WO2022036710A1

WO2022036710A1 - Method of indication selection for a fault diagnosis of a gearbox

Info

Publication number: WO2022036710A1
Application number: PCT/CN2020/110594
Authority: WO
Inventors: Zhanchi LIU; Heqing SUN
Original assignee: Abb Schweiz Ag
Priority date: 2020-08-21
Filing date: 2020-08-21
Publication date: 2022-02-24

Abstract

A method, an electronic device and computer readable storage medium for fault diagnosis. The method comprises: determining, from a signal associated with a motion of a component of a gearbox (110), a plurality of indications of motion characteristics of the component; determining variations between the plurality of indications and a plurality of sets of historical indications of the plurality of indications, each set of historical indications indicating the motion characteristics of the component; selecting indications from the plurality of indications such that the variations of the selected indications are larger than the variations of the indications other than the selected indications; and detecting a fault that occurred in the gearbox (110) based on the selected indications. There is provided a method for fault diagnosis that can be implemented easily and reliably.

Description

METHOD OF INDICATION SELECTION FOR A FAULT DIAGNOSIS OF A GEARBOX

FIELD

Embodiments of the present disclosure generally relate to fault diagnosis for a gearbox.

BACKGROUND

A variety of industrial applications comprise gearboxes. In many cases, an eventual failure of the gearbox is the result of continued cycling of a component in which defects have already occurred. Such defects may include cracks or other deformations of the component in the gearbox. Because the failure of the gearbox may lead to expensive repairs and down time, it is important to monitor the status of the gearbox before failures occur. A fault diagnosis device has been proposed to diagnose faults of the gearbox.

Such a fault diagnosis device may obtain information about motion characteristics of the gearbox and can monitor the gearbox based on the obtained information. For a complex gearbox, such as a planetary gearbox, the amount of the information is very large and the key information may be overlooked, making the fault diagnosis device incapable of performing an accurate diagnosis. Therefore, there is a need for an improved approach for the fault diagnosis of the gearbox. In particular, there is a need for a method for fault diagnosis that can be implemented easily and reliably.

SUMMARY

According to implementations of the subject matter described herein, there is provided an improved fault diagnosis method and associated electronic device.

In a first aspect, there is provided a method for fault diagnosis. The method comprises: determining, from a signal associated with a motion of a component of a gearbox, a plurality of indications of motion characteristics of the component; determining variations between the plurality of indications and a plurality of sets of historical indications of the plurality of indications, each set of historical indications indicating the motion characteristics of the component; selecting indications from the plurality of indications such that the variations of the selected indications are larger than the variations of the indications other than the selected indications; and detecting a fault that occurred in the gearbox based on the selected indications.

In a second aspect, there is provided an electronic device. The electronic device comprises: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions executable by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the acts of the method in the first aspect described above.

In a third aspect, there is provided a computer readable storage medium. The computer readable storage medium has computer readable program instructions stored thereon which, when executed by a processing unit, cause the processing unit to perform the acts of the method in the first aspect described above.

The Summary introduces a selection of concepts in a simplified form that are further described below in the Detailed Description. The Summary is not intended to identify key features or essential features of the subject matter described herein, nor is it intended to be used to limit the scope of the subject matter described herein.

BRIEF DESCRIPTION OF THE DRAWINGS

Through the more detailed description of some embodiments of the present disclosure in the accompanying drawings, the above and other objects, features and advantages of the present disclosure will become more apparent, wherein:

Fig. 1 illustrates an example environment in which embodiments of the present disclosure may be implemented;

Fig. 2 illustrates a flowchart of an example process for the fault diagnosis device according to some embodiments of the present disclosure;

Fig. 3 illustrates a flowchart of an example process for the fault diagnosis device according to some embodiments of the present disclosure; and

Fig. 4 illustrates a block diagram of an example computing system/device suitable for implementing example embodiments of the present disclosure.

Throughout the drawings, the same or similar reference symbols refer to the same or similar elements.

DETAILED DESCRIPTION OF IMPLEMENTATIONS

Principles of the subject matter described herein will now be described with reference to some example implementations. It should be understood that these implementations are described only for the purpose of illustration and to help those skilled in the art to better understand and thus implement the subject matter described herein, without suggesting any limitations to the scope of the subject matter disclosed herein.

As used herein, the term “based on” is to be read as “based at least in part on. ” The terms “an implementation” and “one implementation” are to be read as “at least one implementation. ” The term “another implementation” is to be read as “at least one other implementation. ” The term “first, ” “second, ” and the like may refer to different or the same objects. Other definitions, either explicit or implicit, may be included below.

It should be further understood that the terms “comprises” , “comprising” , “has” , “having” , “includes” and/or “including” , when used herein, specify the presence of stated features, elements, and/or components, etc., but do not preclude the presence or addition of one or more other features, elements, components and/or combinations thereof.

Fault diagnosis devices are usually used to perform a fault diagnosis of a gearbox. Such fault diagnosis devices obtain information about motion characteristics of the gearbox and monitor the gearbox based on the obtained information. As the information associated with the gearbox is usually very large, leading the fault diagnosis devices incapable of performing a diagnosis efficiently.

A plurality of indications associated with motion characteristics of a component of the gearbox may be extracted from the information and then used to perform the diagnosis. However, the amount of the indications for one component of a gearbox would be in the hundreds, especially for a planetary gearbox. Hundreds of indications would make some key indications obscured and overlooked, and thereby these indications cannot characterize the component properly, leading to an inaccurate fault diagnosis of the gearbox.

In order to at least solve the above problem and other potential problems, embodiments of the present disclosure provide an improved method for the fault diagnosis that is applicable to perform the fault diagnosis reliably and robustly.

Fig. 1 illustrates an environment 100 in which embodiments of the subject matter described herein may be employed. The environment 100 is illustrated as a fault diagnosis environment comprising a gearbox 110 and a fault diagnosis device 120.

The gearbox 110 comprises a plurality of gears arranged within the housing of the gearbox 110. As shown, the gearbox 110 is a planetary gearbox comprising planetary gears 102-1, 102-2, 102-3, a sun gear member 104, and a ring gear member 103. The planetary gears 102-1, 102-2, 102-3 may be arranged on a planetary carrier assembly.

In some embodiments, the sun gear member 104 may be coupled to an input shaft of the gearbox 110 and the planetary carrier assembly may be coupled to the output shaft of the gearbox 110. It should be understood that the gearbox 110 may be implemented in other forms, such as a parallel-shaft gearbox, a worm gearbox, a bevel gearbox, or a planetary gearbox comprising different numbers of planetary gears.

The fault diagnosis device 120 is provided to monitor the gearbox 110. The fault diagnosis device 120 may be a general-purpose computer, a physical computing device, or a portable electronic device, or may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communication network.

The fault diagnosis device 120 may obtain a signal 112 associated with a motion of the gearbox 110. The fault diagnosis device 120 may detect whether a fault has occurred in the gearbox 110 based on the signal 112. The output of the fault diagnosis device 120, i.e., a diagnosis result 122, indicates whether a fault has occurred in the gearbox 110.

According to embodiments of the present disclosure, the fault diagnosis device 120 can monitor the gearbox 110 based on a plurality of indications extracted from the signal 112. Reference is made to Fig. 2, which illustrates a flowchart of an example process 200 for the fault diagnosis device 120 according to some embodiments of the present disclosure.

At block 202, the fault diagnosis device 120 determines a plurality of indications of motion characteristics of a component from the signal 112. The signal 112 is associated with a motion of a component (such as the planetary gear 102-1) of the gearbox 110.

In some embodiments, the signal 112 may comprise one or more of the following: a vibration signal of the gearbox 110, a torque signal associated with torque of the output shaft of the gearbox 110, a current signal associated with the speed of the input shaft of the gearbox 110. In some embodiments, at least one of the following sensors may be coupled to the gearbox 110: an accelerometer which measures vibration waveforms of the gearbox 110, a current sensor that measures the current waveforms inputted to a motor that drives the input shaft of the gearbox 110, or a torque sensor which measures the torque waveforms of the output shaft.

In some embodiments, the plurality of indications are determined based on one or more of the following: a magnitude of a frequency in a spectrum of the signal 112 where the frequency is associated with the motion of the component (such as the planetary gear 102-1) , signal-to-noise ratios or magnitudes of sidebands of the frequency, or a Root Mean Square or a Kurtosis of a pattern in time-domain of the signal 112. As an example, the frequencies related to the motion of the component comprise a gear mesh frequency of the component.

In some embodiments, the plurality of indications may comprise one or more of the following: the magnitude of the frequency in the spectrum of the signal 112, signal-to-noise ratios or magnitudes of sidebands of the frequency, or the Root Mean Square or the Kurtosis of the pattern in time-domain of the signal 112. Alternatively, or in addition, the plurality of indications may comprise an integrated indication which is obtained by combining or processing the plurality of indications extracted from the signal 112. For example, a sum of magnitudes of a plurality of the frequencies may be calculated, and the sum of the magnitudes may be normalized to obtain the integrated indication. As another example, a sum of the signal-to-noise ratios of sidebands of the frequency may be obtained, and the sum of the signal-to-noise ratios may be divided by the frequency to obtain the integrated indication. It should be understood that other combination of the indications listed above would be applicable as well.

The scope of the embodiments of the present disclosure is not limited in this regard, and any other indications and any combination thereof that may give an accurate representation for the status of the component may be applicable as well.

It should be understood that any other suitable technique may be used to extract indications from the signal 112 and/or process the extracted indications. For example, the fault diagnosis device 120 may utilize a mechanism model and a signal model to extract indications from the signal 112 of the gearbox 110. The mechanism model, which uses expertise to analyze the gearbox, is a model created based on the internal mechanism of the gearbox. The fault diagnosis device 120 may utilize the mechanism model to perform a physic analysis of the gearbox 110. For example, the fault diagnosis device 120 may utilize the mechanism model to analyze the signal 112 of the gearbox 110 such that frequencies associated with the motion of a specific component can be predicted.

The fault diagnosis device 120 may utilize the signal model to extract indications from the signal 112 based on the physic analysis of the gearbox 110. For example, the fault diagnosis device 120 may utilize the signal model to calculate spectrum of the signal, and/or calculate frequencies related to the motion of the component based on the physic analysis of the gearbox 110, and/or extract amplitudes of the calculated frequencies. Alternatively, or in addition, the fault diagnosis device 120 may utilize the signal model to calculate signal-to-noise ratios or magnitudes of sidebands of the frequencies, and/or a Root Mean Square or a Kurtosis of a pattern in time-domain of the signal 112, and/or calculate the integrated indication as discussed above.

For ease of description, the component of the gearbox 110 may be referred to as the planetary gear 102-1 hereinafter. It should be understood that the component of the gearbox 110 may refer to any other component of the gearbox 110, such as the planetary gears 102-2, 102-3, the sun gear member 104, or the ring gear member 103.

At block 204, the fault diagnosis device 120 determines variations between the plurality of indications and a plurality of sets of historical indications of the plurality of indications. Each set of historical indications indicates the motion characteristics of the planetary gear 102-1. In some embodiments, each one of the plurality of indications corresponds to one set of historical indications. In some embodiments, the fault diagnosis device 120 may determine the variations based on an expectation value of each set of historical indications. For a given indication of the plurality of indications, the fault diagnosis device 120 determines the expectation value of the set of historical indications corresponding to the given indication.

The fault diagnosis device 120 may further calculate a difference between a value of the given indication and the expectation value. As such, the fault diagnosis device 120 can determine the variation of the given indication to be the calculated difference. In the same way, the fault diagnosis device 120 may determine the variation of each indication of the plurality of indications.

In order to determine the expectation value, in some embodiments, the fault diagnosis device 120 may determine a distribution pattern of the set of historical indications corresponding to the given indication. Then, the expectation value of the set of historical indications corresponding to the given indication can be calculated based on the distribution pattern. For example, the distribution pattern may be a Weibull distribution or a Gaussian distribution.

In some embodiments, the fault diagnosis device 120 may determine the variations of the plurality of indications further based on a standard deviation of the distribution pattern. For example, the fault diagnosis device 120 may determine the standard deviation of the distribution pattern of the set of historical indications. As such, for the given indication, the fault diagnosis device 120 may determine the variation of the given indication based on the value of the given indication, the expectation value and the standard deviation of the distribution pattern, such as by the equation,

In other embodiments, for each indication, the fault diagnosis device 120 may determine a variation between the indication and the set of historical indications in other way. For example, for each indication determined from the signal 112, the fault diagnosis device 120 may first create a dataset which comprises the indication and the corresponding set of historical indications, and then the fault diagnosis device 120 may determine the standard deviation of the dataset. As such, the fault diagnosis device 120 may determine the standard deviation of the dataset as the variation of the indication.

Regarding the integrated indication, a plurality of historical indications corresponding to the integrated indication may be determined in the same way as the integrated indication is generated. As an example, a sum of historical magnitudes of a plurality of the frequencies may be calculated, and then the sum of the historical magnitudes may be normalized to obtain one historical indication of the plurality of historical indications. In the same way, each one of the plurality of historical indications of the integrated indication can be generated. Accordingly, the variation of the integrated indication can be determined in the manner discussed above.

It should be understand that other suitable technology can be used to determine the variation between the indication and the corresponding set of historical indications.

At block 206, the fault diagnosis device 120 selects indications from the plurality of indications. The variations of the selected indications are larger than the variations of the indications other than the selected indications. As a principle used herein, the selected indications having larger variations can be used to monitor the status of the component accurately.

In some embodiments, the fault diagnosis device 120 may sort the plurality of indications based on the numerical value of the variations thereof. A predetermined number of indications having larger variations may be selected accordingly. That is, the variations of the predetermined number of selected indications are larger than the variations of the indications other than the selected indications. It should be understood that the predetermined number may be a constant number or a variable number that can be determined based on the total number of the plurality of indications.

At block 208, the fault diagnosis device 120 detects a fault that occurred in the gearbox 110 based on the selected indications.

In some embodiments, the fault diagnosis device 120 may detect a fault that occurred in the gearbox 110 based on a fault diagnosis model. As used herein, a “fault diagnosis model” is a machine learning model, which may also be referred to as a “learning model” , “learning network” , “network model” , or “model. ” A deep learning model is one example of a machine learning model, examples of which include a “neural network. ” The fault diagnosis model is learned from historical indications of a component and associated labeling information indicating the status of the component of the gearbox (i.e., healthy or faulty) . A machine learning model represents an association between the input data and output results. As such, information can be learned from the historical indications of the component to implement a highly automated diagnosis of the input data.

As such, the fault diagnosis device 120 may utilize the selected indications as the input data of the fault diagnosis model. The fault diagnosis device 120 may detect whether a fault has occurred in the gearbox 110 based on the fault diagnosis model.

In some embodiments, the fault diagnosis device 120 may detect whether a fault has occurred in the planetary gear 102-1 based on a sum s of the selected indications and a confidence interval associated with the selected indications. Fig. 3 illustrates a flowchart of an example process 300 for the fault diagnosis device according to some embodiments of the present disclosure.

At block 302, the fault diagnosis device 120 determines a sum s of the selected indications.

At block 304, the fault diagnosis device determines a healthy range for the planetary gear 102-1. The healthy range of the planetary gear 102-1 indicates that the planetary gear 102-1 is healthy. In some embodiments, for example, for the selected indications [t ₁, t ₂, t ₃ … n] , each one of the selected indication corresponding to a set of historical indications as shown in the Table 1 below:

Table 1: an example of the selected indication and the corresponding historical indications.

Selected Indications	Corresponding Historical Indications
t ₁	[t ₁₁, t ₁₂, t ₁₃, … t _1x]
t ₂	[t ₂₁, t ₂₂, t ₂₃, … t _2x]
…	…
t _n	[t _n1, t _n2, t _n3, … t _nx]

Note that in Table 1, the number of the historical indications for each one of the selected indications may be the same or different.

Thus, the sum s of the selected indications may be determined by the equation of: s=t ₁+t ₂+…+t _n. Moreover, the fault diagnosis device 120 may determine a first sum s ₁=t ₁₁+t ₂₁+…+t _n1, a second sum s ₂=t ₁₂+t ₂₂+…+t _n2, …, and a x ^st sum s _x=t _1x+t _2x+…+t _nx. The fault diagnosis device 120 then may determine a distribution pattern k of the first sum s ₁, the second sum s ₂, …, the x ^st sum s _x. Thus, an expectation value μ and a standard deviation σ of the distribution pattern k can be determined, while the healthy range may be determined as [0, μ+3σ] .

In other embodiments, the fault diagnosis device 120 may determine a weighted sum s′ of the selected indications. For example, the fault diagnosis device 120 may apply a weight factor to each one of the selected indications, respectively, and then sum the weighted selected indications by the equation of: s′ =w ₁*t ₁+w ₂*t ₂+…+w _n*t _n. Likewise, the fault diagnosis device 120 may apply a corresponding weight factor to the historical indications corresponding to the selected indications, as shown in Table 2 below.

Table 2: an example of the weighted selected indication and the corresponding weighted historical indications.

Weighted Selected Indications	Weighted Historical Indications
w ₁*t ₁	w ₁* [t ₁₁, t ₁₂, t ₁₃, … t _1x]
w ₂*t ₂	w ₂* [t ₂₁, t ₂₂, t ₂₃, … t _2x]
…	…
w _n*t _n	w _n* [t _n1, t _n2, t _n3, … t _nx]

Note that in Table 2, the number of the historical indications for each one of the selected indications may be the same or different.

Thus, the fault diagnosis device 120 may determine a first sum s′ ₁=w ₁*t ₁₁+w ₂*t ₂₁+…+w _n*t _n1, a second sum s′ ₂=w ₁*t ₁₂+w ₂*t ₂₂+…+w _n*t _n2, …, and a x ^st sum s′ _x=w ₁*t _1x+w ₂*t _2x+…+w _n*t _nx. The fault diagnosis device 120 then may determine a distribution pattern k′ of the first sum s′ ₁, the second sum s′ ₂, …, and the x ^st sum s′ _x. Thus, an expectation value μ′, a deviation σ′ of the distribution pattern k′ can be determined, while the healthy range may be determined as [0, μ′+3σ′] .

At block 306, if the sum s the selected indications is out of the healthy range [0, μ+3σ] , or if the sum s′ of the selected indications is out of the healthy range [0, μ′+ 3σ′] , the fault diagnosis device 120 determines that a fault has occurred in the planetary gear 102-1 and thus a fault has occurred in the gearbox 110. Otherwise, the fault diagnosis device 120 may determine that the planetary gear 102-1 is healthy and thus the gearbox 110 is healthy.

In other embodiments, the fault diagnosis device 120 may detect whether a fault has occurred in the planetary gear 102-1 based on a probability density function which is calculated based on the plurality of sets of historical indications of the selected indications. The probability density function can be calculated by means of statistical method. As such, a confidence interval of the probability density function under a certain confidence level can be determined. The certain confidence level may be set as 85%or 95%or other suitable level. Furthermore, a probability value of the selected indications can be determined by inputting the selected indications into the probability density function. Thus, if the probability value of the selected indications is present within the confidence interval, the fault diagnosis device 120 may detect that no fault has occurred in the planetary gear 102-1. If the probability value of the selected indications is out of the confidence interval, the fault diagnosis device 120 may detect that a fault has occurred in the planetary gear 102-1.

It should be understand that other suitable technology can be used to determine whether a fault has occurred in the planetary gear 102-1.

In order to expand the amount of the set of the historical indications, in some embodiments, the fault diagnosis device 120 may further store the determined plurality of indications into a database as a new set of historical indications of the planetary gear 102-1.

In some embodiments, the fault diagnosis device may be created for each component of the gearbox 110. For example, a corresponding fault diagnosis device may be created for each of the ring gear member 103, the planetary gears 102-1, 102-2, 102-3, and the sun gear member 104. Thus, the fault diagnosis result for the gearbox 110 may be determined based on the diagnosis results of the components of the gearbox 110.

Fig. 4 illustrates a block diagram of an example computing system/device 400 suitable for implementing example embodiments of the present disclosure. The system/device 400 can be implemented as or implemented in the fault diagnosis device 120 of Fig. 1. The system/device 400 may be a general-purpose computer, a physical computing device, or a portable electronic device, or may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communication network. The system/device 400 can be used to implement the process 200 of Fig. 2 and/or the process 300 of Fig. 3.

As depicted, the system/device 400 includes a processor 401 which is capable of performing various processes according to a program stored in a read only memory (ROM) 402 or a program loaded from a storage unit 408 to a random access memory (RAM) 403. In the RAM 403, data required when the PROCESSOR 401 performs the various processes or the like is also stored as required. The PROCESSOR 401, the ROM 402 and the RAM 403 are connected to one another via a bus 404. An input/output (I/O) interface 405 is also connected to the bus 404.

The processor 401 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) , graphic processing unit (GPU) , co-processors, and processors based on multicore processor architecture, as non-limiting examples. The system/device 400 may have multiple processors, such as an application-specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

A plurality of components in the system/device 400 are connected to the I/O interface 405, including an input unit 406, such as a keyboard, a mouse, or the like; an output unit 407 including a display such as a cathode ray tube (CRT) , a liquid crystal display (LCD) , or the like, and a loudspeaker or the like; the storage unit 408, such as a disk and optical disk, and the like; and a communication unit 409, such as a network card, a modem, a wireless transceiver, or the like. The communication unit 409 allows the system/device 400 to exchange information/data with other devices via a communication network, such as the Internet, various telecommunication networks, and/or the like.

The methods and processes described above, such as the process 200 and/or process 300, can also be performed by the processor 401. In some embodiments, the process 200 and/or process 300 can be implemented as a computer software program or a computer program product tangibly included in the computer readable medium, e.g., storage unit 408. In some embodiments, the computer program can be partially or fully loaded and/or embodied in the system/device 400 via ROM 402 and/or communication unit 409. The computer program includes computer executable instructions that are executed by the associated processor 401. When the computer program is loaded to RAM 403 and executed by the PROCESSOR 401, one or more acts of the process 200 and/or process 300 described above can be implemented. Alternatively, PROCESSOR 401 can be configured via any other suitable manner (e.g., by means of firmware) to execute the process 200 and/or process 300 in other embodiments.

Generally, various example embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of the example embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it will be appreciated that the blocks, apparatuses, systems, techniques, or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

The present disclosure also provides a computer readable storage medium having computer readable program instructions stored thereon which, when executed by a processing unit, cause the processing unit to perform the methods/processes as described above. A computer readable storage medium may include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM) , a read-only memory (ROM) , an erasable programmable read-only memory (EPROM or Flash memory) , an optical fiber, a portable compact disc read-only memory (CD-ROM) , an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Computer readable program instructions for carrying out methods disclosed herein may be written in any combination of one or more programming languages. The program instructions may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program instructions, when executed by the processor or controller, cause the functions/operations specified in the flowcharts and/or block diagrams to be implemented. The program instructions may execute entirely on a computer, partly on the computer, as a stand-alone software package, partly on the computer and partly on a remote computer or entirely on the remote computer or server. The program instructions may be distributed on specially-programmed devices which may generally be referred to herein as “modules” .

While operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.

Although the present disclosure has been described in language specific to structural features and/or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

A method for fault diagnosis, comprising:

determining, from a signal associated with a motion of a component of a gearbox, a plurality of indications of motion characteristics of the component;

determining variations between the plurality of indications and a plurality of sets of historical indications of the plurality of indications, each set of historical indications indicating the motion characteristics of the component;

selecting indications from the plurality of indications such that the variations of the selected indications are larger than the variations of the indications other than the selected indications; and

detecting a fault that occurred in the gearbox based on the selected indications.
The method of claim 1, wherein determining the variations between the plurality of indications and the plurality of sets of historical indications comprises: for a given indication of the plurality of indications:

determining an expectation value of the set of historical indications of the given indication; and

determining a variation of the given indication based on a difference between a value of the given indication and the expectation value.
The method of claim 1, wherein determining the variations between the plurality of indications and the plurality of sets of historical indications comprises: for a given indication of the plurality of indications:

determining an expectation value and a standard deviation of the set of historical indications of the given indication; and

determining a variation of the given indication based on a value of the given indication, the expectation value and the standard deviation.
The method of claim 1, wherein detecting the fault that occurred in the gearbox based on the selected indications comprises:

determining a sum of the selected indications;

determining a healthy range for the component based on a plurality of sets of historical indications of the selected indications, the healthy range indicating that the component is healthy; and

detecting the fault that occurred in the gearbox if the sum of the selected indications is out of the healthy range.
The method of claim 4, wherein determining the sum of the selected indications comprises determining one of the following:

a sum of the selected indications; or

a weighted sum of the selected indications.
The method of claim 1, wherein detecting the fault that occurred in the gearbox based on the selected indications comprises:

determining a probability density function based on a plurality of sets of historical indications of the selected indications;

determining a confidence interval of the probability density function under a certain confidence level;

determining a probability of the selected indications based on the probability density function;

detecting the fault that occurred in the gearbox if the probability of the selected indications is out of confidence interval.
The method of claim 1, further comprising:

in response to that no fault occurred in the gearbox, storing the plurality of indications into a database as a new set of historical indications of the component.
The method of claim 1, wherein the plurality of indications are determined based on one or more of the following:

a magnitude of a frequency in a spectrum of the signal, the frequency associated with the motion of the component;

signal-to-noise ratios or magnitudes of sidebands of the frequency; or

a Root Mean Square or a Kurtosis of a pattern in time-domain of the signal.
An electronic device, comprising:

at least one processing unit; and

at least one memory coupled to the at least one processing unit and storing instructions executable by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the acts of any one of the methods according to claims 1-8.
A computer readable storage medium having computer readable program instructions stored thereon which, when executed by a processing unit, cause the processing unit to perform the acts of any one of the methods according to claims 1-8.