CN114781670A - Method, device, equipment and medium for experimental equipment maintenance management - Google Patents

Method, device, equipment and medium for experimental equipment maintenance management Download PDF

Info

Publication number
CN114781670A
CN114781670A CN202210414474.5A CN202210414474A CN114781670A CN 114781670 A CN114781670 A CN 114781670A CN 202210414474 A CN202210414474 A CN 202210414474A CN 114781670 A CN114781670 A CN 114781670A
Authority
CN
China
Prior art keywords
index
index set
correlation
statistical
target
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.)
Pending
Application number
CN202210414474.5A
Other languages
Chinese (zh)
Inventor
李菊
蔡汶树
吴泽诚
郑嘉豪
黄恒新
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Technology University
Original Assignee
Shenzhen Technology University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Technology University filed Critical Shenzhen Technology University
Priority to CN202210414474.5A priority Critical patent/CN114781670A/en
Publication of CN114781670A publication Critical patent/CN114781670A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a method, a device, equipment and a medium for maintaining and managing experimental equipment, wherein the method comprises the following steps: acquiring a first performance index set of target equipment in a first time period; obtaining fault categories of the target equipment according to the first performance index set, wherein the fault categories are divided into a first category and a second category; performing feature extraction on the first performance index set to obtain a first feature index set; constructing a first model according to a first sample, wherein the first sample is used for characterizing a data set consisting of a first characteristic element in a first characteristic index set and a fault category; acquiring a second characteristic index set of the target equipment in a second time period; and inputting the second characteristic index set to the first model to obtain the fault prediction probability of the target equipment, and determining the fault equipment according to the fault prediction probability. The invention provides a method, a device, equipment and a medium for maintaining and managing experimental equipment so as to reduce the maintenance cost of the equipment.

Description

Method, device, equipment and medium for experimental equipment maintenance management
Technical Field
The invention relates to the field of equipment maintenance management, in particular to a method, a device, equipment and a medium for experimental equipment maintenance management.
Background
At present, most of maintenance management methods for laboratory equipment can only record, process, monitor and archive the equipment maintenance process, so that the abnormality can only be recorded after a fault occurs and the abnormality is waited for the related technical personnel to process. This can greatly improve cost of maintenance, has prolonged the progress of teaching scientific research simultaneously, and more serious can influence student and mr's safety even.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the embodiment of the invention provides a method, a device, equipment and a medium for maintaining and managing experimental equipment, so as to reduce the maintenance cost of the equipment.
In one aspect, an embodiment of the present invention provides a method for maintenance and management of experimental equipment, including: acquiring a first performance index set of target equipment in a first time period; obtaining a fault category of the target device according to the first performance index set, wherein the fault category is divided into a first category and a second category, the first category is that a performance element in the first performance index set shows that a fault occurs, and the second category is that the performance element in the first performance index set shows that no fault occurs; performing feature extraction on the first performance index set to obtain a first feature index set; building a first model from a first sample, wherein the first sample is used to characterize a data set consisting of a first feature element in the first set of feature metrics and the fault category; acquiring a second characteristic index set of the target equipment in a second time period; and inputting a second characteristic index set to the first model to obtain the fault prediction probability of the target equipment, and determining fault equipment according to the fault prediction probability.
The experimental equipment maintenance management method provided by the embodiment of the invention at least has the following beneficial effects: the method comprises the steps of carrying out feature processing on a first performance index set of target equipment to obtain a first feature index set, constructing a first model according to the first feature index set, inputting a second feature index set of the target equipment to the first model to obtain fault equipment, and distributing the fault equipment to a corresponding maintenance object to be maintained by utilizing the distance between the fault equipment and the type of the maintenance object. By the method, the equipment is intelligently subjected to fault prediction, so that the maintenance cost of the equipment is reduced.
