CN112445199B - Maintenance interval determining method and device, storage medium and terminal - Google Patents
Maintenance interval determining method and device, storage medium and terminal Download PDFInfo
- Publication number
- CN112445199B CN112445199B CN201910845526.2A CN201910845526A CN112445199B CN 112445199 B CN112445199 B CN 112445199B CN 201910845526 A CN201910845526 A CN 201910845526A CN 112445199 B CN112445199 B CN 112445199B
- Authority
- CN
- China
- Prior art keywords
- data
- maintenance
- fault
- reliability function
- maintenance item
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A maintenance interval determining method and device, a storage medium and a terminal are provided, wherein the maintenance interval determining method comprises the following steps: determining at least one fault mode corresponding to the maintenance item; counting historical fault data and current operation data of the maintenance item in each corresponding fault mode; taking the historical fault data as death data, taking the current operation data as right deletion data, and obtaining a reliability function of each fault mode corresponding to the maintenance item point by using the death data and the right deletion data; obtaining a tolerable fault rate threshold value for each fault mode corresponding to the maintenance item point, and calculating allowable working time by using the reliability function and the fault rate threshold value; and determining the maintenance time interval of the maintenance item according to the allowable working time of each fault mode corresponding to the maintenance item. The technical scheme of the invention can accurately determine the maintenance interval of the equipment so as to avoid untimely or excessive maintenance.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a maintenance interval determining method and device, a storage medium and a terminal.
Background
At present, the repair process of equipment such as a high-speed motor train unit mainly comprises five-level repair, wherein one level of repair is daily repair, and the other level of repair is advanced repair. Current preventive maintenance mechanisms are primarily experience-based, timed maintenance solutions.
However, the determination of the repair interval in the prior art lacks support for data for safety reasons. The intervals are typically set too conservatively with excessive maintenance resulting in unnecessary expense.
Disclosure of Invention
The invention solves the technical problem of how to accurately determine the maintenance interval of equipment so as to avoid untimely or excessive maintenance.
In order to solve the foregoing technical problem, an embodiment of the present invention provides a maintenance interval determining method, where the maintenance interval determining method includes: determining at least one fault mode corresponding to the maintenance item; counting historical fault data and current operation data of the maintenance item in each corresponding fault mode; taking the historical fault data as death data, taking the current operation data as right deletion data, and obtaining a reliability function of each fault mode corresponding to the maintenance item point by using the death data and the right deletion data, wherein the reliability function R (t) is used for describing the probability that the failure time of the maintenance item point is more than t under the corresponding fault mode; obtaining a tolerable fault rate threshold value for each fault mode corresponding to the maintenance item point, and calculating allowable working time by using the reliability function and the fault rate threshold value; and determining the maintenance time interval of the maintenance item according to the allowable working time of each fault mode corresponding to the maintenance item.
Optionally, the obtaining a reliability function by using the death data and the right deletion data includes: and calling a survival analysis tool box through a calling interface, and inputting the death data and the right deletion data to obtain the reliability function.
Optionally, the obtaining a reliability function by using the death data and the right deletion data includes: obtaining the reliability function by using the death data and the right deletion data through a parameter estimation algorithm, wherein the reliability function meets exponential distribution or Weibull distribution; or, the death data and the right deletion data are used for obtaining the reliability function through a nonparametric estimation algorithm, and the reliability function is a piecewise step function.
Optionally, the obtaining the reliability function by a nonparametric estimation algorithm using the death data and the right deletion data includes: obtaining the piecewise step function using the death data and the right deletion data statistics; judging whether the piecewise step function conforms to the exponential distribution or Weibull distribution; determining the piecewise step function as the reliability function if the piecewise step function does not conform to the exponential distribution or Weibull distribution; and if the piecewise step function conforms to the exponential distribution or Weibull distribution, obtaining the reliability function through the parameter estimation algorithm.
Optionally, the obtaining a tolerable failure rate threshold for each failure mode corresponding to the maintenance item point, and calculating an allowable operating time by using the reliability function and the failure rate threshold includes: and if the reliability function is obtained through a parameter estimation algorithm, substituting the fault rate threshold value into the reliability function corresponding to each fault mode corresponding to the maintenance item point, and taking the calculated time as the allowable working time of each fault mode corresponding to the maintenance item point.
