CN115879248A - Full life cycle management method and system suitable for vacuum pump - Google Patents
Full life cycle management method and system suitable for vacuum pump Download PDFInfo
- Publication number
- CN115879248A CN115879248A CN202310194933.8A CN202310194933A CN115879248A CN 115879248 A CN115879248 A CN 115879248A CN 202310194933 A CN202310194933 A CN 202310194933A CN 115879248 A CN115879248 A CN 115879248A
- Authority
- CN
- China
- Prior art keywords
- data
- vacuum pump
- target
- life
- life prediction
- 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.)
- Granted
Links
- 238000007726 management method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000007781 pre-processing Methods 0.000 claims abstract description 25
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000007621 cluster analysis Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 230000003750 conditioning effect Effects 0.000 claims description 2
- 238000006731 degradation reaction Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 20
- 230000006870 function Effects 0.000 description 15
- 238000003860 storage Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000011176 pooling Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000013049 sediment Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Compressors, Vaccum Pumps And Other Relevant Systems (AREA)
Abstract
The application relates to a full life cycle management method and system suitable for a vacuum pump, belonging to the technical field of product full life cycle management, and the method comprises the following steps: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data; constructing a vacuum pump service life prediction model based on the target data; calculating to obtain a life decay curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model; and selecting a processing mode of the target vacuum pump according to the life attenuation curve and processing the processing mode to realize the full life cycle management of the target vacuum pump. According to the method and the device, the service life of the target vacuum pump is predicted, so that the performance degradation process of the vacuum pump can be accurately predicted, the full life cycle of the applied vacuum pump is effectively managed, and the use reliability, safety and management efficiency of the vacuum pump are improved.
Description
Technical Field
The application relates to the technical field of product full-life-cycle management, in particular to a full-life-cycle management method and system suitable for a vacuum pump.
Background
In a system with a vacuum pump, the vacuum pump may age and be polluted by sediments during the operation process of the full life cycle, thereby causing performance and efficiency to be reduced and causing abnormal conditions, the prior art usually determines the abnormal conditions and replacement cycles of the vacuum pump through the experience of technical personnel, however, the service life of the vacuum pump is different according to different use environments of the vacuum pump, and the conventional method is difficult to accurately determine the maintenance and replacement cycles of the vacuum pump, thereby causing the use reliability and safety of the vacuum pump to be low, and therefore, a method for managing the full operation life cycle of the vacuum pump by using related dynamic information of the vacuum pump is urgently needed.
Disclosure of Invention
In view of the above, it is necessary to provide a method, a system, a computer device and a storage medium for managing a full life cycle of a vacuum pump, which can accurately determine the performance degradation problem occurring during the operation of the vacuum pump, thereby facilitating maintenance and management.
In one aspect, there is provided a full lifecycle management method for a vacuum pump, the method comprising:
step A: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data;
and B, step B: constructing a vacuum pump service life prediction model based on the target data;
and C: calculating to obtain a life attenuation curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model;
step D: and selecting a processing mode of the target vacuum pump according to the life decay curve and processing the target vacuum pump to realize the full life cycle management of the target vacuum pump.
In one embodiment, the method further comprises the following steps: the first data comprises initial state data, application environment data, running state data and loss data of the vacuum pump, and the preprocessing of the first data to obtain target data comprises the following steps: performing data cleaning on the first data; screening the cleaned first data according to a preset data volume to obtain second data; classifying and sequencing the second data based on a cluster analysis strategy to obtain 4 data sets of different categories, namely a first category, a second category, a third category and a fourth category; and reading and fitting the data set of the target category by using a data adjusting mechanism to obtain the target data.
In one embodiment, the method further comprises the following steps: the reading and fitting of the data set of the target category by using the data conditioning mechanism to obtain the target data comprises: normalizing the read data set of the target category, wherein the calculation formula is as follows:
wherein ,
normalized coefficient representing the mth data attribute, <' > or>
A custom coefficient representing the nth data,
an mth data attribute, representing an nth data, is asserted>
A weight representing an mth data attribute>
Which is indicative of the number of data attributes,
normalized value representing an m-th data attribute of an nth data>
，/>
Representing the amount of data;
fitting the normalized data by using a fitting function, wherein the fitting function is as follows:
wherein ,
represents the fitted function value, <' > in >>
A normalized value representing the first, second, third and fourth class data sets, respectively, i representing an iteration coefficient, ->
Fitting coefficients representing a jth category data set>
Characteristic parameters representing a jth category data set;
and defining the data value after the fitting processing as the target data.
In one embodiment, the method further comprises the following steps: the construction process of the vacuum pump life prediction model comprises the following steps: pre-constructing a first vacuum pump service life prediction model based on a deep neural network; training the first vacuum pump life prediction model based on the target data obtained by a plurality of vacuum pumps; and when the precision of the first vacuum pump life prediction model reaches a preset standard, outputting a second vacuum pump life prediction model obtained after training is finished, namely the final vacuum pump life prediction model.
