Method and apparatus for estimating remaining useful life of a device

Abstract

The present disclosure belongs to the technical field of nuclear power and particularly relates to a method and device for estimating the residual service life of equipment. The present disclosure analyzes equipment vibration signals to obtain equipment health indicators. The vibration signals contain rich health state information of mechanical equipment. The present disclosure quantifies the vibration signals to construct a health index to represent the health state degradation trend of the equipment. Based on the extracted equipment health indicators, the degradation process of the equipment is modeled using various degradation trends such as polynomial degradation. Finally, the residual service life of the equipment is estimated based on the concept of soft threshold. In this way, the present disclosure realizes real-time online monitoring, intelligent early warning, intelligent diagnosis and life prediction of systems and equipment, improves the reliability analysis and management capability of the equipment, and helps enterprise managers to optimize maintenance decisions.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of nuclear power, and particularly relates to a method and device for estimating the remaining service life of equipment. BACKGROUND

[0002] In the industrial field, due to the wear of equipment during use, the wear presents a phenomenon of continuous accumulation with different running time and running conditions, which leads to the gradual reduction of the usable life of the equipment. How to more objectively and accurately monitor the service life of the equipment has become a problem to be solved. SUMMARY

[0003] In order to overcome the problems in the related art, a method and device for estimating the remaining service life of equipment are provided.

[0004] According to an aspect of an embodiment of the present disclosure, a method for estimating the remaining service life of equipment is provided, and the method comprises:

[0005] According to a preset sampling frequency, an original vibration signal of a target equipment in a preset time period is collected;

[0006] A sensitive frequency band in which a non-fault signal is located is determined, and the original vibration signal is filtered to obtain a filtered vibration signal according to the sensitive frequency band;

[0007] The filtered vibration signal is envelope demodulated to obtain an envelope signal;

[0008] The root mean square value of the envelope signal is determined, and the root mean square value is normalized to obtain health degree data of the target equipment in the preset time period;

[0009] A degradation model as shown in Formula I is fitted according to the health degree data,

[0010] X k =b0+A k b+ε(t) Formula I

[0011] Wherein, X k is a health degree data set of the target equipment at each time, A k is a set of each time, b is a set of degradation model parameters, b=(b1,b2) T , and ε(t) is an error term, ε(t)=σ 2 I k , σ is a constant, and I k is a k-order unit matrix;

[0012] According to the degradation model, a remaining service life of the target device under the current failure threshold is determined according to the set failure threshold.

[0013] In a possible implementation, the method further includes:

[0014] According to the health degree data newly acquired from the target device, the degradation model is updated in parameters by using a Bayesian method, so that the degradation model is adaptively updated.

[0015] In a possible implementation, according to the health degree data newly acquired from the target device, the degradation model is updated in parameters by using a Bayesian method, so that the degradation model is adaptively updated, including:

[0016] According to the Bayesian parameter posterior distribution being proportional to the product of the prior distribution and the likelihood function, the conjugate prior assumption can ensure that the prior distribution and the posterior distribution have the same distribution form. Assuming that the prior distribution of b is a normal distribution with a mean μ b and a variance ∑ b , the posterior distribution of b is:

[0017]

[0018] wherein, assuming the posterior distribution of the parameter b is subject to N(C k D k , C k ), and the posterior distribution of X k is p(X k |b) is a likelihood function.

[0019] At t k+l , the mean of X k+l is and the variance is

[0020] According to another aspect of the embodiments of the present disclosure, a device remaining service life estimation apparatus is provided, and the apparatus includes:

[0021] A collection module is configured to collect original vibration signals of a target device in a preset time period according to a preset sampling frequency;

[0022] A filtering module is configured to determine a sensitive frequency band in which a non-fault signal is located, and perform filtering processing on the original vibration signals according to the sensitive frequency band to obtain filtered vibration signals;

[0023] An envelope module is configured to perform envelope demodulation on the filtered vibration signals to obtain envelope signals;

[0024] A normalization module configured to determine a root mean square value of the envelope signal, and normalize the root mean square value to obtain health degree data of the target device in a preset time period;

[0025] A first determination module configured to fit a degradation model as shown in Equation One according to the health degree data, X k =b0+A k b+ε(t) Equation One

[0026] wherein, X k is a set of health degree data of the target device at each time point, A k is the set of each time point, b is a set of degradation model parameters, b = (b1, b2) T , and ε(t) is an error term, ε(t) = σ 2 I k , σ is a constant, I k is a k-order identity matrix;

[0027] A second determination module configured to determine, by using the degradation model, a remaining useful life of the target device under a current failure threshold, with respect to a set failure threshold.