Optionally, if the reliability function is obtained through a non-parametric estimation algorithm, the following formula is used to calculate the allowable operating time of each fault mode corresponding to the maintenance item point: and a ═ min { r (T) | r (T) ≧ 1-r }, and T ═ inf { T | r (T) ═ a }, wherein r (T) represents a reliability function corresponding to each fault mode corresponding to the maintenance item point, r represents the fault rate threshold, and inf represents an infimum function.
Optionally, the determining at least one failure mode corresponding to the maintenance item includes: acquiring historical maintenance data of the maintenance item; and determining a fault mode corresponding to the maintenance item according to the fault mode which generates faults in the historical maintenance data of the maintenance item.
Optionally, the determining the maintenance time interval of the maintenance item according to the allowable working time of each fault mode corresponding to the maintenance item includes: and selecting the minimum value of the allowable working time of each fault mode corresponding to the maintenance item point to be used as the maintenance time interval of the maintenance item point.
Optionally, the historical fault data includes a fault time duration or a fault mileage, and the current operation data includes a current used time duration or a current fault mileage.
In order to solve the above technical problem, an embodiment of the present invention further discloses a maintenance interval determining device, where the maintenance interval determining device includes: the failure mode determining module is used for determining at least one failure mode corresponding to the maintenance item; the statistical module is used for counting historical fault data and current operation data of the maintenance item in each corresponding fault mode; the reliability function module is used for taking the historical fault data as death data, taking the current operation data as right deletion data, and obtaining a reliability function of each fault mode corresponding to the maintenance item point by using the death data and the right deletion data, wherein the reliability function R (t) is used for describing the probability that the failure time of the maintenance item point is more than t under the corresponding fault mode; the allowable working duration calculation module is used for acquiring a tolerable fault rate threshold value for each fault mode corresponding to the maintenance item point and calculating allowable working duration by using the reliability function and the fault rate threshold value; and the maintenance time interval determining module is used for determining the maintenance time interval of the maintenance item according to the allowable working time of each fault mode corresponding to the maintenance item.
The embodiment of the invention also discloses a storage medium, wherein a computer instruction is stored on the storage medium, and the steps of the maintenance interval determination method are executed when the computer instruction runs.
The embodiment of the invention also discloses a terminal which comprises a memory and a processor, wherein the memory is stored with a computer instruction capable of running on the processor, and the processor executes the step of the maintenance interval determination method when running the computer instruction.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
according to the technical scheme, a reliability function is established through historical fault data and current operation data of the maintenance item points in each corresponding fault mode, so that a fault distribution rule of the maintenance item points in each corresponding fault mode is obtained, the probability that the failure time of the maintenance item points in each corresponding fault mode is greater than t is further obtained, the allowable working time under a tolerable fault rate threshold value is calculated on the basis of the probability, and the maintenance time interval of the maintenance item points is determined on the premise of controlling the occurrence rate of faults; therefore, the problem that the maintenance interval of the existing maintenance item is determined only by experience and lacks data support can be solved, the occurrence rate of faults between two adjacent maintenance intervals is effectively controlled, excessive maintenance is avoided as far as possible, and a strong basis is provided for guaranteeing operation and reducing operation cost.
Drawings
FIG. 1 is a flow chart of a method of determining a maintenance interval in accordance with an embodiment of the present invention;
FIG. 2 is a flowchart of one embodiment of step S103 shown in FIG. 1;
FIG. 3 is a flowchart of one embodiment of step S101 shown in FIG. 1;
fig. 4 is a schematic structural diagram of a maintenance interval determination apparatus according to an embodiment of the present invention.
Detailed Description
As described in the background, the prior art determination of service intervals lacks support for data for safety reasons. The intervals are typically set too conservatively with excessive maintenance resulting in unnecessary expense.
The inventor of the application discovers that the reliability theory can estimate the reliability of the equipment by utilizing historical fault data and current normal-use equipment data without faults, so that the probability of the equipment faults within a certain period of time (or mileage) can be effectively estimated, and the mathematical support is provided for the determination of the maintenance interval, thereby effectively preventing the conditions of under-repair, over-repair and the like of the equipment.