According to some embodiments of the invention, the deriving the fault class of the target device according to the first set of performance indicators comprises: the target device of which the fault category is the first category is a first device; determining that a ratio of the first device in the target device is less than a first threshold, then randomly sampling the target device of the second class such that the ratio is greater than or equal to the first threshold; if the performance element is determined to be a time sequence index, performing statistical processing on the time sequence index to obtain at least one of a continuity index and a non-continuity index; if the performance element is determined to be a continuity index, performing normalization processing on the continuity index to be used as a statistical element in a statistical index set; and if the performance element is determined to be a non-continuity index, encoding the non-continuity index to be used as a statistical element in the statistical index set.
According to some embodiments of the present invention, the performing feature extraction on the first performance index set to obtain a first feature index set includes: obtaining a target correlation according to a first average correlation and a second average correlation, wherein the first average correlation is an average correlation between the statistical elements and the fault categories, and the second average correlation is an average correlation between two random different statistical elements; the correlation formula for obtaining the target correlation is as follows:
Figure BDA0003604958410000021
wherein, MeritsIn order for the target correlation to be described,
Figure BDA0003604958410000022
for the first average correlation value,
Figure BDA0003604958410000023
and k is the number of the statistical elements.
According to some embodiments of the present invention, the performing feature extraction on the first performance index set to obtain a first feature index set includes: randomly extracting two different statistical elements from the statistical index set to serve as a first test index and a second test index, wherein the average value of the first correlation is the first average correlation, and the average value of the second correlation is the second average correlation; r is a radical of hydrogenff＝rXY，rXYFor the second correlation, the first test metric is expressed in the form of: x ═ X1,x2,...,xn) (ii) a The second test index is expressed in the form of: y ═ Y1,y2,...,yn) N is the total number of the statistical elements in the statistical index set; if it is determined that the first test index and the second test index are both continuity indexes, a first formula for obtaining the second correlation is as follows:
Figure BDA0003604958410000024
wherein the content of the first and second substances,
Figure BDA0003604958410000025
is xiThe average value of (a) is calculated,
Figure BDA0003604958410000026
is yiThe mean value of (a); determining that the first test index and the second test index are both discontinuity indexes, and obtaining a second formula of the second correlation is as follows:
Figure BDA0003604958410000027
wherein n isxThe value number of the discrete value in the first test index is 1x，xkiThe values of (A) are as follows: if xkX is ═ ikiIf x is 1kNot equal to i, then xki＝0；nyThe value number of the discrete value in the second test index is discreteThe value is 1y，ykjThe values of (A) are as follows: if ykJ, then ykj1, if ykNot equal to j, then ykj＝0；Pxi＝Sum(xk＝i)/n，Pyj＝Sum(yk＝j)/n，Pij＝Sum(xk＝i,ykJ)/n; if one of the first test index and the second test index is determined to be a continuity index and the other is determined to be a non-continuity index, a third formula for obtaining the second correlation is as follows:
Figure BDA0003604958410000031
wherein n isxThe value number of the discrete value in the first test index is 1x，xkiThe values of (A) are as follows: if xkI, then xkiIf x is 1kNot equal to i, then xki＝0；
Figure BDA0003604958410000032
Is yiMean value of Pxi＝Sum(xk＝i)/n。
According to some embodiments of the present invention, the performing feature extraction on the first performance index set to obtain a first feature index set includes:
a first step of determining that the number of the statistical elements is 1, obtaining the target correlation of the statistical elements according to the correlation formula, obtaining a statistical index corresponding to a reference value as a first characteristic element in a first characteristic index set, marking the statistical elements, and updating the number of the statistical elements, wherein the reference value is the maximum value of the target correlation obtained in the statistical index set; a second step of determining that the number of the statistical elements is not 1, obtaining the target correlation of the statistical elements which are not marked in a statistical index set according to the correlation formula, if the maximum value of the target correlation is greater than the reference value, obtaining the corresponding statistical elements as the first characteristic elements in a first characteristic index set, marking the statistical elements, and updating the number of the statistical elements; and a third step of repeating the second step until the maximum value of the target correlation of the statistical elements is less than or equal to the reference value, or the number of the statistical elements is equal to the number of the statistical elements in the statistical index set.