[0028] In a possible implementation, the apparatus further includes:

[0029] An updating module configured to update parameters of the degradation model by using a Bayesian apparatus according to newly acquired health degree data of the target device, so that the degradation model is adaptively updated.

[0030] In a possible implementation, the updating module includes:

[0031] An updating submodule configured to assume that a posterior distribution of a Bayesian parameter is proportional to a product of a prior distribution and a likelihood function, and a conjugate prior assumption can ensure that the prior distribution and the posterior distribution have the same distribution form, assume that the prior distribution of b is a normal distribution with a mean of μ b and a variance of ∑ b , and the posterior distribution of b is:

[0032]

[0033] wherein, assume that the posterior distribution of the parameter b is subject to N(C k D k , C k ), and the posterior distribution of X k is p(X k |b) is a likelihood function;

[0034] Then at t k+l the mean of X k+l is the variance of X

[0035] According to another aspect of the embodiments of the present disclosure, there is provided a device remaining useful life estimation apparatus, the apparatus comprising:

[0036] a processor;

[0037] a memory for storing processor-executable instructions;

[0038] wherein the processor is configured to perform the method described above.

[0039] According to another aspect of the embodiments of the present disclosure, there is provided a non-volatile computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method described above.

[0040] The present disclosure has the beneficial effect that the present disclosure analyzes the device vibration signal to obtain a device health index. The vibration signal contains rich health state information of mechanical equipment, and the present disclosure scheme constructs a health index by quantizing the vibration signal to represent the health state degradation trend of the equipment. Based on the extracted device health index, a degradation process of the equipment is modeled using a variety of degradation trends such as polynomial degradation, and finally the remaining usable life of the equipment is estimated based on the concept of soft threshold. In this way, the present disclosure realizes real-time online monitoring, intelligent early warning, intelligent diagnosis and life prediction of the system and the equipment, improves the reliability analysis and management capability of the equipment, and helps enterprise managers to optimize maintenance decisions. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is a flowchart of a device remaining useful life estimation method according to an exemplary embodiment.

[0042] Figure 2 is a block diagram of a device remaining useful life estimation apparatus according to an exemplary embodiment. DETAILED DESCRIPTION

[0043] The present disclosure will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] Figure 1 is a flowchart of a device remaining useful life estimation method according to an exemplary embodiment. The method can be executed by a terminal device, for example, the terminal device can be a server, a desktop computer, etc., and the type of terminal device is not limited by the embodiments of the present disclosure. As shown in Figure 1 the method can include:

[0045] Step 100, collecting the original vibration signal of the target device within a preset time period according to a preset sampling frequency;

[0046] Step 101, determining a sensitive frequency band where a non-fault signal is located, filtering the original vibration signal according to the sensitive frequency band to obtain a filtered vibration signal;

[0047] Step 102, performing envelope demodulation on the filtered vibration signal to obtain an envelope signal;

[0048] Step 103: determining a root mean square value of the envelope signal, and performing normalization processing on the root mean square value to obtain health data of the target device within a preset time period;

[0049] Step 104: fitting the health data to obtain a degradation model as shown in Formula 1.

[0050] X k =b0+A k b+ε(t) formula 1

[0051] Among them, X k is the health data set of the target device at each moment, A k Gather for each moment, b is the set of degradation model parameters, b=(b1,b2) T , ε(t) is the error term, ε(t)=σ 2 I k , σ is a constant, I k is the k-order identity matrix;

[0052] Step 105 : For the set failure threshold, the degradation model is used to determine the remaining useful life of the target device under the current failure threshold.

[0053] In a possible implementation, the method further includes:

[0054] According to the health data newly acquired from the target device, the Bayesian method is used to update the parameters of the degradation model, so that the degradation model is adaptively updated.