According to the technical scheme, a reliability function is established through historical fault data and current operation data of the maintenance items under each corresponding fault mode, so that a fault distribution rule of the maintenance items under each corresponding fault mode is obtained, namely the probability that the failure time of the maintenance items under each corresponding fault mode is greater than t is also obtained, the allowable working time under a tolerable fault rate threshold value is calculated on the basis of the probability, namely, the maintenance time interval of the maintenance items is determined on the premise of controlling the occurrence rate of faults; therefore, the problem that the maintenance interval of the existing maintenance item is determined only by experience and lacks data support can be solved, the occurrence rate of faults between two adjacent maintenance intervals is effectively controlled, excessive maintenance is avoided as far as possible, and a strong basis is provided for guaranteeing operation and reducing operation cost.
The maintenance item in this embodiment may be a maintenance location in any applicable terminal device, and may include several components, for example, one or more components of a motor train unit, one or more components of a vehicle, and the like.
In this embodiment, a failure mode corresponding to a maintenance entry means that a certain component in the maintenance entry fails.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
Fig. 1 is a flowchart of a maintenance interval determination method according to an embodiment of the present invention.
Referring to fig. 1, the repair interval determining method may include the following steps:
step S101: determining at least one fault mode corresponding to the maintenance item;
step S102: counting historical fault data and current operation data of the maintenance item in each corresponding fault mode;
step S103: taking the historical fault data as death data, taking the current operation data as right deletion data, and obtaining a reliability function of each fault mode corresponding to the maintenance item point by using the death data and the right deletion data, wherein the reliability function R (t) is used for describing the probability that the failure time of the maintenance item point is more than t under the corresponding fault mode;
step S104: obtaining a tolerable fault rate threshold value for each fault mode corresponding to the maintenance item point, and calculating allowable working time by using the reliability function and the fault rate threshold value;
step S105: and determining the maintenance time interval of the maintenance item according to the allowable working time of each fault mode corresponding to the maintenance item.
It should be noted that the sequence numbers of the steps in this embodiment do not represent a limitation on the execution sequence of the steps.
In a specific implementation of step S101, each maintenance entry may include one or more components, and each maintenance entry may have one or more failure modes when a failure occurs. From this, one or more failure modes corresponding to each maintenance entry may be determined.
It will be appreciated by those skilled in the art that the failure mode may be a manifestation of a failure; reference may be made to the prior art regarding specific types of failure modes, as embodiments of the invention are not limited in this respect.
In the specific implementation of step S102, the death data and right deletion data of the maintenance item in each corresponding failure mode, that is, the historical failure data and the current operation data, may be counted to obtain a reliability function. For example, the historical fault data 11 and the current operation data 11 of the maintenance item point 1 in the fault mode 1, and the historical fault data 12 and the current operation data 12 of the maintenance item point 1 in the fault mode 2 are counted; the historical failure data 21 and the current operation data 21 of the statistical maintenance item 2 in the failure mode 1, and the like, wherein the current operation data 11, the current operation data 12, and the current operation data 21 may be the same data.
In a specific embodiment, the historical fault data includes a fault time duration or a running mileage, and the current running data includes a current used time duration or a running mileage.
In the specific implementation of step S103, the historical failure data may be regarded as death data, that is, the maintenance item fails at the time; the current operation data is used as right deletion data, namely the maintenance item point does not have a fault before the moment. And obtaining the reliability function of each fault mode corresponding to the maintenance item point by using the death data and the right deletion data. The reliability function R (t) can describe the probability that a repair term point will fail for a time greater than t in its corresponding failure mode. For example, the reliability function R11(t) for repair entry 1 at its corresponding failure mode 1 may represent the probability that repair entry 1 will fail for a time greater than t at failure mode 1.
Further, in the specific implementation of step S104 and step S105, the allowable operating time of the maintenance item in each corresponding failure mode may be calculated according to the obtained reliability function of each failure mode corresponding to the maintenance item.
Because the allowable working time lengths of the same maintenance item in different corresponding failure modes may be different, the final allowable working time length may be selected from the different allowable working time lengths to serve as the maintenance time interval of the maintenance item.