According to some embodiments of the invention, the constructing the first model from the first sample comprises: obtaining a first derivative and a second derivative through the first sample and a loss function; determining that the first characteristic element is a continuity index, and discretizing the first characteristic element to obtain a discontinuity index; obtaining a gain value of the first sample, and selecting the first sample with the largest gain value as a splitting point; splitting according to the splitting point to obtain a target tree, determining that the depth of the target tree is equal to a second threshold, stopping splitting, and acquiring the target tree as a first model; and obtaining the weight of the node of the first model, and obtaining a predicted value according to the weight.
According to some embodiments of the invention, further comprising: the target device of which the fault category is the first category is a first device; acquiring a third characteristic index set of the first equipment, and forming a data set according to a third characteristic element of the third characteristic index set and the category of the maintenance object to serve as a second sample; acquiring a fourth characteristic index set of the fault equipment; obtaining a target distance according to the third characteristic index set and the fourth characteristic index set; and acquiring the maintenance object class corresponding to the third characteristic element with the minimum target distance, and allocating the fault equipment to the other places of the maintenance object class for maintenance.
In another aspect, an embodiment of the present invention provides an experimental apparatus maintenance management apparatus, including: the device comprises a first module, a second module and a third module, wherein the first module is used for acquiring a first performance index set of target equipment in a first time period; a second module, configured to obtain a fault category of the target device according to the first performance index set, where the fault category is divided into a first category and a second category, the first category indicates that a fault occurs in a performance element in the first performance index set, and the second category indicates that no fault occurs in the performance element in the first performance index set; a third module, configured to perform feature extraction on the first performance index set to obtain a first feature index set; a fourth module for constructing a first model from a first sample, wherein the first sample is used for characterizing a data set consisting of a first feature element in the first feature index set and the fault category; a fifth module, configured to obtain a second feature index set of the target device in a second time period; and the sixth module is used for inputting a second characteristic index set to the first model to obtain the fault prediction probability of the target equipment, and determining the fault equipment according to the fault prediction probability.
The experimental equipment maintenance management device provided by the embodiment of the invention at least has the following beneficial effects: the method comprises the steps of carrying out feature processing on a first performance index set of target equipment to obtain a first feature index set, constructing a first model according to the first feature index set, inputting a second feature index set of the target equipment to the first model to obtain fault equipment, and distributing the fault equipment to a corresponding maintenance object for maintenance by using the distance between the fault equipment and the category of the maintenance object. By the method, intelligent fault prediction is carried out on the equipment, so that the maintenance cost of the equipment is reduced.
On the other hand, an embodiment of the present invention further provides a computer device, including: at least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one program causes the at least one processor to implement the method for laboratory equipment repair management as described in any one of the above.
The computer equipment provided by the embodiment of the invention at least has the same beneficial effects as the experimental equipment maintenance management method.
In another aspect, an embodiment of the present invention provides a storage medium, where program instructions are stored in the storage medium, and when the program instructions are executed by a processor, the storage medium implements the experimental facility maintenance management method according to any one of the above descriptions.
The storage medium according to the embodiment of the invention has at least the same beneficial effects as the experimental equipment maintenance management method.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for maintaining and managing laboratory equipment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a method for performing maintenance and management on laboratory equipment according to another embodiment of the present invention;
FIG. 3 is a schematic block diagram of a maintenance management apparatus for laboratory equipment according to an embodiment of the present invention;
fig. 4 is a schematic block diagram of an apparatus of an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. In the following description, suffixes such as "module", "part", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no peculiar meaning in itself. Thus, "module", "component" or "unit" may be used mixedly. "first", "second", etc. are used for the purpose of distinguishing technical features only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the precedence of the indicated technical features. In the following description, the method steps are labeled continuously for convenience of examination and understanding, and the implementation sequence of the steps is adjusted without affecting the technical effect achieved by the technical scheme of the invention in combination with the overall technical scheme of the invention and the logical relationship among the steps. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
Referring to fig. 1, a method of an embodiment of the invention includes:
step S100, a first performance index set of target equipment in a first time period is obtained;
step S200, obtaining fault types of target equipment according to a first performance index set, wherein the fault types are divided into a first type and a second type, the first type is that performance elements in the first performance index set display faults, and the second type is that the performance elements in the first performance index set display no faults;
according to some embodiments of the invention, step S200 further comprises the steps of:
the target equipment with the fault category being the first category is the first equipment;
if the proportion of the first equipment in the target equipment is determined to be smaller than a first threshold value, randomly sampling the second category of target equipment to enable the proportion to be larger than or equal to the first threshold value;
if the performance element is determined to be a time sequence index, performing statistical processing on the time sequence index to obtain at least one of a continuity index and a non-continuity index;
if the performance element is determined to be a continuity index, performing normalization processing on the continuity index to serve as a statistical element in a statistical index set;
and if the performance element is determined to be the non-continuity index, encoding the non-continuity index to be used as a statistical element in the statistical index set.
