CN115719013B - Multistage maintenance decision modeling method and device for intelligent manufacturing production line - Google Patents
Multistage maintenance decision modeling method and device for intelligent manufacturing production line Download PDFInfo
- Publication number
- CN115719013B CN115719013B CN202310035776.6A CN202310035776A CN115719013B CN 115719013 B CN115719013 B CN 115719013B CN 202310035776 A CN202310035776 A CN 202310035776A CN 115719013 B CN115719013 B CN 115719013B
- Authority
- CN
- China
- Prior art keywords
- model
- functional
- production line
- availability
- degradation
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a multistage maintenance decision modeling method and device for an intelligent manufacturing production line, wherein the method comprises the following steps: obtaining the fault time distribution of the functional fault and the degradation fault of the component by utilizing the historical fault data of the component; constructing a functional life model and a degradation life model of the component according to the fault time distribution; according to the functional life model and the degradation life model of the component, constructing a functional availability model, a performance availability model and a performance availability penalty model of the equipment; calculating the loss of the production line due to the functional failure and the degradation failure by using the functional availability model, the performance availability model and the performance availability penalty model of the equipment, and constructing a production line benefit model; and carrying out optimization solution on the production line benefit model according to constraint conditions of the production line requirements to obtain maintenance decision for maximizing the production line benefit. The invention can construct a multistage maintenance decision model of the intelligent manufacturing production line, reduce unexpected shutdown and maximize the benefit of the production line.
Description
Technical Field
The invention belongs to the technical field of intelligent manufacturing, and particularly relates to a multistage maintenance decision modeling method and device for an intelligent manufacturing production line, computer equipment and a computer readable storage medium.
Background
An intelligent manufacturing line is a manufacturing system which is composed of a plurality of manufacturing devices and performs interconnection communication and cooperative work between the plurality of devices through an information system such as an MES (manufacturing execution system ). The production line can randomly generate functional faults or degradation faults in the production operation process, and the random functional faults or hidden degradation faults can cause accidental shutdown of the production line, so that serious economic and social benefit losses are brought. In the production line running operation, failure of any one device will result in different degrees of loss of the production line. Also, different devices have multiple critical components, and different components have multiple failure modes. The existing maintenance decision of most manufacturing production lines only considers the failure prediction of equipment level, does not consider the influence problem of bottom components and even different failures, and cannot provide sufficient technical support for the active operation and maintenance of intelligent manufacturing production lines.
Disclosure of Invention
The invention aims to provide a multistage maintenance decision modeling method and device for an intelligent manufacturing production line, computer equipment and a computer readable storage medium, which can construct a multistage maintenance decision model for the intelligent manufacturing production line, effectively support analysis and formulation of a maintenance scheme of the intelligent manufacturing production line, reduce unexpected shutdown and maximize production line benefit.
One aspect of the present invention provides a multi-level maintenance decision modeling method for an intelligent manufacturing line that includes m devices E i I=1,..m, each device E i Having n i Component C ij ，j＝1，...，n i The method comprises the following steps:
failure time distribution obtaining step: by means of part C ij Obtain part C ij A failure time distribution of functional failures and a failure time distribution of degradation failures;
a component life model construction step, based on component C ij Time distribution of all functional failures of building component C ij Functional life model based on random dependence of multifunctional faults
According to part C ij Is used to construct component C ij Is based on the degradation life model of random dependence of multiple degradation faults
A device availability model construction step, based on component C ij Functional life model of (2)
Build equipment E i Is based on the functional availability model A of the multi-component functional structure dependence i (t) according to part C ij Is>
Build equipment E i Performance availability model B based on multi-component performance structure dependency i (t) and Performance availability penalty model AB i (t), wherein t is time;
production line benefit model construction step, utilizing equipment E i Functional availability model A i (t) calculating the loss of the production line due to the functional failure; using apparatus E i Performance availability model B of (2) i (t) and Performance availability penalty model AB i (t) calculating the loss of the production line caused by the degradation fault, and constructing a production line benefit model based on multi-equipment economic dependence according to the loss of the production line caused by the functional fault and the degradation fault;
and a maintenance decision obtaining step, wherein the production line benefit model is optimized and solved according to constraint conditions required by the production line, so as to obtain a maintenance decision for maximizing the production line benefit.