In a specific application, a maintenance operation will be performed on the maintenance item at the maintenance time interval determined in step S105 in the subsequent step.
It should be noted that the tolerable failure rate threshold may be a preset probability value, which may be an empirical value, and may represent the failure rate of the repair item in its corresponding failure mode. The tolerable failure rate threshold may be adaptively adjusted according to the actual application environment, which is not limited in the embodiment of the present invention.
According to the embodiment of the invention, a reliability function is established through historical fault data and current operation data of the maintenance item points under each corresponding fault mode, so that a fault distribution rule of the maintenance item points under each corresponding fault mode is obtained, the probability that the failure time of the maintenance item points under each corresponding fault mode is greater than t is further obtained, the allowable working time under a tolerable fault rate threshold value is calculated on the basis of the probability, and the maintenance time interval of the maintenance item points is determined on the premise of controlling the occurrence rate of faults; therefore, the problem that the maintenance interval of the existing maintenance item is determined only by experience and lacks data support can be solved, the occurrence rate of faults between two adjacent maintenance intervals is effectively controlled, excessive maintenance is avoided as far as possible, and a strong basis is provided for guaranteeing operation and reducing operation cost.
In a specific embodiment, step S105 shown in fig. 1 may include the following steps: and selecting the minimum value of the allowable working time of each fault mode corresponding to the maintenance item point to be used as the maintenance time interval of the maintenance item point.
In this embodiment, for different allowable operating durations of the fault modes corresponding to each maintenance item, the minimum value of the different allowable operating durations may be selected as the maintenance time interval of the maintenance item. By adopting the time interval, the maintenance items can be maintained in time under each fault mode, and the normal operation of the maintenance items is ensured.
For example, the Admission of each failure mode corresponding to repair entry 1The allowable operating time periods are respectively T1,T2,…Tn. Wherein n is the number of the fault modes under the maintenance item 1. Outputting the minimum value T of the multiple allowable working time lengthsmin＝min{T1,T2,…Tn}，TminMaintenance interval for maintenance entry 1.
In one non-limiting embodiment of the present invention, step S103 shown in fig. 1 may include the following steps: and calling a survival analysis tool box through a calling interface, and inputting the death data and the right deletion data to obtain the reliability function.
In specific implementation, the survival analysis toolbox can integrate various parameter estimation algorithms and non-parameter estimation algorithms of the traditional survival analysis theory about the reliability function (namely, the survival function), and can obtain effective estimation of the reliability function through a simple calling interface. Specifically, the survival analysis toolbox may be pre-packaged, and the estimated reliability function may be obtained by directly calling the survival analysis toolbox, that is, inputting the death data and the right deletion data obtained by statistics into the survival analysis toolbox.
In one non-limiting embodiment of the present invention, the estimation of the reliability function may include a parametric estimation algorithm as well as a non-parametric estimation algorithm. Referring to fig. 2, step S103 shown in fig. 1 may include the following steps:
step S201: obtaining the reliability function by using the death data and the right deletion data through a parameter estimation algorithm, wherein the reliability function meets exponential distribution or Weibull distribution;
step S202: and obtaining the reliability function by using the death data and the right deletion data through a nonparametric estimation algorithm, wherein the reliability function is a piecewise step function.
It should be noted that, in an actual application, one of step S201 and step S202 may be selectively executed.
In this embodiment, the reliability function obtained by the parameter estimation algorithm may satisfy exponential distribution or weibull distribution, and the reliability function obtained by the non-parameter estimation algorithm is a piecewise step function.
Specifically, the parameter estimation algorithm of the reliability function may be a likelihood function that maximizes:
wherein θ is a parameter to be estimated. First part f (t)iTheta) corresponds to death data, F is a density function corresponding to a reliability function, and a second portion 1-F (t)iθ) corresponds to right erasure data, and F is the distribution function corresponding to the reliability function, i.e. F (t) is 1-r (t). And substituting the time corresponding to the death data and the right deletion data into a formula to obtain a univariate function about theta, and obtaining the maximum likelihood estimation of theta by an optimization method such as gradient descent.
It should be understood by those skilled in the art that the parameter estimation algorithm may be other estimation calculation processes, and the embodiment of the present invention is not limited thereto.