In one embodiment, the method further comprises the following steps: the expression of the vacuum pump life prediction model comprises:
wherein ,
indicates the predicted value of the life at time t +1>
Represents the difference value of the target data between time t and time t +1, and->
Represents an average life value, is>
Represents a loss factor at time t +1>
Represents the loss coefficient at time t, k represents the iteration coefficient, and->
Indicating an index.
In one embodiment, the method further comprises the following steps: the calculating and obtaining the life decay curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model comprises the following steps: inputting the target data of the target vacuum pump corresponding to each time point obtained by calculation into the vacuum pump life prediction model to obtain a first life prediction value; segmenting a plurality of time points according to a preset interval, and solving the average value of the first life prediction values corresponding to each segment to obtain a second life prediction value; and forming a one-to-one mapping relation between the second life prediction value and the middle time point of the segmented interval, and connecting the second life prediction values corresponding to the middle time points to generate a life decay curve.
In one embodiment, the method further comprises the following steps: the selecting and processing the processing mode of the target vacuum pump according to the life decay curve comprises the following steps: calculating the slope of the second life prediction value corresponding to two adjacent intermediate time points based on the life decay curve; judging the processing mode of the target vacuum pump according to the slope: when the slope is greater than a first preset value and the service life is less than a second preset value, judging that the target vacuum pump has a fault and needs to be overhauled; and when the slope is greater than a first preset value and the service life is greater than or equal to a second preset value, judging that the target vacuum pump needs to be scrapped.
In another aspect, there is provided a full lifecycle management system for a vacuum pump, the system comprising:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring first data of a vacuum pump in a historical database and preprocessing the first data to obtain target data;
the model building module is used for building a vacuum pump service life prediction model based on the target data;
the calculating module is used for calculating and obtaining a life attenuation curve of the target vacuum pump in a plurality of time periods by utilizing the vacuum pump life prediction model;
and the selection module is used for selecting and processing the processing mode of the target vacuum pump according to the life decay curve so as to realize the full life cycle management of the target vacuum pump.
In another aspect, a computer device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the following steps when executing the computer program:
step A: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data;
and B, step B: constructing a vacuum pump service life prediction model based on the target data;
step C: calculating to obtain a life attenuation curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model;
step D: and selecting a processing mode of the target vacuum pump according to the life attenuation curve and processing the processing mode to realize the full life cycle management of the target vacuum pump.
In yet another aspect, a computer-readable storage medium is provided, having stored thereon a computer program which, when executed by a processor, performs the steps of:
step A: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data;
and B: constructing a vacuum pump service life prediction model based on the target data;
and C: calculating to obtain a life decay curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model;
step D: and selecting a processing mode of the target vacuum pump according to the life decay curve and processing the target vacuum pump to realize the full life cycle management of the target vacuum pump.
The above full life cycle management method, system, computer device and storage medium for a vacuum pump, the method comprising: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data; constructing a vacuum pump life prediction model based on the target data; calculating to obtain a life decay curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model; according to the service life attenuation curve, a processing mode of the target vacuum pump is selected and processed, and the full life cycle management of the target vacuum pump is achieved.
Drawings
FIG. 1 is a diagram of an exemplary embodiment of a full lifecycle management method for vacuum pumps;
FIG. 2 is a schematic flow chart diagram illustrating a method for full lifecycle management for vacuum pumps, according to one embodiment;
FIG. 3 is a block diagram of a full lifecycle management system suitable for use with a vacuum pump, according to one embodiment;
FIG. 4 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood that throughout the description of this application, unless the context clearly requires otherwise, the words "comprise", "comprising", and the like, are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
It will be further understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present application, the meaning of "a plurality" is two or more unless otherwise specified.
It should be noted that the terms "S1", "S2", etc. are used for describing steps only, do not refer to an order or sequence meaning, and do not limit the present application, and are used for describing the method of the present application only and should not be understood as indicating the sequence of steps. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present application.
The full-life-cycle management method suitable for the vacuum pump can be applied to the application environment shown in fig. 1. The terminal 102 communicates with a data processing platform disposed on the server 104 through a network, wherein the terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a full-life-cycle management method for a vacuum pump is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:
s1: the method comprises the steps of obtaining first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data.