Preferably, in the equipment availability model construction step, component C ij Functional life model of (2)
Fused into device E i Functional model of (2)>
The expected functional failure time of the computing device at time t +.>
Obtaining device E i Functional availability of->
Preferably, in the device availability model construction step, the calculating means C ij Expected degradation fault duration within Γ (t)
Obtaining device E i Performance failure time>
Thereby obtaining the apparatus E i Performance availability model of->
Wherein Γ (t) is device E i Γ (t) =t- α i (t)。
Preferably, in the device availability model construction step, the device E is constructed as follows i Performance availability penalty model AB of (a) i (t)：
Wherein omega ij Is part C ij Is to device E i An influencing factor for the production quality of (a).
Preferably, in the production line benefit model construction step, the model A is constructed according to the function availability i (t) and Performance availability model B i (t) obtaining expected failure time points according to the serial-parallel connection relation among devices and a performance availability penalty model AB i (t) calculating the loss in the time period between each expected failure time point.
Preferably, in the component lifetime model construction step, the failure time distribution of all the functional failures is respectively Monte Carlo sampledTaking the earliest fault composition statistic X in the w-th sampling sample of each distribution ij ＝min{x ij，1 ，...，x ij，w ，...，x ij，z Fitting the statistics to obtain a functional life model
Wherein z is Monte Carlo sampling times, and z is more than 10000.
Preferably, in the component lifetime model construction step, a multivariate joint distribution function is constructed for a plurality of degradation faults that affect each other
As a model of degradation life, wherein->
Is part C ij Number of degradation faults sigma lk The degree of random dependence of the multiple degenerate faults is measured as a covariance matrix.
Preferably, in the component life model constructing step, the degradation life model is corrected based on random dependence between the functional failure and the degradation failure in such a manner that occurrence of the functional failure reduces the mean value of failure distribution time of the degradation failure in a certain probability and in a certain proportion while increasing the variance thereof
Another aspect of the present invention provides a multi-stage maintenance decision modeling apparatus for an intelligent manufacturing line including m devices E i I=1,..m, each device E i Having n i Component C ij ，j＝1，...，n i The apparatus comprises:
failure time distribution obtaining module: by means of part C ij Historical fault data of (a)Obtaining part C ij A failure time distribution of functional failures and a failure time distribution of degradation failures;
component life model building module based on component C ij Time distribution of all functional failures of building component C ij Functional life model of (2)
According to part C ij Is used to construct component C ij Is>
The equipment availability model building module is used for building a model according to the component C ij Functional life model of (2)
Build equipment E i Functional availability model A i (t) according to part C ij Is>
Build equipment E i Performance availability model B of (2) i (t) and Performance availability penalty model AB i (t), wherein t is time;
production line benefit model construction module utilizing equipment E i Functional availability model A i (t) calculating the loss of the production line due to the functional failure; using apparatus E i Performance availability model B of (2) i (t) and Performance availability penalty model AB i (t) calculating the loss of the production line caused by the degradation fault, and constructing a production line benefit model according to the loss of the production line caused by the functional fault and the degradation fault;
and the maintenance decision obtaining module is used for carrying out optimization solution on the production line benefit model according to constraint conditions required by the production line to obtain maintenance decision for maximizing the production line benefit.
A further aspect of the invention provides a computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method described above when executing the computer program.
A further aspect of the invention provides a computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the method described above.
According to the multistage maintenance decision modeling method and device, the computer equipment and the computer readable storage medium of the intelligent manufacturing production line, a multistage maintenance model of the intelligent manufacturing production line can be constructed, analysis and formulation of a maintenance scheme of the intelligent manufacturing production line are effectively supported, unexpected shutdown is reduced, and production line benefits are maximized.
Drawings
For a clearer description of the technical solutions of the present invention, the following description will be given with reference to the attached drawings used in the description of the embodiments of the present invention, it being obvious that the attached drawings in the following description are only some embodiments of the present invention, and that other attached drawings can be obtained by those skilled in the art without the need of inventive effort: FIG. 1 is a flow chart of a multi-level maintenance decision modeling method of an intelligent manufacturing line according to an embodiment of the present invention.
FIG. 2 is a schematic illustration of a line benefit model according to one embodiment of the present invention.
FIG. 3 is a block diagram of a multistage maintenance decision modeling apparatus for an intelligent manufacturing line according to an embodiment of the present invention.