Specifically, the non-parameter estimation algorithm of the reliability function may be to directly estimate some important moments, for example, reliability function values at several moments corresponding to death data, to obtain a ladder-type reliability function (that is, the reliability function from the previous death moment to the next death moment has the same value). For example, the examples of exponential distribution and weibull distribution are used to illustrate how to use the non-parametric method to obtain the reliability function r (t) and examine the distribution type: death time t of all death data1，t2……tnIn the coordinate system, n points (t) are obtained as followsi,ln(R(ti) I) 1,2, … … n. If the n points are substantially collinear, the reliability function is considered to approximately follow an exponential distribution. Otherwise, calculate the following n points (ln (t)i),ln(-ln(R(ti) ()) i ═ 1,2, … … n. If the n points are substantially collinear, the reliability function is considered to approximately follow a Weibull distribution. In this case, the reliability function can be estimated by using a parameter estimation algorithm. Otherwise, under the condition that the reliability function does not obey Weibull distribution or exponential distribution, directly taking the step-type reliability function obtained by the calculation as the final reliability functionAn estimated reliability function.
It should be understood by those skilled in the art that the non-parametric estimation method may use a lifetime table algorithm, a product limit estimation algorithm, etc., and may also be any other implementable non-parametric estimation algorithm, which is not limited in this embodiment of the present invention.
Further, step S103 shown in fig. 1 may include the following steps: obtaining the piecewise step function using the death data and the right deletion data statistics; judging whether the piecewise step function conforms to the exponential distribution or Weibull distribution; determining the piecewise step function as the reliability function if the piecewise step function does not conform to the exponential distribution or Weibull distribution; and if the piecewise step function conforms to the exponential distribution or Weibull distribution, obtaining the reliability function through the parameter estimation algorithm.
In this embodiment, the distribution of the piecewise step function obtained by the non-parametric estimation algorithm may be judged to determine the final reliability function.
In other words, in the case where the stepwise function does not conform to the exponential distribution or the weibull distribution, the stepwise function is directly taken as the reliability function; on the contrary, in the case that the piecewise step function does not conform to the exponential distribution or the weibull distribution, it means that the distribution function under the exponential distribution or the weibull distribution can be further estimated by the parameter estimation algorithm, so that the reliability function can be obtained by the parameter estimation algorithm. I.e. the non-parametric estimate and the parametric estimate may be combined to determine the reliability function.
Further, step S104 may include the steps of: and if the reliability function is obtained through a parameter estimation algorithm, substituting the fault rate threshold value into the reliability function corresponding to each fault mode corresponding to the maintenance item point, and taking the calculated time as the allowable working time of each fault mode corresponding to the maintenance item point.
In this embodiment, for the reliability function obtained by the parameter estimation algorithm, when the allowable operating duration is calculated by using the reliability function, the tolerable failure rate threshold may be directly substituted into the reliability function.
Optionally, for the reliability function obtained by the non-parametric estimation algorithm, since the reliability function is a piecewise step function, and the same Y value in the step function may correspond to different X values, that is, under the same failure rate threshold, there may be a plurality of different time values, and therefore, the minimum value also needs to be calculated.
In a specific application, a tolerable failure rate threshold, that is, a preset probability r, is set for the failure mode 1 corresponding to the maintenance item point 1, that is, the failure probability of the failure mode 1 between two maintenance operations is controlled within the range of r. When the reliability function R (T) is obtained through a parameter estimation algorithm, allowing the working time length T to be the time when R (T) is 1-r; when r (t) is approximated by a non-parametric estimation algorithm: the intermediate parameter a ═ min { r (T) | r (T) ≧ 1-r }, the allowable operating time period T ═ inf { T | r (T) ≧ a }, where inf denotes the infimum limit.
In a non-limiting embodiment of the present invention, referring to fig. 3, step S101 shown in fig. 1 may include the following steps:
step S301: acquiring historical maintenance data of maintenance items;
step S302: and determining the fault mode corresponding to each maintenance item according to the fault mode which generates faults in the historical maintenance data of the maintenance items.