Specifically, a first performance index set of a target device in a first time period is obtained by using a device performance index grasping tool, wherein the first performance index set comprises a plurality of performance elements, historical failure conditions of the target device exist, the historical failure conditions comprise predicted failures and manually detected failures, the target device is classified according to the performance elements in the first performance index set, the failure is displayed as a first category, and the failure which does not occur is displayed as a second category. Considering that the occurrence frequency of the faulty device is not high, the accuracy of the model is affected when the model is established and used, so that the proportion of the faulty device of the first category, that is, the first device, in the faulty device is obtained according to the fault category, if the proportion is smaller than a first threshold, the target device of the second category is randomly extracted, so that the proportion of the first device and the target device is equal to the first threshold, and the randomly extracted device becomes a new target device set for subsequent processing. In the first performance index set, the performance element may be a time sequence performance index or a non-time sequence performance index, and a time sequence point in the time sequence performance index is obtained, for example: performance data for each hour in the first time period may be selected, the performance data for each hour corresponding to a time series point. The obtained time sequence points are subjected to statistical processing to obtain non-continuity indexes such as a maximum value, a minimum value, a mean value, a variance, a trend, a peak value, a skewness and the like, it should be noted that the missing time sequence points are supplemented with 0, for example: the first time period of Monday to Friday is obtained, and the performance index data of 12 hours in the two time periods of 8-12 days and 14-22 days are selected as 60 time sequence points, wherein, the time sequence points possibly have no performance index data, and the missing values are supplemented to be 0. The non-time sequence indexes are divided into continuity indexes and non-continuity indexes, wherein all non-continuity indexes, namely the non-continuity indexes in the non-time sequence indexes and the non-continuity indexes obtained after the non-time sequence indexes are processed, are coded to obtain statistical elements; after normalization processing is carried out on the continuity indexes, statistical elements are also obtained, wherein missing values in the continuity indexes are also subjected to filling processing; and collecting the obtained statistical elements to obtain a statistical index set. It is understood that the discontinuity indicator is a discrete indicator. By this approach, the first set of performance indicators is pre-processed so that the indicators can be used in subsequent execution environments.
Step S300, performing feature extraction on the first performance index set to obtain a first feature index set;
specifically, a target correlation is obtained according to a first average correlation and a second average correlation, wherein the first average correlation is an average correlation between a statistical element and a fault category, and the second average correlation is an average correlation between two random different statistical elements; it is to be noted thatOne category is labeled 1 and the second category is labeled 0. And screening statistical elements in the statistical index set through the target correlation, wherein the correlation formula for obtaining the target correlation is as follows:
Figure BDA0003604958410000051
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003604958410000052
is the first average correlation value and is the second average correlation value,
Figure BDA0003604958410000053
k is the number of statistical elements for the second average correlation value. Randomly extracting two different statistical elements from the statistical index set to serve as a first test index and a second test index, wherein the average value of the first correlation is a first average correlation, and the average value of the second correlation is a second average correlation; r is a radical of hydrogenff＝rXY，rXYFor the second correlation, the first test indicator is expressed as: x ═ X1,x2,...,xn) (ii) a The second test index is expressed in the form of: y ═ Y1,y2,...,yn) N is the total number of statistical elements in the statistical index set; it can be understood that rff＝rXYAlthough represented differently, when both represent a second correlation of two different statistical elements, rXYX, y in (1) specifically denote a second correlation of the first test index and the second test index, and rffF in (1) generally refers to a statistical element in the statistical index set.