Fig. 4 is a block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention provides a multistage maintenance decision modeling method for an intelligent manufacturing production line. An intelligent manufacturing line typically includes multiple devices, with different devices having multiple critical components, and different components having multiple failure modes. Taking a small production line as an example, the production line comprises 1 robot, 4 machine tools and other equipment, wherein the robot is provided with key components such as a sliding guide rail, a servo motor, a speed reducer and the like, and different components have various fault modes, the influences of the different components are different, for example, the servo motor has an abnormal encoder caused by mechanical impact and cannot work; there are turn-to-turn insulation shorts, bearing wear, etc., which result in reduced system performance, but still function.
For convenience of description, the following is assumed:
an intelligent manufacturing line comprises m devices, E i It is indicated that i=1, m;
each device E i Having n i Parts, parts C ij The expression j=1,.. i ；
Each part C ij With p ij A fault, wherein the loss of function fault is common
And is denoted as->
Performance degradation fault co->
And is denoted as->
Satisfy->
Wherein, the failure of the function is abbreviated as the function failure, once the failure occurs, the component can not work, the production line is stopped, such as mechanical fracture, structural jam, electrical short circuit, etc., and the maintenance or replacement is needed; the performance degradation fault, namely degradation fault for short, can still work once the component occurs, but the working quality is reduced, so that the defective product rate of the production line is continuously increased, and the shutdown maintenance is needed when the production line reaches the threshold line.
Unlike the prior art based on equipment-level fault prediction and maintenance decision, the multi-level maintenance decision modeling method of the intelligent manufacturing production line of the embodiment of the invention considers multiple faults and random dependencies thereof, multiple components and structural dependencies thereof, multiple devices and economic dependencies thereof, integrates multi-level dependency modeling according to a modularized thought, analyzes and builds a primary fault distribution model, a secondary component life model, a tertiary device availability model and a four-level production line benefit model from bottom to top, and provides technical support for enterprise building maintenance decision models.
In order to apply the multistage maintenance decision modeling method of the embodiment of the invention, the production line, equipment, components and fault mode decomposition can be carried out from top to bottom by means of FMEA (Failure Mode and Effect Analysis, failure mode and impact analysis), FTA (Fault Tree Analysis ) and the like; for a key fault mode (hereinafter also referred to as fault), the key fault mode is classified into a degradation fault and a functional fault, wherein the degradation fault process and degree can be directly or indirectly discovered through sensing monitoring or maintenance detection of equipment; faults that the process cannot "discover" are classified as functional faults. For example: the servo motor turn-to-turn insulation short circuit, bearing abrasion and the like of the robot are all degradation faults in mechanism, but the current/vibration sensor needs to be installed on line, or the maintenance process can be discovered by testing with a special off-line device regularly, the equipment is provided with on-line monitoring or regular maintenance testing, and the equipment is classified as the degradation faults, otherwise, the equipment is classified as the functional faults.
FIG. 1 is a flow chart of a multi-level maintenance decision modeling method of an intelligent manufacturing line according to an embodiment of the present invention. As shown in fig. 1, the multistage maintenance decision modeling method of the intelligent manufacturing line according to the embodiment of the present invention includes steps S1 to S5.
Step S1: failure time distribution obtaining step
In this step, component C is used ij Obtain part C ij A failure time distribution of functional failures and a failure time distribution of degradation failures.
In one embodiment, the historical fault data of the components such as on-line monitoring or maintenance periodic test of the equipment is utilized to obtain a 'fault distribution model' of key faults, namely fault time distribution, through a life prediction algorithm, and a fault time distribution function PDF of the functional faults is constructed through random process modeling of the occurrence time of the similar faults of the historical faults 1 The method comprises the steps of carrying out a first treatment on the surface of the For degradation faults, a degradation model is built by adopting a method based on mechanism or data driving, and a fault time distribution function PDF of the degradation faults is obtained 2 . By using the fault distribution model, the fault probability at different moments can be obtained, the fault results (such as severity) are integrated, and the corresponding fault risk is calculated.
Step S2: component lifetime model construction step
In this step, according to part C ij Time distribution of all functional failures of building component C ij Functional life model based on random dependence of multifunctional faults
According to part C ij Is used to construct component C ij Is based on the random dependence of multiple degradation faults>
In one embodiment, a "component life model" based on multiple-fault stochastic dependencies is built for critical components (e.g., functional components of the robot such as the slide rail, decelerator, servo motor, etc.).
In the construction of a component life model, first, random dependencies among a plurality of functional failures are considered, for the functional failures
Is part C ij Is obtained by a failure time distribution obtaining step S1
Is->
Is subjected to Monte Carlo sampling respectively
If the time of failure distribution for each functional failure is sampled z times, typically z > 10000. Taking the w-th sample x of each distribution ijk，w Considering the competing failure relationship of the functional failures (i.e., any functional failure occurring, equipment shutdown), the earliest occurring (minimum sampling time) failure
Composition statistics X ij ＝min{x ij，1 ，...，x ij，w ，....，x ij，z Fitting with a suitable distribution to obtain a model of the functional lifetime of the component +.>
In the component life model construction, random dependencies between multiple degradation faults are secondarily considered. Considering that performance degradation is not a single degradation, often an overall degradation, the degradation process of the same component most of the time exhibits a correlation (mostly a positive correlation). For example, for a servo motor of a robot, the more the motor grease is lost, the more the bearings wear outThe vibration of the motor is increased, the efficiency is reduced, the heat is increased due to the downloading of the bearing performance, the temperature is increased along with the rising, other deformation and insulation problems are caused, and the vibration and temperature rise monitoring quantities are positive correlation degradation faults. Since the more serious the degradation is, the higher the fault risk is, and the influence relation of degradation amount is described by fault probability, two or more degradation faults which are mutually influenced can be constructed, and the relevance is measured by covariance matrix or correlation coefficient and the like. In one example, for 2 degenerate faults that interact
And->
Wherein->
Is part C ij Is obtained by step S1>
And->
Failure time distribution->
And->
Representing its joint distribution, sigma lk The degree of random dependence is measured as a covariance matrix. And analogizing more than 2 fault conditions, and constructing a part degradation life model.
Random dependencies between functional and degradation faults are further considered in the component life model construction. Work (work)The occurrence of a fault aggravates the risk of occurrence of a dependent degenerate fault with a certain probability. For example, power supply abnormality of the servo motor occurs randomly, and belongs to functional failure, and the occurrence of power supply abnormality risks degradation failure such as insulation. Regarding the random dependence of the functional failure and the degradation failure, the distribution type (such as normal distribution) of the degradation failure is not changed by considering the functional failure, but the occurrence of the functional failure can reduce the mean value of the degradation failure time in a certain proportion with a certain probability while increasing the variance thereof, thereby obtaining a corrected degradation lifetime model
Step S3: device availability model building step
In this step, according to part C ij Functional life model of (2)
Build equipment E i Is based on the functional availability model A of the multi-component functional structure dependence i (t) according to part C ij Is>
Build equipment E i Performance availability model B based on multi-component performance structure dependency i (t) and Performance availability penalty model AB i (t)。
In one embodiment, a three-level equipment availability model based on multi-component structural dependencies is built for critical equipment (e.g., robots and numerically controlled machine tools for small production lines).
Specifically, in the device availability model construction, at time t:
the functional life model of each component is obtained, for example, by the method of sampling and taking small Monte Carlo
Functional model integrated into a single device->
The expected functional failure duration of the computing device at time t is
The device functional uptime is expected to be Γ (t) =t- α i (t) device function availability model
Within 0- Γ (t), each component C is calculated based on the degradation lifetime model of each component ij Expected degradation failure duration within Γ (t)>
Equipment E i Is of the performance failure time of
Device Performance availability model>
At Γ (t) - β i Between (t) and Γ (t), the equipment is operated with diseases, and omega is introduced in consideration of the influence of the performance of the components on the production quality of the equipment ij As part C ij The more severe the degradation, the greater the impact on the quality of production, ω ij Is an increasing function of t, with +.>
Is increased by an increase in (a); thus, as time progresses, the first component reaches a degraded life, introducing a first ω ij If not maintained, the second part is degraded and out of tolerance, and a second omega is introduced ij The influence accumulation (such as linear accumulation) of multiple components and so on to obtain a device performance availability penalty model and a device performance availability penalty model AB i (t) is a piecewise function:
here, beta i(k) (k) in (t) represents
Order statistics of (a), i.e. k, k of the order from big to small>
Namely beta i(1) (t)。
According to apparatus E i Performance availability penalty model AB of (a) i (t) obtaining the apparatus E i Penalty factor at some time t.
Step S4: production line benefit model construction step
In this step, device E is utilized i Functional availability model A i (t) calculating the loss of the production line due to the functional failure; using apparatus E i Performance availability model B of (2) i (t) and Performance availability penalty model AB i And (t) calculating the loss of the production line due to the degradation fault, and constructing a production line benefit model based on multi-equipment economic dependence according to the loss of the production line due to the functional fault and the degradation fault.
In the production line benefit model construction step, a model A is constructed according to the function availability i (t) and Performance availability model B i (t) obtaining expected failure time points according to the serial-parallel connection relation among devices and a performance availability penalty model AB i (t) calculating the loss in the time period between each expected failure time point.
In the intelligent manufacturing production line, the connection relation among the devices is different, and the production line loss is different due to the failure of the devices. For example, in the foregoing example of a small-sized production line, the production line includes 1 robot and 4 machine tools 1-4, the robot and 4 machine tools are in serial connection, the 4 machine tools are connected in series and then in parallel, for example, the machine tool 1 is connected in series with the machine tool 2, the machine tool 3 is connected in series with the machine tool 4, and the two serial branches are connected in parallel. Under the connection relation, if the robot has a functional failure, the whole line production is stopped, and the availability is smaller than the effective working time of all the equipment of the robot and is the same as that of the robot; if the machine tool 1 is stopped, the machine tool 2 is stopped, and the productivity of the production line is halved. And carrying out production line capacity analysis through the availability of each device and the serial-parallel connection relation among the devices.
FIG. 2 is a schematic illustration of a line benefit model according to one embodiment of the present invention. As shown in FIG. 2, all the equipment is normal at the beginning, and the availability and the productivity are 100%; at time t1, the degradation fault of the machine tool 2 causes the productivity of the machine tool 2 to be reduced to 100% -AB 2 ，AB 2 Penalty factors for machine tool 2 at that time; at time t2, if the function of the machine tool 1 fails, the capacity of the machine tool 1 is 0, and the shutdown capacity of the machine tool 2 is also 0% due to the serial connection between the machine tool 1 and the machine tool 2; the capacity of the robot is halved; by t3 and t4, respectively, the machine tool 3 and the machine tool 4 have degradation faults, the productivity of each machine tool 3 and the machine tool 4 is reduced, and the penalty factors of the branches formed by the machine tool 3 and the machine tool 4 in series are accumulated. And finally, the function of the robot is failed, and the whole line production is stopped. Thereby, the device function availability and the performance availability in each time interval are obtained. In the maintenance decision optimizing process, t1, t2, t3, t4, t5 and the like are based on the function availability model A i (t) and Performance availability model B i (t) the expected failure time point obtained.
In the production line benefit model construction step, equipment E is utilized i Functional availability model A i (t) calculating yield loss for each expected failure period, the yield loss being the product of line availability and rated production rate X for a period of time, at times t2-t5 in FIG. 3, yield loss CA due to a functional failure 2-5 50% > (t 5-t 2) × X, 100% loss after t 5; using apparatus E i Performance availability model B i (t) and Performance availability penalty model AB i (t) calculating loss CB due to production of defective products 1-2 ＝0.5X*AB 2 0.5X represents that the parallel branch is responsible for only half the capacity; same reason CB 4-5 ＝0.5X*(AB 3 +AB 4 )。
In the production line benefit, firstly, the economic dependence of multiple devices can be obtained statistically, namely, each maintenance will generate oneFixed cost C 0 The fixed cost does not change with the number of maintenance objects, and depends on the fixed parts such as personnel/scheduling and the like, and the shutdown loss waiting for maintenance and the like. The waiting time of the subsequent maintenance is generally longer than that of the predicted maintenance, so the fixed cost of the subsequent maintenance is far higher than that of the preventive maintenance.
In the benefit of the production line, the production loss C under the maintenance of multiple equipment combinations is considered 1 ，C 1 Maximum time for parallel repair of multiple devices; spare part and maintenance costs C considering replacement of specific parts or maintenance of specific failure modes 2 。
Line benefit t X under normal operation, deducting the loss and fixed cost C due to functional and degradation faults 0 Loss of production C 1 And maintenance cost C 2 And the like, and the production line benefit is obtained.
Step S5: maintenance decision obtaining step
In the step, according to the constraint condition of the production line requirement, the production line benefit model is optimized and solved, and the maintenance decision for maximizing the production line benefit is obtained.
Specifically, on the basis of constructing a production line benefit model, adding relevant constraints according to production line requirements such as safety production requirements such as major functional faults (for example, fatal faults are always smaller than a specified value), quality control requirements of defective products (for example, defective products at any time are smaller than the specified value), monthly yield requirements (for example, basic yield benefits are maintained every month), key equipment availability requirements (the key equipment functional availability is required to be larger than the specified value) and the like; according to the production line scheduling conditions, a proper time period is selected, maintenance time, maintenance faults or maintenance components are taken as optimization variables, and an optimization algorithm such as dynamic solution is utilized to carry out optimization solution on a production line benefit model, so that maintenance time and maintenance decisions such as maintenance objects for maximizing production line benefits are obtained under constraint conditions.