In this embodiment, for the failure mode corresponding to the maintenance item, the failure mode may be obtained from historical maintenance data of the maintenance item. The historical repair data for a repair entry may include failure modes for which the repair entry has failed. That is, a failure mode occurring in the historical repair data of a repair entry may be taken as a failure mode corresponding to the repair entry.
For example, for repair entry 1 whose historical repair data includes repair operations for failure mode 1, failure mode 2, and failure mode 3, then it may be determined that the failure mode to which repair entry 1 corresponds includes failure mode 1, failure mode 2, and failure mode 3.
Referring to fig. 4, the embodiment of the present invention further discloses a maintenance interval determination apparatus 40, and the maintenance interval determination apparatus 40 may include a failure mode determination module 401, a statistics module 402, a reliability function module 403, an allowable operating time calculation module 404, and a maintenance time interval determination module 405.
The failure mode determining module 401 is configured to determine at least one failure mode corresponding to the maintenance item; the statistical module 402 is used for counting historical fault data and current operation data of the maintenance item in each corresponding fault mode; the reliability function module 403 is configured to use the historical fault data as death data, use the current operation data as right deletion data, and obtain a reliability function of each fault mode corresponding to a maintenance item point by using the death data and the right deletion data, where the reliability function r (t) can describe a probability that failure time of the maintenance item point is greater than t in the corresponding fault mode; the allowable working duration calculation module 404 is configured to obtain a tolerable failure rate threshold for each failure mode corresponding to the maintenance item point, and calculate an allowable working duration by using the reliability function and the failure rate threshold; the maintenance time interval determination module 405 is configured to determine the maintenance time interval of the maintenance item according to the allowable working time of each failure mode corresponding to the maintenance item.
According to the embodiment of the invention, a reliability function is established through historical fault data and current operation data of the maintenance item points under each corresponding fault mode, so that a fault distribution rule of the maintenance item points under each corresponding fault mode is obtained, the probability that the failure time of the maintenance item points under each corresponding fault mode is greater than t is further obtained, the allowable working time under a tolerable fault rate threshold value is calculated on the basis of the probability, and the maintenance time interval of the maintenance item points is determined on the premise of controlling the occurrence rate of faults; therefore, the problem that the maintenance interval of the existing maintenance item is determined only by experience and lacks data support can be solved, the occurrence rate of faults between two adjacent maintenance intervals is effectively controlled, excessive maintenance is avoided as far as possible, and a strong basis is provided for guaranteeing operation and reducing operation cost.
For more details on the working principle and the working mode of the maintenance interval determination device 40, reference may be made to the related descriptions in fig. 1 to 3, and details are not repeated here.
The embodiment of the invention also discloses a storage medium, wherein computer instructions are stored on the storage medium, and when the computer instructions are operated, the steps of the method shown in the figures 1 to 3 can be executed. The storage medium may include ROM, RAM, magnetic or optical disks, etc. The storage medium may further include a non-volatile memory (non-volatile) or a non-transitory memory (non-transient), and the like.
The embodiment of the invention also discloses a terminal which can comprise a memory and a processor, wherein the memory is stored with computer instructions capable of running on the processor. The processor, when executing the computer instructions, may perform the steps of the methods shown in fig. 1-3. The terminal includes, but is not limited to, a mobile phone, a computer, a tablet computer and other terminal devices.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A maintenance interval determination method, comprising:
determining at least one fault mode corresponding to the maintenance item;
counting historical fault data and current operation data of the maintenance item in each corresponding fault mode;
taking the historical fault data as death data, taking the current operation data as right deletion data, and obtaining a reliability function of each fault mode corresponding to the maintenance item point by using the death data and the right deletion data, wherein the reliability function R (t) is used for describing the probability that the failure time of the maintenance item point is more than t under the corresponding fault mode;
obtaining a tolerable fault rate threshold value for each fault mode corresponding to the maintenance item point, and calculating allowable working time by using the reliability function and the fault rate threshold value;
determining the maintenance time interval of the maintenance item according to the allowable working time of each fault mode corresponding to the maintenance item;
the obtaining a reliability function using the death data and the right deletion data comprises: obtaining the reliability function by using the death data and the right deletion data through a parameter estimation algorithm, wherein the reliability function meets exponential distribution or Weibull distribution; or, the death data and the right deletion data are used for obtaining the reliability function through a nonparametric estimation algorithm, and the reliability function is a piecewise step function.