It should be noted that the first data includes initial state data, application environment data, operation state data and loss data of the vacuum pump, for example, the initial state data may include one or more of design prediction quality, model, manufacturing quality, acceptance quality, manufacturer production defect, and the like, the application environment data may include one or more of ambient temperature, humidity, climate characteristics, and the like, the operation state data includes one or more of current value, pressure value, number of usage times, and the like, the loss data includes one or more of wear value, number of failures, impact resistance, and the like, the data are subjected to weight assignment based on an expert weighting method, wherein the expert weighting method refers to scoring the target data by using an expert in the field, in this embodiment, scoring is performed on all target data according to the influence degree of the target data on the life value, assigning different weights to different indexes according to the scoring result, and storing the different weights in a historical database;
further, the preprocessing the first data to obtain target data includes:
performing data cleaning on the first data, wherein in the step, in order to process invalid values and missing values, better data are obtained so as to improve the prediction precision of a subsequent model;
screening the cleaned first data according to a preset data volume to obtain second data, wherein the preset data volume can be set according to actual needs;
classifying and sequencing the second data based on a cluster analysis strategy to obtain 4 data sets of different classes, namely a first class, a second class, a third class and a fourth class, wherein the cluster analysis refers to an analysis process of grouping a set of physical or abstract objects into a plurality of classes consisting of similar objects;
reading and fitting a data set of a target category by using a data adjusting mechanism to obtain target data, specifically:
normalizing the read data set of the target category, wherein the calculation formula is as follows:
wherein ,
normalized coefficient representing the mth data attribute, <' > or>
A custom coefficient representing the nth data,
represents the nth dataIs selected based on the mth data attribute of (4), "based on the status of the data attribute in the data store," "based on the status of the data attribute in the data store,">
A weight representing an mth data attribute>
Which is indicative of the number of data attributes,
normalized value representing an m-th data attribute of an nth data>
，/>
Representing the amount of data;
fitting the normalized data by using a fitting function, wherein the fitting function is as follows:
wherein ,
represents the fitted function value, < >>
Normalized values representing a first class, a second class, a third class and a fourth class of data sets, respectively, i represents an iteration coefficient, </or >>
Fitting coefficients representing a jth category data set>
Characteristic parameters representing the jth category data set;
and defining the data value after fitting processing as the target data.
S2: and constructing a vacuum pump service life prediction model based on the target data.
It should be noted that, the process of constructing the vacuum pump life prediction model includes:
the method comprises the following steps of pre-constructing a first vacuum pump life prediction model based on a deep neural network, wherein the deep neural network comprises: the feature extraction network and the attribute prediction network comprise: the system comprises a convolutional layer, a pooling layer, a nonlinear layer and a full-link layer, wherein the convolutional layer extracts new features from input data through linear transformation, the pooling layer can map a plurality of values into one value to reduce a feature space, the nonlinear layer is applied to an activation mechanism of a biological neuron, and the full-link layer is used for associating and assisting the convolutional layer, the pooling layer and the nonlinear layer;
training the first vacuum pump life prediction model based on the target data obtained by a plurality of vacuum pumps;
and when the precision of the first vacuum pump life prediction model reaches a preset standard, preferably, the precision value of the preset standard is 0.97 or more, and outputting a second vacuum pump life prediction model obtained after training is finished, namely the final vacuum pump life prediction model.
The attribute prediction network comprises the vacuum pump service life prediction model and can be described by the following expression:
wherein ,
a predicted value of life time at t +1>
Represents the difference value of the target data between time t and time t +1, and>
represents an average life value>
Represents the loss factor at time t +1, is greater than>
Represents a loss coefficient at time t, k represents an iteration coefficient, and>
indicating an index.
S3: and calculating the life attenuation curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model.
It should be noted that the steps specifically include:
inputting the target data of the target vacuum pump corresponding to each time point obtained by calculation into the vacuum pump service life prediction model to obtain a first service life prediction value;
segmenting a plurality of time points according to a preset interval, and solving an average value of the first life prediction values corresponding to each segment to obtain a second life prediction value, wherein illustratively, the preset interval is 10 minutes from 8 hours to 8 hours, and the time points are defined as 1 minute from 8 hours and 2 minutes (8230) \ 8230; 10 minutes at 8 hours;
and forming a one-to-one mapping relationship between the second life prediction value and the middle time point of the segmented interval, illustratively, when the middle time point of the segmented interval is 8 hours and 5 minutes, connecting the second life prediction values corresponding to the multiple middle time points to generate a life decay curve, and placing the life decay curve in a rectangular coordinate system so as to facilitate subsequent calling.
S4: and selecting a processing mode of the target vacuum pump according to the life decay curve and processing the target vacuum pump to realize the full life cycle management of the target vacuum pump.
It is to be noted that the steps specifically include:
calculating the slope of the second predicted life value corresponding to two adjacent intermediate time points based on the life decay curve, wherein the two adjacent intermediate time points can be 8 hours, 5 minutes and 8 hours, 15 minutes as an example, as described above;
judging the processing mode of the target vacuum pump according to the slope:
when the slope is greater than a first preset value and the service life is less than a second preset value, judging that the target vacuum pump has a fault and needs to be overhauled;
when the slope is larger than a first preset value and the service life is larger than or equal to a second preset value, judging that the target vacuum pump needs to be scrapped;
and when the slope is smaller than the first preset value and the service life is greater than or equal to or smaller than the second preset value, no processing is performed.
In the above full life cycle management method for a vacuum pump, the method includes: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data; constructing a vacuum pump service life prediction model based on the target data; calculating to obtain a life decay curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model; according to the service life attenuation curve, the processing mode of the target vacuum pump is selected and processed, and the full life cycle management of the target vacuum pump is achieved.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 3, there is provided a full lifecycle management system for a vacuum pump, comprising: the device comprises a preprocessing module, a model building module, a calculating module and a selecting module, wherein:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring first data of a vacuum pump in a historical database and preprocessing the first data to obtain target data;
the model construction module is used for constructing a vacuum pump service life prediction model based on the target data;
the calculating module is used for calculating and obtaining a life attenuation curve of the target vacuum pump in a plurality of time periods by utilizing the vacuum pump life prediction model;
and the selection module is used for selecting and processing the processing mode of the target vacuum pump according to the life decay curve so as to realize the full life cycle management of the target vacuum pump.
As a preferred implementation manner, in an embodiment of the present invention, the preprocessing module is specifically configured to:
performing data cleaning on the first data;
screening the cleaned first data according to a preset data volume to obtain second data;
classifying and sequencing the second data based on a cluster analysis strategy to obtain 4 data sets of different categories, namely a first category, a second category, a third category and a fourth category;
reading and fitting a data set of a target category by using a data adjusting mechanism to obtain target data;
the first data includes initial state data, application environment data, operational state data, and wear data of the vacuum pump.
As a preferred implementation manner, in an embodiment of the present invention, the preprocessing module is further specifically configured to:
normalizing the read data set of the target category, wherein the calculation formula is as follows:
wherein ,
normalized coefficient representing the mth data attribute, <' > or>
A custom coefficient representing the nth data,
an mth data attribute, representing an nth data, is asserted>
A weight representing an mth data attribute>
Which represents the number of data attributes,
normalized value representing an m-th data attribute of an nth data>
，/>
Indicating the amount of data;
fitting the normalized data by using a fitting function, wherein the fitting function is as follows:
wherein ,
represents the fitted function value, <' > in >>
Normalized values representing a first class, a second class, a third class and a fourth class of data sets, respectively, i represents an iteration coefficient, </or >>
A fitting coefficient representing the jth class data set, <' > is selected>
Characteristic parameters representing a jth category data set;
and defining the data value after the fitting processing as the target data.
As a preferred implementation manner, in the embodiment of the present invention, the model building module is further specifically configured to:
pre-constructing a first vacuum pump service life prediction model based on a deep neural network;
training the first vacuum pump life prediction model based on the target data obtained by a plurality of vacuum pumps;
when the precision of the first vacuum pump life prediction model reaches a preset standard, outputting a second vacuum pump life prediction model obtained after training is finished, namely the final vacuum pump life prediction model;
wherein the expression of the vacuum pump life prediction model comprises:
wherein ,
indicates the predicted value of the life at time t +1>
Represents the difference value of the target data between time t and time t +1, and->
Represents an average life value, is>
Represents the loss factor at time t +1, is greater than>
Represents the loss coefficient at time t, k represents the iteration coefficient, and->
Indicating an index.
As a preferred implementation manner, in an embodiment of the present invention, the calculation module is specifically configured to:
inputting the target data of the target vacuum pump corresponding to each time point obtained by calculation into the vacuum pump life prediction model to obtain a first life prediction value;
segmenting the multiple time points according to a preset interval, and solving an average value of the first life prediction values corresponding to each segment to obtain a second life prediction value;
and forming a one-to-one mapping relation between the second life prediction value and the middle time point of the segmented interval, and connecting the second life prediction values corresponding to the middle time points to generate a life decay curve.
As a preferred implementation manner, in an embodiment of the present invention, the selection module is specifically configured to:
calculating the slope of the second life prediction value corresponding to two adjacent middle time points based on the life decay curve;
judging the processing mode of the target vacuum pump according to the slope:
when the slope is larger than a first preset value and the service life is smaller than a second preset value, judging that the target vacuum pump has a fault and needs to be overhauled;
and when the slope is greater than a first preset value and the service life is greater than or equal to a second preset value, judging that the target vacuum pump needs to be scrapped.
For specific limitations of the full-life cycle management system suitable for the vacuum pump, reference may be made to the above limitations of the full-life cycle management method suitable for the vacuum pump, which are not described herein again. The various modules described above in the full lifecycle management system for vacuum pumps can be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, a display screen, and an input system 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 comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a full lifecycle management method for a vacuum pump. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s1: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data;
s2: constructing a vacuum pump service life prediction model based on the target data;
s3: calculating to obtain a life decay curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model;
s4: and selecting a processing mode of the target vacuum pump according to the life decay curve and processing the target vacuum pump to realize the full life cycle management of the target vacuum pump.
In one embodiment, the processor when executing the computer program further performs the steps of:
performing data cleaning on the first data;
screening the cleaned first data according to a preset data volume to obtain second data;
classifying and sequencing the second data based on a cluster analysis strategy to obtain 4 data sets of different categories, namely a first category, a second category, a third category and a fourth category;
reading and fitting a data set of a target category by using a data adjusting mechanism to obtain target data;
the first data includes initial state data, application environment data, operational state data, and wear data of the vacuum pump.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
normalizing the read data set of the target category, wherein the calculation formula is as follows:
wherein ,
normalized coefficient representing the mth data attribute, <' > or>
A custom coefficient representing the nth data,
an mth data attribute, representing an nth data, is asserted>
Represents the weight of the mth data attribute, and->
Which represents the number of data attributes,
normalized value representing an m-th data attribute of an nth data>
，/>
Indicating the amount of data;
fitting the normalized data by using a fitting function, wherein the fitting function is as follows:
wherein ,
represents the fitted function value, < >>
Normalized values representing a first class, a second class, a third class and a fourth class of data sets, respectively, i represents an iteration coefficient, </or >>
A fitting coefficient representing the jth class data set, <' > is selected>
Characteristic parameters representing a jth category data set;
and defining the data value after fitting processing as the target data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
pre-constructing a first vacuum pump service life prediction model based on a deep neural network;
training the first vacuum pump life prediction model based on the target data obtained by a plurality of vacuum pumps;
when the precision of the first vacuum pump life prediction model reaches a preset standard, outputting a second vacuum pump life prediction model obtained after training is finished, namely the final vacuum pump life prediction model;
wherein the expression of the vacuum pump life prediction model comprises:
wherein ,
indicates the predicted value of the life at time t +1>
Represents the difference value of the target data between time t and time t +1, and->
Represents an average life value, is>
Represents the loss factor at time t +1, is greater than>
K table representing loss coefficient at time tRepresents an iteration coefficient, < >>
Indicating an index.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
inputting the target data of the target vacuum pump corresponding to each time point obtained by calculation into the vacuum pump service life prediction model to obtain a first service life prediction value;
segmenting the multiple time points according to a preset interval, and solving an average value of the first life prediction values corresponding to each segment to obtain a second life prediction value;
and forming a one-to-one mapping relation between the second life prediction value and the middle time point of the segmented interval, and connecting the second life prediction values corresponding to the plurality of middle time points to generate a life attenuation curve.
In one embodiment, the processor when executing the computer program further performs the steps of:
calculating the slope of the second life prediction value corresponding to two adjacent middle time points based on the life decay curve;
judging the processing mode of the target vacuum pump according to the slope:
when the slope is larger than a first preset value and the service life is smaller than a second preset value, judging that the target vacuum pump has a fault and needs to be overhauled;
and when the slope is greater than a first preset value and the service life is greater than or equal to a second preset value, judging that the target vacuum pump needs to be scrapped.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
s1: acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data;
s2: constructing a vacuum pump service life prediction model based on the target data;
s3: calculating to obtain a life attenuation curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model;
s4: and selecting a processing mode of the target vacuum pump according to the life attenuation curve and processing the processing mode to realize the full life cycle management of the target vacuum pump.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing data cleaning on the first data;
screening the cleaned first data according to a preset data volume to obtain second data;
classifying and sequencing the second data based on a cluster analysis strategy to obtain 4 data sets of different categories, namely a first category, a second category, a third category and a fourth category;
reading and fitting a data set of a target category by using a data adjusting mechanism to obtain target data;
the first data includes initial state data, application environment data, operational state data, and wear data of the vacuum pump.
In one embodiment, the computer program when executed by the processor further performs the steps of:
normalizing the read data set of the target category, wherein the calculation formula is as follows:
wherein ,
normalized coefficient representing an mth data attribute>
A custom coefficient representing the nth data,
an mth data attribute, representing an nth data, is asserted>
Represents the weight of the mth data attribute, and->
Which is indicative of the number of data attributes,
a normalized value representing an mth data attribute of the nth data, based on the value of the parameter, and a value of the parameter>
，/>
Representing the amount of data;
fitting the normalized data by using a fitting function, wherein the fitting function is as follows:
wherein ,
represents the fitted function value, <' > in >>
A normalized value representing the first, second, third and fourth class data sets, respectively, i representing an iteration coefficient, ->
Fitting coefficients representing a jth category data set>
Denotes the firstCharacteristic parameters of the j category data set;
and defining the data value after the fitting processing as the target data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
pre-constructing a first vacuum pump service life prediction model based on a deep neural network;
training the first vacuum pump life prediction model based on the target data obtained by a plurality of vacuum pumps;
when the precision of the first vacuum pump service life prediction model reaches a preset standard, outputting a second vacuum pump service life prediction model obtained after training is the final vacuum pump service life prediction model;
wherein the expression of the vacuum pump life prediction model comprises:
wherein ,
indicates the predicted value of the life at time t +1>
Represents the difference value of the target data between time t and time t +1, and->
Represents an average life value, is>
Represents the loss factor at time t +1, is greater than>
Represents a loss coefficient at time t, k represents an iteration coefficient, and>
indicating an index.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting the target data of the target vacuum pump corresponding to each time point obtained by calculation into the vacuum pump service life prediction model to obtain a first service life prediction value;
segmenting a plurality of time points according to a preset interval, and solving the average value of the first life prediction values corresponding to each segment to obtain a second life prediction value;
and forming a one-to-one mapping relation between the second life prediction value and the middle time point of the segmented interval, and connecting the second life prediction values corresponding to the middle time points to generate a life decay curve.
In one embodiment, the computer program when executed by the processor further performs the steps of:
calculating the slope of the second life prediction value corresponding to two adjacent intermediate time points based on the life decay curve;
judging the processing mode of the target vacuum pump according to the slope:
when the slope is greater than a first preset value and the service life is less than a second preset value, judging that the target vacuum pump has a fault and needs to be overhauled;
and when the slope is greater than a first preset value and the service life is greater than or equal to a second preset value, judging that the target vacuum pump needs to be scrapped.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application.
Claims (8)
1. A full lifecycle management method for a vacuum pump, the method comprising:
acquiring first data of a vacuum pump in a historical database, and preprocessing the first data to obtain target data;
constructing a vacuum pump service life prediction model based on the target data;
calculating to obtain a life decay curve of the target vacuum pump in a plurality of time periods by using the vacuum pump life prediction model;
and selecting a processing mode of the target vacuum pump according to the life attenuation curve and processing the processing mode to realize the full life cycle management of the target vacuum pump.
2. The method of claim 1, wherein the first data comprises initial status data, application environment data, operating status data, and wear data of the vacuum pump, and the preprocessing the first data to obtain target data comprises:
performing data cleaning on the first data;
screening the cleaned first data according to a preset data volume to obtain second data;
classifying and sequencing the second data based on a cluster analysis strategy to obtain 4 data sets of different categories, namely a first category, a second category, a third category and a fourth category;
and reading and fitting the data set of the target category by using a data adjusting mechanism to obtain the target data.
3. The method of claim 2, wherein the reading and fitting a data set of a target category using a data conditioning mechanism to obtain the target data comprises:
normalizing the read data set of the target category, wherein the calculation formula is as follows:
wherein ,
normalized coefficient representing the mth data attribute, <' > or>
A custom coefficient representing the nth data>
An mth data attribute, representing an nth data, is asserted>
Represents the weight of the mth data attribute, and->
Represents the number of data attributes, greater or lesser>
A normalized value representing an mth data attribute of the nth data, based on the value of the parameter, and a value of the parameter>
，/>
Representing the amount of data;
fitting the normalized data by using a fitting function, wherein the fitting function is as follows:
wherein ,
represents the fitted function value, < >>
Normalized values representing a first class, a second class, a third class and a fourth class of data sets, respectively, i represents an iteration coefficient, </or >>
Fitting coefficients representing a jth category data set>
Characteristic parameters representing a jth category data set;
and defining the data value after the fitting processing as the target data.
4. A method as claimed in claim 3, wherein the construction of the vacuum pump life prediction model comprises:
pre-constructing a first vacuum pump service life prediction model based on a deep neural network;
training the first vacuum pump life prediction model based on the target data obtained by a plurality of vacuum pumps;
and when the precision of the first vacuum pump life prediction model reaches a preset standard, outputting a second vacuum pump life prediction model obtained after training is finished, namely the final vacuum pump life prediction model.
5. A method for full life cycle management for a vacuum pump according to claim 4, wherein said expression of a vacuum pump life prediction model comprises:
wherein ,
indicates the predicted value of the life at time t +1>
Represents the difference value of the target data between time t and time t +1, and->
Represents an average life value, is>
Represents the loss factor at time t +1, is greater than>
Represents the loss coefficient at time t, k represents the iteration coefficient, and->
Indicating an index.
6. A method for full life cycle management of a vacuum pump as claimed in claim 5, wherein said calculating a life decay curve of a target vacuum pump over a plurality of time periods using said vacuum pump life prediction model comprises:
inputting the target data of the target vacuum pump corresponding to each time point obtained by calculation into the vacuum pump life prediction model to obtain a first life prediction value;
segmenting the multiple time points according to a preset interval, and solving an average value of the first life prediction values corresponding to each segment to obtain a second life prediction value;
and forming a one-to-one mapping relation between the second life prediction value and the middle time point of the segmented interval, and connecting the second life prediction values corresponding to the middle time points to generate a life decay curve.
7. The method according to claim 6, wherein the selecting and processing the target vacuum pump according to the life decay curve comprises:
calculating the slope of the second life prediction value corresponding to two adjacent middle time points based on the life decay curve;
judging the processing mode of the target vacuum pump according to the slope:
when the slope is greater than a first preset value and the service life is less than a second preset value, judging that the target vacuum pump has a fault and needs to be overhauled;
and when the slope is greater than a first preset value and the service life is greater than or equal to a second preset value, judging that the target vacuum pump needs to be scrapped.
8. A full lifecycle management system suitable for a vacuum pump, the system comprising:
the system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring first data of a vacuum pump in a historical database and preprocessing the first data to obtain target data;
the model construction module is used for constructing a vacuum pump service life prediction model based on the target data;
the calculating module is used for calculating and obtaining a life attenuation curve of the target vacuum pump in a plurality of time periods by utilizing the vacuum pump life prediction model;
and the selection module is used for selecting and processing the processing mode of the target vacuum pump according to the life decay curve so as to realize the full life cycle management of the target vacuum pump.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310194933.8A CN115879248B (en) | 2023-03-03 | 2023-03-03 | Full life cycle management method and system suitable for vacuum pump |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310194933.8A CN115879248B (en) | 2023-03-03 | 2023-03-03 | Full life cycle management method and system suitable for vacuum pump |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115879248A true CN115879248A (en) | 2023-03-31 |
| CN115879248B CN115879248B (en) | 2023-05-16 |
Family
ID=85761873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310194933.8A Active CN115879248B (en) | 2023-03-03 | 2023-03-03 | Full life cycle management method and system suitable for vacuum pump |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879248B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579677A (en) * | 2023-06-01 | 2023-08-11 | 中国铁道科学研究院集团有限公司通信信号研究所 | Full life cycle management method and system for high-speed railway electric service vehicle-mounted equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150003847A1 (en) * | 2013-06-27 | 2015-01-01 | Xerox Corporation | Estimating accuracy of a remaining useful life prediction model for a consumable using statistics based segmentation technique |
| CN104792529A (en) * | 2015-04-12 | 2015-07-22 | 北京化工大学 | Rolling bearing life prediction method based on state-space model |
| WO2019233297A1 (en) * | 2018-06-08 | 2019-12-12 | Oppo广东移动通信有限公司 | Data set construction method, mobile terminal and readable storage medium |
| CN111982522A (en) * | 2020-09-08 | 2020-11-24 | 潍坊潍柴动力科技有限责任公司 | Engine performance monitoring method, device and system and storage medium |
| CN112488556A (en) * | 2020-12-11 | 2021-03-12 | 广东电网有限责任公司 | Evaluation method, device and terminal for scoring consistency of bid evaluation experts |
| CN113486569A (en) * | 2021-06-04 | 2021-10-08 | 江苏科技大学 | Method for predicting residual life of centrifugal pump |
| CN113495800A (en) * | 2020-04-02 | 2021-10-12 | 北京航空航天大学 | Diagnostic prediction data and feature re-recognition method based on extended multi-attribute decision making |
| CN113536982A (en) * | 2021-06-28 | 2021-10-22 | 长江大学 | Intelligent prediction method, system, equipment and medium for residual life of main reducer |
| CN114297918A (en) * | 2021-12-22 | 2022-04-08 | 大连理工大学 | Aero-engine residual life prediction method based on full-attention depth network and dynamic ensemble learning |
| CN115423370A (en) * | 2022-10-10 | 2022-12-02 | 广东电网有限责任公司 | Relay protection equipment health state assessment method and device |
| CN115526241A (en) * | 2022-09-13 | 2022-12-27 | 成都飞机工业（集团）有限责任公司 | Real-time abnormity detection method, device, equipment and medium for aviation hydraulic pump station |
| CN115575127A (en) * | 2022-10-08 | 2023-01-06 | 江苏立达电梯有限公司 | Bearing residual life prediction method based on whale optimization LSSVM |
-
2023
- 2023-03-03 CN CN202310194933.8A patent/CN115879248B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150003847A1 (en) * | 2013-06-27 | 2015-01-01 | Xerox Corporation | Estimating accuracy of a remaining useful life prediction model for a consumable using statistics based segmentation technique |
| CN104792529A (en) * | 2015-04-12 | 2015-07-22 | 北京化工大学 | Rolling bearing life prediction method based on state-space model |
| WO2019233297A1 (en) * | 2018-06-08 | 2019-12-12 | Oppo广东移动通信有限公司 | Data set construction method, mobile terminal and readable storage medium |
| CN113495800A (en) * | 2020-04-02 | 2021-10-12 | 北京航空航天大学 | Diagnostic prediction data and feature re-recognition method based on extended multi-attribute decision making |
| CN111982522A (en) * | 2020-09-08 | 2020-11-24 | 潍坊潍柴动力科技有限责任公司 | Engine performance monitoring method, device and system and storage medium |
| CN112488556A (en) * | 2020-12-11 | 2021-03-12 | 广东电网有限责任公司 | Evaluation method, device and terminal for scoring consistency of bid evaluation experts |
| CN113486569A (en) * | 2021-06-04 | 2021-10-08 | 江苏科技大学 | Method for predicting residual life of centrifugal pump |
| CN113536982A (en) * | 2021-06-28 | 2021-10-22 | 长江大学 | Intelligent prediction method, system, equipment and medium for residual life of main reducer |
| CN114297918A (en) * | 2021-12-22 | 2022-04-08 | 大连理工大学 | Aero-engine residual life prediction method based on full-attention depth network and dynamic ensemble learning |
| CN115526241A (en) * | 2022-09-13 | 2022-12-27 | 成都飞机工业（集团）有限责任公司 | Real-time abnormity detection method, device, equipment and medium for aviation hydraulic pump station |
| CN115575127A (en) * | 2022-10-08 | 2023-01-06 | 江苏立达电梯有限公司 | Bearing residual life prediction method based on whale optimization LSSVM |
| CN115423370A (en) * | 2022-10-10 | 2022-12-02 | 广东电网有限责任公司 | Relay protection equipment health state assessment method and device |
Non-Patent Citations (4)
| Title |
|---|
| SHANE W. BUTLER等: "Prediction of Vacuum Pump Degradation in Semiconductor Processing", 7TH IFAC SYMPOSIUM ON FAULT DETECTION, SUPERVISION AND SAFETY TECHNICAL PROCESSES 2009 * |
| 任子强;司小胜;胡昌华;王玺;裴洪;: "融合多源数据的非线性退化建模与剩余寿命预测", 中国测试 * |
| 何庆飞;陈桂明;陈小虎;姚春江;邢勇;: "基于支持向量机的液压泵寿命特征因子提取方法", 液压与气动 * |
| 王向周等: "液压泵寿命的在线预测与健康管理", 北京理工大学学报 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579677A (en) * | 2023-06-01 | 2023-08-11 | 中国铁道科学研究院集团有限公司通信信号研究所 | Full life cycle management method and system for high-speed railway electric service vehicle-mounted equipment |
| CN116579677B (en) * | 2023-06-01 | 2023-11-21 | 中国铁道科学研究院集团有限公司通信信号研究所 | Full life cycle management method and system for high-speed railway electric service vehicle-mounted equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115879248B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112150311B (en) | Method, device, computer equipment and storage medium for detecting abnormal energy consumption state | |
| CN109992473B (en) | Application system monitoring method, device, equipment and storage medium | |
| CN110503566B (en) | Wind control model building method and device, computer equipment and storage medium | |
| CN115237710A (en) | Server temperature prediction method and device, computer equipment and storage medium | |
| CN115879248B (en) | Full life cycle management method and system suitable for vacuum pump | |
| CN110555164A (en) | generation method and device of group interest tag, computer equipment and storage medium | |
| CN111091276A (en) | Enterprise risk scoring method and device, computer equipment and storage medium | |
| CN110888625A (en) | Method for controlling code quality based on demand change and project risk | |
| CN115049176A (en) | Material performance evaluation method and device and computer equipment | |
| CN108764553B (en) | User scale prediction method and device and computer equipment | |
| CN114168318A (en) | Training method of storage release model, storage release method and equipment | |
| CN113110961A (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN112348226A (en) | Prediction data generation method, system, computer device and storage medium | |
| CN114580791B (en) | Method and device for identifying working state of bulking machine, computer equipment and storage medium | |
| CN115905864A (en) | Abnormal data detection model training method and device and computer equipment | |
| Irina et al. | CURRENT STATUS OF THE FERTILITY IN KYRGYZSTAN | |
| CN111125918B (en) | Complex product reliability assessment method based on similar life model and similar life | |
| CN115934512A (en) | Storage system dynamic test method and device, computer equipment and storage medium | |
| CN115238484A (en) | Board-level assembly service life prediction method and device, computer equipment and storage medium | |
| CN115238931A (en) | Method and device for planning worn parts, computer equipment and storage medium | |
| CN110795255B (en) | Data batch value adjusting method and device, readable storage medium and equipment | |
| CN112948512A (en) | Position data dividing method and device, computer equipment and storage medium | |
| CN111260191B (en) | Test bed maturity quantization method, device, computer equipment and storage medium | |
| CN116933918A (en) | Electric power data prediction method for internet financial service | |
| CN118053561A (en) | Hospital equipment association management and control method, system, electronic equipment and storage medium |
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 |