The following is a method for obtaining the second correlation for different statistical elements:
if it is determined that the first test index and the second test index are both continuity indexes, a first formula for obtaining the second correlation is as follows:
Figure BDA0003604958410000061
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003604958410000062
is xiMean value of，
Figure BDA0003604958410000063
Is yiThe mean value of (a);
if it is determined that the first test index and the second test index are both discontinuity indexes, a second formula for obtaining a second correlation is as follows:
Figure BDA0003604958410000064
wherein n isxThe value number of the discrete value in the first test index is 1x，xkiThe values of (A) are as follows: if xkI, then xki1, xkNot equal to i, then xki＝0；nyThe value number of the discrete value in the second test index is 1y，ykjThe values of (A) are as follows: if ykJ, then ykj1, if ykNot equal to j, then ykj＝0；Pxi＝Sum(xk＝i)/n，Pyj＝Sum(yk＝j)/n，Pij＝Sum(xk＝i,yk＝j)/n；
Determining one of the first test index and the second test index as a continuity index, and the other as a discontinuity index, and obtaining a third formula of the second correlation as follows:
Figure BDA0003604958410000065
wherein n isxThe value number of the discrete value in the first test index is 1x，xkiThe values of (A) are as follows: if xkX is ═ ikiIf x is 1kNot equal to i, then xki＝0；
Figure BDA0003604958410000066
Is yiOf the average value of (a).
It should be noted that, because the fault category is discrete, when the first correlation is obtained, the third formula is used to calculate if the selected statistical element is determined to be the continuity indicator, and the second formula is used to calculate if the selected statistical element is determined to be the non-continuity indicator.
Performing feature extraction on the statistical index set by using the target correlation to obtain a first feature index set:
the method comprises the following steps that firstly, the number of statistical elements is determined to be 1, namely k in a correlation formula is 1, the target correlation of all statistical elements in a statistical index set is obtained, the statistical element with the maximum target correlation is obtained to serve as a first characteristic element in a first characteristic index set, the selected statistical elements are marked, and the number of the statistical elements, namely the k value, is increased progressively; wherein the target maximum correlation value is used as a reference value.
Step two, determining that the number of statistical elements is not 1, namely k in a correlation formula is not 1, acquiring the unmarked statistical elements in a statistical index set, acquiring the target correlation size of the statistical elements, selecting the maximum value of the target correlation, comparing the maximum value with a reference value, if the maximum value is greater than the reference value, acquiring the statistical elements corresponding to the maximum value as first characteristic elements in a first characteristic index set, marking the statistical elements selected as the first characteristic elements, and increasing the number of the statistical elements;
and thirdly, repeating the second step until the target correlation of the statistical elements is determined to be less than or equal to the reference value, or determining the number of the statistical elements, namely the k value in the correlation formula is equal to the number of the statistical elements in the statistical index set, and terminating the feature selection.
It will be appreciated that, when the second step is repeated, the value of k is incremented, i.e. every time the value of k is repeated, i.e. updated, the original value is added by 1 to obtain a new value.
It should be noted that after the first feature index set is obtained, the first feature elements may be sorted according to the size of the first correlation, so as to facilitate performing fault location after predicting the target device. After the performance indexes are processed into the statistical indexes, a plurality of index characteristics exist, redundancy is generated among the indexes, too many indexes influence the efficiency of model training, the characteristic correlation can be captured well through the method, and the first characteristic elements in the first characteristic index set are selected from the statistical index set.