2. The repair interval determination method of claim 1, wherein said deriving the reliability function by a nonparametric estimation algorithm using the death data and the right deletion data comprises:
obtaining the piecewise step function using the death data and the right deletion data statistics;
judging whether the piecewise step function conforms to the exponential distribution or Weibull distribution;
determining the piecewise step function as the reliability function if the piecewise step function does not conform to the exponential distribution or Weibull distribution;
and if the piecewise step function conforms to the exponential distribution or Weibull distribution, obtaining the reliability function through the parameter estimation algorithm.
3. The repair interval determining method according to claim 1, wherein obtaining a tolerable failure rate threshold for each failure mode corresponding to the repair item, and calculating an allowable operating time period using the reliability function and the failure rate threshold comprises:
and if the reliability function is obtained through a parameter estimation algorithm, substituting the fault rate threshold value into the reliability function corresponding to each fault mode corresponding to the maintenance item point, and taking the calculated time as the allowable working time of each fault mode corresponding to the maintenance item point.
4. The repair interval determination method according to claim 3, wherein if the reliability function is obtained by a non-parametric estimation algorithm, the allowable operating time period of each failure mode corresponding to the repair item is calculated using the following formula:
and a ═ min { r (T) | r (T) ≧ 1-r }, and T ═ inf { T | r (T) ═ a }, wherein r (T) represents a reliability function corresponding to each fault mode corresponding to the maintenance item point, r represents the fault rate threshold, and inf represents an infimum function.
5. The repair interval determining method according to claim 1, wherein the determining at least one failure mode corresponding to a repair entry point comprises:
acquiring historical maintenance data of the maintenance item;
and determining a fault mode corresponding to the maintenance item according to the fault mode which generates faults in the historical maintenance data of the maintenance item.
6. The maintenance interval determination method according to claim 1, wherein determining the maintenance time interval of the maintenance item according to the allowable operating time length of each failure mode corresponding to the maintenance item comprises:
and selecting the minimum value of the allowable working time of each fault mode corresponding to the maintenance item point to be used as the maintenance time interval of the maintenance item point.
7. The repair interval determination method of claim 1, wherein the historical failure data comprises a length of time in use or a mileage traveled while failing, and the current operational data comprises a length of time currently in use or a mileage traveled.
8. A maintenance interval determination apparatus, characterized by comprising:
the failure mode determining module is used for determining at least one failure mode corresponding to the maintenance item;
the statistical module is used for counting historical fault data and current operation data of the maintenance item in each corresponding fault mode;
the reliability function module is used for taking the historical fault data as death data, taking the current operation data as right deletion data, and obtaining a reliability function of each fault mode corresponding to the maintenance item point by using the death data and the right deletion data, wherein the reliability function R (t) is used for describing the probability that the failure time of the maintenance item point is more than t under the corresponding fault mode;
the allowable working duration calculation module is used for acquiring a tolerable fault rate threshold value for each fault mode corresponding to the maintenance item point and calculating allowable working duration by using the reliability function and the fault rate threshold value;
the maintenance time interval determining module is used for determining the maintenance time interval of the maintenance item according to the allowable working time of each fault mode corresponding to the maintenance item;
the reliability function module obtains the reliability function by using the death data and the right deletion data through a parameter estimation algorithm, wherein the reliability function meets the exponential distribution or the Weibull distribution; or the reliability function module obtains the reliability function through a nonparametric estimation algorithm by using the death data and the right deletion data, wherein the reliability function is a piecewise step function.
9. A storage medium having stored thereon computer instructions, wherein the computer instructions are operable to perform the steps of the service interval determination method of any one of claims 1 to 7.