[0055] For example, the degradation model may be updated with a Bayesian approach based on newly acquired health data from the target device, so that the degradation model is adaptively updated, including:

[0056] According to the Bayesian parameter, the posterior distribution is proportional to the product of the prior distribution and the likelihood function. The conjugate prior hypothesis can ensure that the prior distribution and the posterior distribution have the same distribution form. Suppose the prior distribution of b is with a mean of μ b , the variance is ∑b If X is normally distributed, then the posterior distribution of b is:

[0057]

[0058] where X is assumed to be The posterior distribution of the parameter b is N(C k D k ,C k ), then the posterior distribution of X k is p(X k |b) is the likelihood function;

[0059]

[0060] The mean of X k+l at time t is k+l The variance of X at time t is

[0061] In one possible implementation, a device remaining useful life estimation apparatus is provided, and the apparatus comprises:

[0062] A collection module configured to collect original vibration signals of a target device in a preset time period according to a preset sampling frequency;

[0063] A filtering module configured to determine a sensitive frequency band in which a non-fault signal is located, and perform filtering processing on the original vibration signals according to the sensitive frequency band to obtain filtered vibration signals;

[0064] An envelope module configured to perform envelope demodulation on the filtered vibration signals to obtain envelope signals;

[0065] A normalization module configured to determine a root mean square value of the envelope signals, and perform normalization processing on the root mean square value to obtain health degree data of the target device in the preset time period;

[0066] A first determination module configured to fit a degradation model as shown in Formula I according to the health degree data, X k = b0+ A k b+ ε(t) Formula I

[0067] wherein X k is a health degree data set of the target device at each time point, A k is a set of each time point, b is a set of degradation model parameters, b = (b1, b2) T , and ε(t) is an error term, ε(t) = σ 2 I k , and σ is a constant, Ik is a k-order identity matrix;

[0068] The second determining module is configured to determine, for a set failure threshold, a remaining service life of the target device under the current failure threshold by using the degradation model.

[0069] In a possible implementation, the apparatus further includes:

[0070] The updating module is configured to update parameters of the degradation model by using a Bayesian apparatus according to newly acquired health data of the target device, so that the degradation model is adaptively updated.

[0071] In a possible implementation, the updating module includes:

[0072] The updating submodule is configured to assume that a posterior distribution of the Bayesian parameter is proportional to a product of a prior distribution and a likelihood function, a conjugate prior assumption can ensure that the prior distribution and the posterior distribution have the same distribution form, assume that a prior distribution of b is a normal distribution with a mean μ b and a variance ∑ b , and a posterior distribution of b is:

[0073]

[0074] wherein, assume that a posterior distribution of the parameter b is subject to N(C k D k , C k ), and a posterior distribution of X k is p(X k |b) is a likelihood function;

[0075] At t k+l , a mean of X k+l is and a variance is

[0076] The description of the apparatus has been described in detail in the description of the method, and will not be repeated here.

[0077] Figure 2 is a block diagram of a device remaining service life estimation apparatus according to an exemplary embodiment. For example, the apparatus 1900 can be provided as a server. Refer to Figure 2The apparatus 1900 includes a processing assembly 1922, which is further comprised of one or more processors, and memory resources, represented by the memory 1932, for storing instructions, such as an application program, executable by the processing assembly 1922. The application program stored in the memory 1932 can include one or more modules each corresponding to a set of instructions. In addition, the processing assembly 1922 is configured to execute the instructions to perform the above-described methods.

[0078] The apparatus 1900 can also include a power supply assembly 1926 configured to perform power management of the apparatus 1900, a wired or wireless network interface 1950 configured to connect the apparatus 1900 to a network, and an input output (I / O) interface 1958. The apparatus 1900 can operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or the like.

[0079] In exemplary embodiments, there is also provided a non-transitory computer- readable storage medium, such as the memory 1932 including computer program instructions executable by the processing assembly 1922 of the apparatus 1900 to perform the above-described methods.

[0080] The present disclosure can be a system, a method, and / or a computer program product. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0081] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: 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), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or punched tape, a magnetically encoded device such as magnetic strip cards, an optically encoded device such as a compact disc (CD) or DVD, and / or any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0082] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0083] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computing / processing device, partly on the user's computing / processing device, as a stand-alone software package, partly on the user's computing / processing device and partly on a remote computing / processing device or entirely on the remote computing / processing device or server. In the latter scenario, the remote computing / processing device can be connected to the user's computing / processing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing / processing device, for example, through the Internet using an Internet Service Provider. In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0084] The computer readable program instructions can also be loaded onto a computing / processing device, other programmable data processing apparatus, or other device to cause a series of operations to be performed on the computing / processing device, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computing / processing device, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0085] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer- readable storage medium having no data storage cycles that change state. The instructions can be executed by one or more processors of a computer, to cause a series of operational steps to be performed on the computer to produce a computer-implemented process. The instructions can also cause one or more processors of a computer or other programmable data processing apparatus to

[0086] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0087] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0088] Embodiments of the present disclosure have been described above, and the description is intended to be illustrative of the embodiments and not restrictive of the disclosure. Many modifications and variations of the described embodiments are possible in light of this disclosure without departing from the scope and spirit of the described embodiments. The choice of words in this document is intended to best explain the principles of the embodiments, the practical application, or technical improvements over the existing technology, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for estimating the remaining useful life of equipment, characterized in that: The method comprises: Collect the original vibration signal of the target device within a preset time period according to a preset sampling frequency; Determine a sensitive frequency band where the non-fault signal is located, and filter the original vibration signal according to the sensitive frequency band to obtain a filtered vibration signal; performing envelope demodulation on the filtered vibration signal to obtain an envelope signal; Determining a root mean square value of the envelope signal, and performing normalization processing on the root mean square value to obtain health data of the target device within a preset time period; The degradation model shown in Formula 1 is obtained by fitting the health data: X k = b0 + A k b + ε(t) Equation 1 Among them, X k is the health data set of the target device at each moment, A k Gather for each moment, b is the set of degradation model parameters, b=(b1,b2) T , ε(t) is the error term, ε(t)=σ 2 I k , σ is a constant; For a set failure threshold, using the degradation model, determining the remaining useful life of the target device under the current failure threshold; The method further includes: updating parameters of the degradation model using a Bayesian method based on health data newly acquired from the target device, so that the degradation model is adaptively updated, including: According to the Bayesian parameter, the posterior distribution is proportional to the product of the prior distribution and the likelihood function. The conjugate prior hypothesis can ensure that the prior distribution and the posterior distribution have the same distribution form. Suppose the prior distribution of b is with a mean of μ b , the variance is ∑ b Normal distribution; set up Then the posterior distribution of parameter b follows N(C k D k ,C k ), then X k The posterior distribution of p(X k |b) is the likelihood function; Then at t k+l When X k+l The mean of The variance is 2. A device for estimating the remaining useful life of equipment, characterized in that: The device comprises: An acquisition module is used to acquire the original vibration signal of the target device within a preset time period according to a preset sampling frequency; A filtering module, configured to determine a sensitive frequency band where a non-fault signal is located, and filter the original vibration signal according to the sensitive frequency band to obtain a filtered vibration signal; An envelope module, configured to perform envelope demodulation on the filtered vibration signal to obtain an envelope signal; a normalization module, configured to determine a root mean square value of the envelope signal and perform normalization processing on the root mean square value to obtain health data of the target device within a preset time period; The first determining module is configured to obtain a degradation model as shown in Formula 1 according to the health data. X k = b0 + A k b + ε(t) Equation 1 Among them, X k is the health data set of the target device at each moment, A k Gather for each moment, b is the set of degradation model parameters, b=(b1,b2) T , ε(t) is the error term, ε(t)=σ 2 I k , σ is a constant; A second determination module is configured to determine the remaining useful life of the target device under the current failure threshold using the degradation model according to the set failure threshold; The apparatus further includes: an updating module for updating parameters of the degradation model using a Bayesian method based on health data newly acquired from the target device, so that the degradation model is adaptively updated; The update module includes: an update submodule for updating the posterior distribution of the Bayesian parameter in proportion to the product of the prior distribution and the likelihood function, and the conjugate prior assumption can ensure that the prior distribution and the posterior distribution have the same distribution form. Assume that the prior distribution of b is a mean of μ b , the variance is ∑ b Normal distribution; suppose Then the posterior distribution of parameter b follows N(C k D k ,C k ), then X k The posterior distribution of p(X k |b) is the likelihood function; Then at t k+l When X k+l The mean of The variance is 3. A device for estimating the remaining useful life of equipment, characterized in that: The device comprises: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the method of claim 1.

4. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to claim 1 is implemented.

Images