In summary, the multistage maintenance decision modeling method of the intelligent manufacturing production line can construct a multistage maintenance model of the intelligent manufacturing production line, provide technical support for active operation and maintenance of the production line in an intelligent manufacturing environment, reduce unexpected shutdown and maximize production line benefits.
The embodiment of the invention also provides a multistage maintenance decision modeling device of the intelligent manufacturing production line. FIG. 3 is a block diagram of a multistage maintenance decision modeling apparatus for an intelligent manufacturing line according to an embodiment of the present invention. As shown in fig. 3, the multistage maintenance decision modeling apparatus of the intelligent manufacturing line of the present embodiment includes:
the failure time distribution obtaining module 101: by means of part C ij Obtain part C ij A failure time distribution of functional failures and a failure time distribution of degradation failures;
component life model construction module 102, based on component C ij Time distribution of all functional failures of building component C ij Functional life model based on random dependence of multifunctional faults
According to part C ij Is used to construct component C ij Is based on the degradation life model of random dependence of multiple degradation faults
Device availability model building module 103, based on component C ij Functional life model of (2)
Build equipment E i Is based on the functional availability model A of the multi-component functional structure dependence i (t) according to part C ij Is>
Build equipment E i Performance availability model B based on multi-component performance structure dependency i (t) and Performance availability penalty model AB i (t), wherein t is time;
production line benefit model construction module 104, utilizing equipment E i Functional availability model A i (t) calculating the loss of the production line due to the functional failure; using apparatus E i Performance availability model B of (2) i (t) and Performance availability penalty model AB i (t) calculating the loss of the production line caused by the degradation fault, and constructing a production line benefit model based on multi-equipment economic dependence according to the loss of the production line caused by the functional fault and the degradation fault;
and the maintenance decision obtaining module 105 is used for carrying out optimization solution on the production line benefit model according to constraint conditions of the production line requirement to obtain maintenance decision for maximizing the production line benefit.
Specific examples of the multi-stage maintenance decision modeling apparatus for an intelligent manufacturing line of the present embodiment may be referred to above for limitation of the multi-stage maintenance decision modeling method for an intelligent manufacturing line, and will not be described herein. The modules in the multistage maintenance decision modeling device of the intelligent manufacturing line can be fully or partially realized by software, hardware and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Embodiments of the present invention also provide a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 4. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store operating parameter data for each of the frames. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements the steps of the multi-level maintenance decision modeling method of the intelligent manufacturing line of the present embodiment.
Those skilled in the art will appreciate that the structures shown in FIG. 4 are block diagrams only and do not constitute a limitation of the computer device on which the present aspects apply, and that a particular computer device may include more or less components than those shown, or may combine some of the components, or have a different arrangement of components.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the multistage maintenance decision modeling method of the intelligent manufacturing line of the embodiment of the invention.
While certain exemplary embodiments of the present invention have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that modifications may be made to the described embodiments in various different ways without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive of the scope of the invention, which is defined by the appended claims.
Claims (10)
1. Multistage maintenance decision modeling method of intelligent manufacturing production line, wherein the intelligent manufacturing production line comprises m devices E i I=1,..m, each device E i has n i parts C ij ，j＝1，...，n i Characterized in that the method comprises:
failure time distribution obtaining step: by means of part C ij Obtain part C ij A failure time distribution of functional failures and a failure time distribution of degradation failures;
a component life model construction step, based on component C ij Time distribution of all functional failures of building component C ij Functional life model based on random dependence of multifunctional faults
According to part C ij Is used to construct component C ij Is based on the random dependence of multiple degradation faults>
A device availability model construction step, based on component C ij Functional life model of (2)
Build equipment E i Is based on the functional availability model A of the multi-component functional structure dependence i (t) according to part C ij Is>
Build equipment E i Performance availability model B based on multi-component performance structure dependency i (t) and Performance availability penalty model AB i (t), wherein t is time;
production line benefit model construction step, utilizing equipment E i Functional availability model A i (t) calculating the loss of the production line due to the functional failure; using apparatus E i Performance availability model B of (2) i (t) and Performance availability penalty model AB i (t) calculating the loss of the production line caused by the degradation fault, and constructing a production line benefit model based on multi-equipment economic dependence according to the loss of the production line caused by the functional fault and the degradation fault; a maintenance decision obtaining step, according to the constraint condition of the production line requirement, carrying out optimization solution on the production line benefit model to obtain a maintenance decision for maximizing the production line benefit,
in the equipment availability model construction step, part C ij Functional life model of (2)
Fused into a designStandby E i Functional model of (2)>
The expected functional failure time of the computing device at time t +.>
Obtaining device E i Functional availability of->
2. The method according to claim 1, wherein in the equipment availability model construction step, the calculating means C ij Expected degradation fault duration within Γ (t)
Obtaining device E i Performance failure time of (a)
Thereby obtaining the apparatus E i Performance availability model of->
Wherein Γ (t) is device E i Is used for the expected functional normal time of the (c),
Γ(t)＝t-α i (t)。
3. the method of claim 2, wherein in the device availability model construction step, the device E is constructed as follows i Performance availability penalty model AB of (a) i (t)：
Wherein omega ij Is part C ij Is to device E i An influencing factor for the production quality of (a).
4. A method according to any one of claims 1-3, characterized in that in the line benefit model building step, the model a is based on the functional availability i (t) and Performance availability model B i (t) obtaining expected failure time points according to the serial-parallel connection relation among devices and a performance availability penalty model AB i (t) calculating the loss in the time period between each expected failure time point.
5. A method according to any one of claims 1-3, wherein in the component life model building step, the time-to-failure distribution of all functional failures is separately Monte Carlo sampled, and the earliest occurring failure composition statistic in the w-th sample of each distribution is taken
X ij ＝min{x ij，1 ，...，X ij，w ，....，x ij，z Fitting the statistics to obtain a functional life model
Wherein z is Monte Carlo sampling times, and z is more than 10000.
6. A method according to any one of claims 1 to 3, wherein in the component lifetime model construction step, a multivariate joint distribution function is constructed for a plurality of degradation faults that interact with each other
As a model of degradation life, wherein->
Is part C ij Number of degradation faults sigma lk The degree of random dependence of the multiple degenerate faults is measured as a covariance matrix.
7. A method according to any one of claims 1 to 3, wherein in the component life model constructing step, the degradation life model is corrected based on the random dependence between the functional failure and the degradation failure in such a manner that occurrence of the functional failure reduces the mean value of the failure distribution time of the degradation failure in a certain probability in a certain proportion while increasing the variance thereof
8. Multistage maintenance decision modeling device of intelligent manufacturing production line, the intelligent manufacturing production line comprises m devices E i I=1,..m, each device E i Having n i Component C ij ，j＝1，...，n i Characterized in that the device comprises:
failure time distribution obtaining module: by means of part C ij Obtain part C ij A failure time distribution of functional failures and a failure time distribution of degradation failures;
component life model building module based on component C ij Time distribution of all functional failures of building component C ij Functional life model based on random dependence of multifunctional faults
According to part C ij Is used to construct component C ij Is based on the random dependence of multiple degradation faults>
Equipment availability model construction modelBlock according to part C ij Functional life model of (2)
Build equipment E i Is based on the functional availability model A of the multi-component functional structure dependence i (t) according to part C ij Is>
Build equipment E i Performance availability model B based on multi-component performance structure dependency i (t) and Performance availability penalty model AB i (t), wherein t is time;
production line benefit model construction module utilizing equipment E i Functional availability model A i (t) calculating the loss of the production line due to the functional failure; using apparatus E i Performance availability model B of (2) i (t) and Performance availability penalty model AB i (t) calculating the loss of the production line caused by the degradation fault, and constructing a production line benefit model based on multi-equipment economic dependence according to the loss of the production line caused by the functional fault and the degradation fault; the maintenance decision obtaining module is used for carrying out optimization solution on the production line benefit model according to the constraint condition of the production line requirement to obtain the maintenance decision for maximizing the production line benefit,
the equipment availability model building module builds part C ij Functional life model of (2)
Fused into device E i Functional model of (2)>
The expected functional failure time of the computing device at time t +.>
Obtaining device E i Functional availability of->
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1-7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310035776.6A CN115719013B (en) | 2023-01-10 | 2023-01-10 | Multistage maintenance decision modeling method and device for intelligent manufacturing production line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310035776.6A CN115719013B (en) | 2023-01-10 | 2023-01-10 | Multistage maintenance decision modeling method and device for intelligent manufacturing production line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115719013A CN115719013A (en) | 2023-02-28 |
| CN115719013B true CN115719013B (en) | 2023-04-25 |
Family
ID=85257977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310035776.6A Active CN115719013B (en) | 2023-01-10 | 2023-01-10 | Multistage maintenance decision modeling method and device for intelligent manufacturing production line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115719013B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102495549A (en) * | 2011-11-22 | 2012-06-13 | 中联重科股份有限公司 | Remote maintenance decision system of engineering machinery and method thereof |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103838619A (en) * | 2014-03-17 | 2014-06-04 | 宋佰超 | Method for determining fault frequency of repairable system |
| CN105825279A (en) * | 2016-05-27 | 2016-08-03 | 太原科技大学 | Multi-component system group maintenance decision method and multi-component system group maintenance decision device based on prediction |
| CN106600072A (en) * | 2016-12-21 | 2017-04-26 | 中国航空工业集团公司雷华电子技术研究所 | Maintenance decision optimization algorithm based on failure prediction |
| CN109284557B (en) * | 2018-09-29 | 2020-09-18 | 北京航空航天大学 | Preventive maintenance method of anti-packet boosting assembly based on fault analysis |
| CN111222259B (en) * | 2020-03-04 | 2022-11-11 | 广西大学 | Multi-component preventive maintenance decision optimization model for metro vehicle bogie |
| US20220136405A1 (en) * | 2020-10-29 | 2022-05-05 | General Electric Company | Systems and methods of servicing equipment |
| CN113435613B (en) * | 2021-08-26 | 2021-12-31 | 北京航空航天大学 | Opportunistic maintenance decision-making method for multiple maintenance events |
| CN113705106A (en) * | 2021-09-01 | 2021-11-26 | 中国科学院长春光学精密机械与物理研究所 | Design method for life cycle maintenance scheme of complex equipment |
-
2023
- 2023-01-10 CN CN202310035776.6A patent/CN115719013B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102495549A (en) * | 2011-11-22 | 2012-06-13 | 中联重科股份有限公司 | Remote maintenance decision system of engineering machinery and method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115719013A (en) | 2023-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Han et al. | Remaining useful life prediction and predictive maintenance strategies for multi-state manufacturing systems considering functional dependence | |
| US20210288493A1 (en) | Optimization of power generation from power sources using fault prediction based on intelligently tuned machine learning power management | |
| Xia et al. | Dynamic maintenance decision-making for series–parallel manufacturing system based on MAM–MTW methodology | |
| Ding et al. | Opportunistic maintenance for wind farms considering multi-level imperfect maintenance thresholds | |
| Yan et al. | Joint maintenance and spare parts inventory optimization for multi-unit systems considering imperfect maintenance actions | |
| US9218233B2 (en) | Systems and methods for control reliability operations | |
| Li et al. | A review of condition-based maintenance: Its prognostic and operational aspects | |
| US20140032470A1 (en) | Systems and methods for control reliability operations | |
| CN111581889B (en) | Fault prediction method, system and equipment for heat supply equipment component | |
| Dong et al. | Prognostic and health management for adaptive manufacturing systems with online sensors and flexible structures | |
| Zhou et al. | Bottleneck-based opportunistic maintenance model for series production systems | |
| Vu et al. | A study on the impacts of maintenance duration on dynamic grouping modeling and optimization of multicomponent systems | |
| Abbasi et al. | Development of predictive maintenance interface using multiple linear regression | |
| Eryilmaz et al. | The number of failed components in series–parallel system and its application to optimal design | |
| Yang et al. | Mission reliability–centered maintenance approach based on quality stochastic flow network for multistate manufacturing systems | |
| Nguyen et al. | Optimization of preventive maintenance scheduling in processing plants | |
| CN115719013B (en) | Multistage maintenance decision modeling method and device for intelligent manufacturing production line | |
| Duan et al. | Adaptive maintenance scheme for degrading devices with dynamic conditions and random failures | |
| CN116384876A (en) | Spare part dynamic inventory-production control method, system and medium based on wiener process | |
| CN112257880B (en) | Maintenance decision method and system for k/n load sharing system | |
| Xue et al. | A data-driven method to predict future bottlenecks in a remanufacturing system with multi-variant uncertainties | |
| Gan et al. | Maintenance Optimization for a Production System Subject to Shocks Considering a Buffer Inventory and Production Defects | |
| Da Silva | Maintenance policy costs considering imperfect repairs | |
| Geiss et al. | Reliability-centered asset management of wind turbines—A holistic approach for a sustainable and cost-optimal maintenance strategy | |
| Li et al. | Considering machine health condition in jointly optimizing predictive maintenance policy and X-bar control chart |
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 |