10. A terminal comprising a memory and a processor, the memory having stored thereon computer instructions executable on the processor, wherein the processor, when executing the computer instructions, performs the steps of the maintenance interval determination method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910845526.2A CN112445199B (en) | 2019-09-04 | 2019-09-04 | Maintenance interval determining method and device, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910845526.2A CN112445199B (en) | 2019-09-04 | 2019-09-04 | Maintenance interval determining method and device, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112445199A CN112445199A (en) | 2021-03-05 |
| CN112445199B true CN112445199B (en) | 2022-03-15 |
Family
ID=74733598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910845526.2A Active CN112445199B (en) | 2019-09-04 | 2019-09-04 | Maintenance interval determining method and device, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112445199B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358299A (en) * | 2017-06-16 | 2017-11-17 | 杭州培慕科技有限公司 | Pre-emptive maintenace closed-loop policy based on fault mode |
| CN107403226A (en) * | 2017-07-17 | 2017-11-28 | 南京中车浦镇城轨车辆有限责任公司 | It is a kind of to determine traction for transformer preventative maintenance interval and the method for number based on residual life reliability |
| CN109740930A (en) * | 2018-12-29 | 2019-05-10 | 华润电力技术研究院有限公司 | Maintenance policy is formulated and Reliability assessment method, terminal and computer storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104237761B (en) * | 2013-06-13 | 2018-05-04 | 通用电气公司 | The system and method for the failure mode detection and protection of insulated gate bipolar transistor |
| CN104239694B (en) * | 2014-08-28 | 2016-11-23 | 北京交通大学 | The failure predication of a kind of municipal rail train bogie and condition maintenarnce method |
| CN108764495A (en) * | 2018-05-15 | 2018-11-06 | 中山职业技术学院 | A kind of decision-making technique and its computer readable storage medium of vehicle maintenance scheme |
-
2019
- 2019-09-04 CN CN201910845526.2A patent/CN112445199B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358299A (en) * | 2017-06-16 | 2017-11-17 | 杭州培慕科技有限公司 | Pre-emptive maintenace closed-loop policy based on fault mode |
| CN107403226A (en) * | 2017-07-17 | 2017-11-28 | 南京中车浦镇城轨车辆有限责任公司 | It is a kind of to determine traction for transformer preventative maintenance interval and the method for number based on residual life reliability |
| CN109740930A (en) * | 2018-12-29 | 2019-05-10 | 华润电力技术研究院有限公司 | Maintenance policy is formulated and Reliability assessment method, terminal and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112445199A (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9727533B2 (en) | Detecting anomalies in a time series | |
| He et al. | Scheduling flexible job shop problem subject to machine breakdown with route changing and right-shift strategies | |
| US11415898B2 (en) | Signal-domain adaptation for metrology | |
| CN113658414B (en) | Mine equipment fault early warning method and device, terminal equipment and storage medium | |
| CN108427986A (en) | A kind of production line electrical fault prediction technique and device | |
| JP7262000B2 (en) | Priority determination system, priority determination method and program | |
| EP4242939A1 (en) | Rru undervoltage risk prediction method, apparatus, and system, device, and medium | |
| WO2016155996A1 (en) | Production system and method for controlling same | |
| CN112668862A (en) | Adaptability quantitative evaluation method of production line | |
| CN116955455B (en) | Processing method and platform suitable for radiation monitoring system | |
| CN113592337A (en) | Fault processing method and device, electronic equipment and storage medium | |
| CN114627628B (en) | Semiconductor machine alarm processing method and device, electronic equipment and storage medium | |
| JP2018124799A (en) | Visualization method of manufacturing result, image processing device and program | |
| CN117556332B (en) | Heating furnace waste heat utilization management method, system and storage medium based on Internet of things | |
| CN112445199B (en) | Maintenance interval determining method and device, storage medium and terminal | |
| CN106557839B (en) | Equipment maintenance strategy optimization method and system based on big data | |
| JP2008141641A (en) | Abnormal traffic detection apparatus and method | |
| CN106936611B (en) | Method and device for predicting network state | |
| CN108073464A (en) | A kind of time series data abnormal point detecting method and device based on speed and acceleration | |
| Nijhawan et al. | On development of change point based generalized SRGM for software with multiple releases | |
| CN109032853B (en) | Method and device for controlling FPGA card group | |
| CN112162528B (en) | Fault diagnosis method, device, equipment and storage medium of numerical control machine tool | |
| CN114742143A (en) | Safe training model construction method, device and system based on federal learning | |
| CN113386797A (en) | Method, apparatus, device, medium and product for controlling an autonomous vehicle | |
| CN113536042A (en) | Time series abnormity detection method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |