，此时，经判断，确定上述三个相关度中，任何一个相关度均大于该第一指定值，即第一工作音频与所有异常样本音频差异程度均较大，此时，确定扫地机器人不存在故障。
本实施例提供的方法，提供了一种计算工作音频与样本音频之间的相关度的方法，通过该方法，可较准确的计算得到工作音频与样本音频时间的相关度，进而根据相关度进行故障诊断。
可选地，在本申请另一可能的实现方式中，步骤S102，可以包括：
计算第一工作音频与第一样本音频之间的能量误差，并将上述能量误差作为上述第一工作音频与上述第一样本音频之间的相关度；其中，上述工作音频与上述样本音频之间的相关度表征上述工作音频与上述样本音频之间的差异程度。
具体的，能量误差按照如下公式计算获得：
D＝SUM(X(t)-c*A(t)^2)
其中，D为第一工作音频与第一样本音频之间的能量误差；X(t)为第一工作音频，采样窗口为t；A(t)为第一样本音频，采样窗口为t；c为常数。
需要说明的是，本实施例计算得到的相关度，表征第一工作音频与第一样本音频之间的差异程度。进一步地，可基于该相关度进行故障诊断。有关故障诊断的具体实现原理和实现过程将在下面的实施例中详细介绍，此处不再赘述。
本实施例提供的方法，提供了另一种计算工作音频与样本音频之间的相关度的方法，通过该方法，可较准确的计算得到工作音频与样本音频时间的相关度，进而根据相关度进行故障诊断。
图3为本申请提供的扫地机器人故障诊断方法实施例三的流程图。在上述实施例的基础上，请参照图3，本实施例提供的方法，第一样本音频包括扫地机器人正常工作时的音频，步骤S103，可以包括：
S301、当上述第一工作音频与上述第一样本音频之间的相关度小于第一指定值时，确定不存在故障。
S302、当上述第一工作音频与上述第一样本音频之间的相关度大于或者等于上述第一指定值时，确定存在故障。
本实施例提供的方法，当工作音频与样本音频之间的相关度为通过上述方法计算得到的相关度时，该相关度表征工作音频与样本音频之间的差异程度，即相关度越小，该工作音频与样本音频之间的差异程度越小，该工作音频与样本音频越相似。当第一工作音频与上述第一样本音频之间的相关度小于第一指定值时，说明第一工作音频与第一样本音频相似，而第一样本音频为扫地机器人正常工作时的音频，因此，此时，确定扫地机器人不存在故障。进一步地，当第一工作音频与第一样本音频之间的相关度大于或者等于上述第一指定值，说明第一工作音频与第一样本音频的差异程度较大，两者不相似，此时，确定存在故障。
具体的，第一指定值是根据实际需要设定的，本实施例中，不对第一指定值的具体值进行限定。例如，第一指定值可以为5、10等。下面以第一指定值为10为例进行说明。
例如，计算得到第一工作音频与第一样本音频之间的相关度为50，说明第一工作音频与第一样本音频差异程度较大，而第一样本音频为扫地机器人正常工作时的音频，因此，此时，确定扫地机器人存在故障。
再例如，计算得到第一工作音频与第一样本音频之间的相关度为3，此时，说明第一工作音频与第一样本音频差异程度较小，此时，确定扫地机器人不存在故障。
本实施例提供的方法，通过预先存储扫地机器人正常工作时的样本音频，进而在扫地机器人实际工作时，获取扫地机器人的工作音频，并将工作音频与样本音频进行比对，得到两者之间的相关度，且该相关度表征两者之间的差异程度。这样，在两者之间的相关度小于第一指定值时，确定扫地机器人不存在故障，而在两者之间的相关度大于或者等于上述第一指定值时，确定扫地机器人存在故障。这样，可诊断因异物缠绕导致的故障，适用性较好。
图4为本申请提供的扫地机器人故障诊断方法实施例四的流程图。本实施例提供的方法，当确定扫地机器人存在故障时，所述方法还可以包括：
S401、获取上述扫地机器人的指定部件工作时的第二工作音频。
具体的，指定部件包括以下至少一个部件：驱动轮、从动轮、边刷、滚刷和风机。下面以指定部件包括驱动轮和从动轮为例进行说明，本步骤S401中，可先仅启动驱动轮，获取驱动轮工作时的音频作为第二工作音频，进而再仅启动从动轮，获取从动轮工作时的音频作为第二工作音频。
S402、将上述第二工作音频与预先存储的上述指定部件的第二样本音频进行比对，得到上述第二工作音频与上述第二样本音频之间的相关度。
具体的，有关将第二工作音频与第二样本音频进行比对，得到第二工作音频与第二样本音频之间的相关度的具体实现过程和实现原理可以参见前面实施例中的描述，此处不再赘述。例如，可采用图2所示方法计算得到第二工作音频与第二样本音频之间的相关度。
S403、根据上述第二工作音频与上述第二样本音频之间的相关度，确定上述指定部件是否存在故障。
可选地，在本申请一可能的实现方式中，第二样本音频可以包括扫地机器人的上述指定部件正常工作时的正常样本音频，且第二工作音频与第二样本音频之间的相关度等于第二工作音频的能量值与第二样本音频的能量值的差值的绝对值，或者是第二工作音频与第二样本音频之间的能量误差。此时，第二工作音频与第二样本音频之间的相关度表征两者之间的差异程序。
此时，本步骤S403中，可在第二工作音频与第二样本音频之间的相关度小于第一指定值时，确定该指定部件不存在故障，在第二工作音频与第二样本音频之间的相关度大于或者等于上述第一指定值，确定该指定部件存在故障。需要说明的是，有关该实现方式的具体实现过程和实现原理可以参见实施例三中的描述，此处不再赘述。
进一步地，在本申请另一可能的实现方式中，预先存储的指定部件的第二样本音频可以包括上述指定部件正常工作时的正常样本音频和上述指定部件异常工作时的异常样本音频，且第二工作音频与第二样本音频之间的相关度等于第二工作音频的能量值与第二样本音频的能量值的差值的绝对值或者是第二工作音频与第二样本音频之间的能量误差时，本步骤的具体实现过程，可以包括：
(1)比较第一相关度和第二相关度；其中，上述第一相关度为上述第二工作音频与上述正常样本音频之间的相关度，上述第二相关度为上述第二工作音频数据与上述异常样本音频之间的相关度。
(2)当上述第一相关度大于或等于上述第二相关度时，确定上述指定部件存在故障；
(3)当上述第一相关度小于上述第二相关度时，确定上述指定部件不存在故障。
结合上面的例子，当指定部件包括驱动轮和从动轮时，例如，针对驱动轮，计算得到该驱动轮的工作音频与正常样本音频之间的相关度为10，该驱动轮的工作音频与异常 样本音频之间的相关度为50，此时，由于驱动轮的工作音频与正常样本音频之间的差异程度较小，确定驱动轮不存在故障。进一步，针对从动轮，计算得到该从动轮的工作音频与正常样本音频之间的相关度为30，该从动轮的工作音频与异常样本音频之间的相关度为5，此时，由于从动轮的工作音频与异常样本音频之间的差异程度较小，确定从动轮存在故障。
本实施例提供的方法，在确定扫地机器人存在故障时，通过获取扫地机器人的指定部件工作时的第二工作音频，进而将第二工作音频与预先存储的该指定部件的第二样本音频进行比对，得到第二工作音频与第二样本音频之间的相关度，从而可根据第二工作音频与第二样本音频之间的相关度，确定该指定部件是否存在故障。这样，在扫地机器人存在故障时，可进一步明确指定部件是否存在故障，明确发生故障的部件。
图5为本申请提供的扫地机器人故障诊断方法实施例五的流程图。请参照图5，本实施例提供的方法，可以包括：
S501、获取扫地机器人工作时的第一工作音频。
S502、将上述第一工作音频与预先存储的上述扫地机器人的第一样本音频进行比对，得到上述第一工作音频与上述第一样本音频之间的相关度。其中，上述第一工作音频与上述第一样本音频之间的相关度可等于上述第一工作音频的能量值与上述第一样本音频的能量值之间的差值的绝对值，或者是上述第一工作音频与上述第一样本音频之间的能量误差。上述第一样本音频包括扫地机器人正常工作时的音频。
S503、判断上述第一工作音频与上述第一样本音频之间的相关度是否小于第一指定值，若是，执行步骤S504，若否，执行步骤S505。
S504、确定上述扫地机器人不存在故障。
S505、确定上述扫地机器人存在故障，获取上述扫地机器人的指定部件工作时的第二工作音频。
S506、将上述第二工作音频与预先存储的上述指定部件的第二样本音频进行比对，得到上述第二工作音频与上述第二样本音频之间的相关度。其中，上述第二工作音频与上述第二样本音频之间的相关度可等于上述第二工作音频的能量值与上述第二样本音频的能量值之间的差值的绝对值，或者是上述第一工作音频与上述第一样本音频之间的能量误差。上述第二样本音频包括上述指定部件正常工作时的正常样本音频和上述指定部件异常工作时的异常样本音频。
S507、比较第一相关度和第二相关度。其中，上述第一相关度为上述第二工作音频与上述正常样本音频之间的相关度，上述第二相关度为上述第二工作音频数据与上述异常样本音频之间的相关度。
S508、当上述第一相关度大于或等于上述第二相关度时，确定上述指定部件存在故障。当上述第一相关度小于上述第二相关度时，确定上述指定部件不存在故障。
具体的，有关各步骤的具体实现过程和实现原理可以参见前面实施例中的描述，此处不再赘述。
本实施例提供的方法，不仅可判断扫地机器人是否存在故障，还能够在判断扫地机器人存在故障时，进一步确定指定部件是否存在故障，以明确故障发生的部位。
下面给出另一个具体的实施例，用以详细介绍本申请提供的扫地机器人故障诊断方法。
图6为本申请提供的扫地机器人故障诊断方法实施例六的流程图。请参照图6，本实施例提供的方法，可以包括：
S601、获取扫地机器人工作时的第一工作音频。
具体的，有关该步骤S601的具体实现过程和实现原理可以参见现有技术中的介绍，此处不再赘述。
S602、将上述第一工作音频与预先存储的上述扫地机器人的第一样本音频进行比对，得到上述第一工作音频与上述第一样本音频之间的相关度。其中，上述第一工作音频与上述第一样本音频之间的相关度可等于上述第一工作音频与上述第一样本音频的互相关系数。上述第一样本音频包括扫地机器人正常工作时的音频。
具体的，第一工作音频和第一样本音频之间的互相关系数采用如下公式计算得到：
Figure PCTCN2019082505-appb-000001
其中，c为第一工作音频和第一样本音频之间的互相关系数；x(t)为第一工作音频，采样窗口为t；A(t)为第一样本音频，采样窗口为t。
需要说明的是，本实施例提供的方法，工作音频与样本音频之间的相关度等于工作音频与样本音频之间的互相关系数，该相关度表征工作音频与样本音频之间的相似程度，即该相关度越大，工作音频与样本音频越相似。
S603、判断上述第一工作音频与上述第一样本音频之间的相关度是否大于或等于第二指定值，若是，执行步骤S604，若否，执行步骤S605。
S604、确定上述扫地机器人不存在故障。
具体的，当第一工作音频与上述第一样本音频之间的相关度大于或等于第二指定值，说明第一工作音频与第一样本音频较相似，而第一样本音频为扫地机器人正常工作时的音频，因此，此时，确定扫地机器人不存在故障。
S605、确定上述扫地机器人存在故障，获取上述扫地机器人的指定部件工作时的第二工作音频。
S606、将上述第二工作音频与预先存储的上述指定部件的第二样本音频进行比对，得到上述第二工作音频与上述第二样本音频之间的相关度。其中，上述第二工作音频与上述第二样本音频之间的相关度可等于上述第二工作音频与上述第二样本音频之间的互相关系数。上述第二样本音频包括上述指定部件正常工作时的正常样本音频和上述指定部件异常工作时的异常样本音频。
具体的，有关互相关系数的具体计算原理可以参见步骤S602中的介绍，此处不再赘述。
S607、比较第一相关度和第二相关度。其中，上述第一相关度为上述第二工作音频与上述正常样本音频之间的相关度，上述第二相关度为上述第二工作音频数据与上述异常样本音频之间的相关度。
S608、当上述第一相关度大于上述第二相关度时，确定上述指定部件不存在故障，当上述第一相关度小于或等于上述第二相关度时，确定上述指定部件存在故障。
具体的，互相关系数表征工作音频与样本音频之间的相似程度，互相关系数越大，表征该工作音频与样本音频越相似。因此，本例中，第二工作音频与正常样本音频之间的相关度大于第二工作音频数据与异常样本音频之间的相关度时，确定指定部件的状态为正常样本音频对应的状态，即确定指定部件不存在故障；相反，则确定指定部件存在故障。
本实施例提供的方法，不仅可确定扫地机器人是否存在故障，还能够在确定扫地机器人存在故障时，进一步确定故障发生的部位。
以上对本申请提供的方法进行了描述，下面对本申请提供的扫地机器人进行描 述：
图7为本申请一示例性实施例示出的扫地机器人的硬件结构图。请参照图7，本实施例提供的扫地机器人，可以包括：音频采集模块710、存储器720和处理器730。其中：所述音频采集模块710，用于获取扫地机器人工作时的第一工作音频；所述存储器720，用于存储所述扫地机器人的第一样本音频；所述处理器730，用于将所述第一工作音频与所述第一样本音频进行比对，得到所述第一工作音频与所述第一样本音频之间的相关度，并根据所述相关度确定所述扫地机器人是否存在故障。
本实施例提供的扫地机器人，可用于执行图1所示方法实施例的技术方案，其实现原理和技术效果类似，此处不再赘述。
进一步地，所述存储器720，还用于存储扫地机器人的指定部件的第二样本音频；在这种情况下，所述音频采集模块710，还用于在所述处理器730确定所述扫地机器人存在故障时，获取所述扫地机器人的指定部件工作时的第二工作音频；所述处理器730，还用于将所述第二工作音频与预先存储的所述指定部件的第二样本音频进行比对，得到所述第二工作音频与所述第二样本音频之间的相关度，并根据所述第二工作音频与所述第二样本音频之间的相关度确定所述指定部件是否存在故障。
进一步地，将工作音频与样本音频进行比对，得到工作音频与样本音频之间的相关度，包括：分别计算所述工作音频和所述样本音频的能量值；计算所述工作音频的能量值与所述样本音频的能量值之间的差值的绝对值，并将所述绝对值作为所述工作音频与所述样本音频之间的相关度。此时，所述工作音频与所述样本音频之间的相关度表征所述工作音频与所述样本音频之间的差异程度。
或者，将工作音频与样本音频进行比对，得到工作音频与样本音频之间的相关度，包括：计算所述工作音频与所述样本音频之间的能量误差，并将所述能量误差作为所述工作音频与所述样本音频之间的相关度。此时，所述工作音频与所述样本音频之间的相关度表征所述工作音频与所述样本音频之间的差异程度。
在这种情况下，样本音频包括扫地机器人正常工作时的音频；根据工作音频与样本音频之间的相关度，确定是否存在故障，包括：当所述工作音频与样本音频之间的相关度小于第一指定值时，确定不存在故障；当所述工作音频与样本音频之间的相关度大于或者等于所述第一指定值，确定存在故障。
此外，所述第二样本音频包括所述指定部件正常工作时的正常样本音频和所述 指定部件异常工作时的异常样本音频。所述根据所述第二工作音频数据与所述第二样本音频之间的相关度，确定所述指定部件是否发生故障，包括：比较第一相关度和第二相关度，其中，所述第一相关度为所述第二工作音频与所述正常样本音频之间的相关度，所述第二相关度为所述第二工作音频数据与所述异常样本音频之间的相关度；当所述第一相关度大于或等于所述第二相关度时，确定所述指定部件存在故障；当所述第一相关度小于所述第二相关度时，确定所述指定部件不存在故障。
进一步地，将工作音频与样本音频进行比对，得到工作音频与样本音频之间的相关度，包括：计算所述工作音频与所述样本音频的互相关系数，并将所述互相关系数作为所述工作音频与所述样本音频之间的相关度。此时，所述工作音频与所述样本音频之间的相关度表征所述工作音频与所述样本音频之间的相似程度。
在这种情况下，样本音频包括扫地机器人正常工作时的音频；根据工作音频与样本音频之间的相关度，确定是否存在故障，包括：当所述工作音频与样本音频之间的相关度大于或等于第二指定值时，确定不存在故障；当所述工作音频与样本音频之间的相关度小于所述第二指定值，确定存在故障。
此外，所述第二样本音频包括所述指定部件正常工作时的正常样本音频和所述指定部件异常工作时的异常样本音频；所述根据所述第二工作音频数据与所述第二样本音频之间的相关度，确定所述指定部件是否发生故障，包括：比较第一相关度和第二相关度；其中，所述第一相关度为所述第二工作音频与所述正常样本音频之间的相关度，所述第二相关度为所述第二工作音频数据与所述异常样本音频之间的相关度；当所述第一相关度大于所述第二相关度时，确定所述指定部件不存在故障；当所述第一相关度小于或等于所述第二相关度时，确定所述指定部件存在故障。
本申请还提供一种计算机存储介质，其上存储有计算机程序，所述程序被处理器执行时本申请提供的任一扫地机器人故障诊断方法的步骤。
具体的，适合于存储计算机程序指令和数据的计算机可读介质包括所有形式的非易失性存储器、媒介和存储器设备，例如包括半导体存储器设备(例如EPROM、EEPROM和闪存设备)、磁盘(例如内部硬盘或可移动盘)、磁光盘以及CD ROM和DVD-ROM盘。
以上所述仅为本申请的较佳实施例而已，并不用以限制本申请，凡在本申请的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本申请保护的范围 之内。

Claims (11)

  1. 一种扫地机器人故障诊断方法，包括：
    获取扫地机器人工作时的第一工作音频；
    将所述第一工作音频与预先存储的所述扫地机器人的第一样本音频进行比对，得到所述第一工作音频与所述第一样本音频之间的相关度；
    根据所述相关度，确定所述扫地机器人是否存在故障。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在确定所述扫地机器人存在故障时，获取所述扫地机器人的指定部件工作时的第二工作音频；
    将所述第二工作音频与预先存储的所述指定部件的第二样本音频进行比对，得到所述第二工作音频与所述第二样本音频之间的相关度；
    根据所述第二工作音频与所述第二样本音频之间的相关度，确定所述指定部件是否存在故障。
  3. 根据权利要求1或2所述的方法，其特征在于，将工作音频与样本音频进行比对，得到工作音频与样本音频之间的相关度，包括：
    分别计算所述工作音频和所述样本音频的能量值；
    计算所述工作音频的能量值与所述样本音频的能量值的差值的绝对值，并将所述绝对值作为所述工作音频与所述样本音频之间的相关度。
  4. 根据权利要求1或2所述的方法，其特征在于，将工作音频与样本音频进行比对，得到工作音频与样本音频之间的相关度，包括：
    计算所述工作音频与所述样本音频之间的能量误差，并将所述能量误差作为所述工作音频与所述样本音频之间的相关度。
  5. 根据权利要求3或4所述的方法，其特征在于，样本音频包括扫地机器人正常工作时的音频；根据工作音频与样本音频之间的相关度，确定是否存在故障，包括：
    当所述工作音频与所述样本音频之间的相关度小于第一指定值时，确定不存在故障；
    当所述工作音频与所述样本音频之间的相关度大于或者等于所述第一指定值时，确定存在故障。
  6. 根据权利要求3或4所述的方法，其特征在于，所述第二样本音频包括所述指定部件正常工作时的正常样本音频和所述指定部件异常工作时的异常样本音频；根据所述第二工作音频数据与所述第二样本音频之间的相关度，确定所述指定部件是否发生故障，包括：
    比较第一相关度和第二相关度；其中，所述第一相关度为所述第二工作音频与所述正常样本音频之间的相关度，所述第二相关度为所述第二工作音频数据与所述异常样本音频之间的相关度；
    当所述第一相关度大于或等于所述第二相关度时，确定所述指定部件存在故障；
    当所述第一相关度小于所述第二相关度时，确定所述指定部件不存在故障。
  7. 根据权利要求1或2所述的方法，其特征在于，将工作音频与样本音频进行比对，得到工作音频与样本音频之间的相关度，包括：
    计算所述工作音频与所述样本音频的互相关系数，并
    将所述互相关系数作为所述工作音频与所述样本音频之间的相关度。
  8. 根据权利要求7所述的方法，其特征在于，样本音频包括扫地机器人正常工作时的音频；根据工作音频与样本音频之间的相关度，确定是否存在故障，包括：
    当所述工作音频与所述样本音频之间的相关度大于或等于第二指定值时，确定不存在故障；
    当所述工作音频与所述样本音频之间的相关度小于所述第二指定值时，确定存在故障。
  9. 根据权利要求7所述的方法，其特征在于，所述第二样本音频包括所述指定部件正常工作时的正常样本音频和所述指定部件异常工作时的异常样本音频；根据所述第二工作音频数据与所述第二样本音频之间的相关度，确定所述指定部件是否发生故障，包括：
    比较第一相关度和第二相关度；其中，所述第一相关度为所述第二工作音频与所述正常样本音频之间的相关度，所述第二相关度为所述第二工作音频数据与所述异常样本音频之间的相关度；
    当所述第一相关度大于所述第二相关度时，确定所述指定部件不存在故障；
    当所述第一相关度小于或等于所述第二相关度时，确定所述指定部件存在故障。
  10. 一种扫地机器人，其特征在于，包括：
    音频采集模块，用于获取扫地机器人工作时的第一工作音频；
    存储器，用于存储所述扫地机器人的第一样本音频；
    处理器，用于将所述第一工作音频与所述第一样本音频进行比对，得到所述第一工作音频与所述第一样本音频之间的相关度，并根据所述相关度确定所述扫地机器人是否存在故障。
  11. 一种计算机存储介质，其上存储有计算机程序，其特征在于，所述程序被处理器执行时实现权利要求1-9任一项所述方法。
PCT/CN2019/082505 2018-06-29 2019-04-12 扫地机器人故障诊断 WO2020001130A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810713351.5 2018-06-29
CN201810713351.5A CN110658006B (zh) 2018-06-29 2018-06-29 一种扫地机器人故障诊断方法和扫地机器人

Publications (1)

Publication Number Publication Date
WO2020001130A1 true WO2020001130A1 (zh) 2020-01-02

Family

ID=68986019

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/082505 WO2020001130A1 (zh) 2018-06-29 2019-04-12 扫地机器人故障诊断

Country Status (2)

Country Link
CN (1) CN110658006B (zh)
WO (1) WO2020001130A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114290312A (zh) * 2021-12-02 2022-04-08 上海擎朗智能科技有限公司 机器人车轮检测方法、装置及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003061882A (ja) * 2001-08-28 2003-03-04 Matsushita Electric Ind Co Ltd 自走式掃除機
JP2004159735A (ja) * 2002-11-11 2004-06-10 Matsushita Electric Ind Co Ltd 移動作業ロボット
CN2693167Y (zh) * 2003-03-14 2005-04-20 高超明智公司 具有颗粒探测器的自动真空吸尘器
CN103054516A (zh) * 2011-10-21 2013-04-24 三星电子株式会社 机器人吸尘器以及用于机器人吸尘器的控制方法
CN103479313A (zh) * 2012-06-11 2014-01-01 海尔集团公司 一种用于洗碗机的语音提醒***

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS55138634A (en) * 1979-04-16 1980-10-29 Kansai Electric Power Co Inc:The Fault diagnosis apparatus of apparatus
JP2006113002A (ja) * 2004-10-18 2006-04-27 Nsk Ltd 機械設備の異常診断システム
JP4573036B2 (ja) * 2005-03-16 2010-11-04 オムロン株式会社 検査装置および検査方法
CN100523746C (zh) * 2006-05-09 2009-08-05 欧姆龙株式会社 检查装置及检查方法
CN101067930B (zh) * 2007-06-07 2011-06-29 深圳先进技术研究院 一种智能音频辨识***及辨识方法
US20120330499A1 (en) * 2011-06-23 2012-12-27 United Technologies Corporation Acoustic diagnostic of fielded turbine engines
CN202735105U (zh) * 2012-07-03 2013-02-13 上海电机学院 一种故障检测装置
CN104049037A (zh) * 2013-03-15 2014-09-17 东莞富强电子有限公司 故障预警***
CN103245524A (zh) * 2013-05-24 2013-08-14 南京大学 基于神经网络的声学故障诊断方法
US9244042B2 (en) * 2013-07-31 2016-01-26 General Electric Company Vibration condition monitoring system and methods
CN103810374B (zh) * 2013-12-09 2017-04-05 中国矿业大学 一种基于mfcc特征提取的机器故障预测方法
JP2017026509A (ja) * 2015-07-24 2017-02-02 三菱電機株式会社 故障診断装置および故障診断方法
KR20170044386A (ko) * 2015-10-15 2017-04-25 삼성전자주식회사 전자기기 및 전자기기의 제어방법
US10345800B2 (en) * 2016-03-30 2019-07-09 3D Signals Ltd. Acoustic monitoring of machinery

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003061882A (ja) * 2001-08-28 2003-03-04 Matsushita Electric Ind Co Ltd 自走式掃除機
JP2004159735A (ja) * 2002-11-11 2004-06-10 Matsushita Electric Ind Co Ltd 移動作業ロボット
CN2693167Y (zh) * 2003-03-14 2005-04-20 高超明智公司 具有颗粒探测器的自动真空吸尘器
CN103054516A (zh) * 2011-10-21 2013-04-24 三星电子株式会社 机器人吸尘器以及用于机器人吸尘器的控制方法
CN103479313A (zh) * 2012-06-11 2014-01-01 海尔集团公司 一种用于洗碗机的语音提醒***

Also Published As

Publication number Publication date
CN110658006A (zh) 2020-01-07
CN110658006B (zh) 2021-03-23

Similar Documents

Publication Publication Date Title
JP7085370B2 (ja) 診断装置、診断システム、診断方法およびプログラム
US11467024B2 (en) Diagnostic device, computer program, and diagnostic system
JP7338743B2 (ja) 診断装置、診断方法、プログラムおよび診断システム
WO2021043287A1 (zh) 地毯检测方法、装置、扫地机器人和计算机存储介质
US8607093B2 (en) Systems and methods for detecting machine faults in network using acoustic monitoring
US8914341B2 (en) Method and apparatus for continuous compliance assessment
JP4876136B2 (ja) 異常診断装置および異常診断方法
WO2020001130A1 (zh) 扫地机器人故障诊断
JP7067971B2 (ja) 処理区間判定装置、処理区間判定方法、プログラム、および診断装置
CN113892857B (zh) 清洁机器人清洁控制方法、装置、计算机设备和介质
Zhao et al. Failure prediction in datacenters using unsupervised multimodal anomaly detection
WO2021245796A1 (ja) 清掃システム及びプログラム
US20210003637A1 (en) Motor information acquisition system
WO2020052154A1 (zh) 清洁监控方法、装置及吸尘器和移动终端
CN111938508B (zh) 地刷类型识别方法、吸尘设备及存储介质
WO2023124009A1 (zh) 一种清洁机器人的状态判断方法及装置
CN105136394B (zh) 快速处理锅炉风机振动故障的方法及装置
JP6966338B2 (ja) 診断装置、診断方法及び診断プログラム
JP5252563B2 (ja) 電子機器、および電子機器における機構部品の診断方法、ならびに診断プログラム
TWI526676B (zh) 機台振動訊號過濾方法、裝置及電腦可讀取記錄媒體
US8208657B2 (en) Signal processing device, signal processing method, and program
CN114098544B (zh) 工作头的控制方法和工作设备
JP2020008932A (ja) 画像処理装置、画像処理方法及びプログラム
TWI746127B (zh) 寵物照護系統及其方法
JP2006244590A (ja) 磁気テープ、磁気テープ装置の自己診断装置、磁気テープ装置の診断方法、および、磁気テープ装置の診断プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19826184

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19826184

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19826184

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 02.07.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19826184

Country of ref document: EP

Kind code of ref document: A1