Step S400, constructing a first model according to a first sample, wherein the first sample is used for representing a data set consisting of first characteristic elements and fault categories in a first characteristic index set;
specifically, a first derivative and a second derivative are obtained according to a first sample and a loss function, wherein the first sample is obtained according to a data set composed of a first characteristic element in a first characteristic index set and a fault category, and the expression form of the first sample is as follows: i { (x)1,y1),(x2,y2),...,(xn,yn)}，xi(i 1.. n) is an attribute value of the first feature element, and y is an attribute value of the first feature elementi(i 1.., n) is a fault category of the target device; the loss function is:
Figure BDA0003604958410000071
each sample is taken, i.e., I { (x)1,y1),(x2,y2),...,(xn,yn) I (i ═ 1.., n) in (j), the loss function in the current round by each sample
Figure BDA0003604958410000072
Based on
Figure BDA0003604958410000073
First and second derivatives of (a): g is a radical of formulati＝pti-yi，hti＝pti*(1-pti) Wherein g istiIs the first derivative, htiIs a second derivative of the first order,
Figure BDA0003604958410000074
numbering first feature elements in the first feature index set, and discretizing the first feature elements to obtain a non-continuity index if the first feature elements are continuity indexes; obtaining a gain value of the characteristic of the first characteristic element, and selecting a first sample with the maximum gain value as a splitting point, wherein the formula of the gain value is as follows:
Figure BDA0003604958410000075
wherein, gain is a gain value,
Figure BDA0003604958410000076
Figure BDA0003604958410000081
i ∈ L is the first sample to split to the left subtree, i ∈ R is the first sample to split to the right subtree, and λ and γ are regularization coefficients. And for the first samples of the left sub-tree and the right sub-tree, continuously selecting the first sample with the largest gain value to split to obtain a target tree, stopping splitting until the depth of the target tree is confirmed to be equal to a second threshold value, and obtaining the target tree as a first model. It will be appreciated that the second threshold may be chosen based on a priori knowledge or actual requirements. Obtaining the weight of each node through the first model, wherein the node is the last leaf node of the target tree, and the formula for calculating the weight is as follows:
Figure BDA0003604958410000082
wherein wtjAs a weight value, the weight value,
Figure BDA0003604958410000083
i ∈ j is the first sample of the node j that is divided into the t-th tree, and η is the learning rate. It will be appreciated that the regularization coefficients and learning rates may be selected based on a priori knowledge or actual requirements, where
Figure BDA0003604958410000084
Calculating the samples in the first samples to construct a target tree of a target value, acquiring the target tree as a first model, and obtaining a predicted value according to the first model:
Figure BDA0003604958410000085
wherein the content of the first and second substances,
Figure BDA0003604958410000086
is a predicted value, wtjIs the weight of the node, T is the number of the target tree, and T is expressed asSeveral target trees. By the method, data overfitting can be prevented, and the accuracy of the obtained first model is higher than that of a common model. It is understood that the third threshold may be selected according to a priori knowledge or actual requirements.
Step S500, a second characteristic index set of the target equipment in a second time period is obtained;
and S600, inputting a second characteristic index set to the first model to obtain the fault prediction probability of the target equipment, and determining the fault equipment according to the fault prediction probability.
Specifically, a second characteristic index set of the target equipment in a second time period is obtained, data preprocessing is carried out on the second characteristic index set by referring to preprocessing of the first characteristic index set to obtain indexes which are convenient for subsequent operation, the preprocessed indexes are input into the first model to obtain a predicted value of the equipment i
Figure BDA0003604958410000087
And determining that the failure prediction probability is greater than a third threshold value, and determining that the failure equipment is failed.
According to some embodiments of the invention, the invention further comprises the following steps, as shown in fig. 2:
step S710, a third characteristic index set of the first equipment is obtained, and a data set is formed according to a third characteristic element of the third characteristic index set and the class of the maintenance object and serves as a second sample;
step S720, acquiring a fourth characteristic index set of the fault equipment;
step 730, obtaining a target distance according to the third characteristic index set and the fourth characteristic index set;
step S740, obtaining the maintenance object category corresponding to the third feature element with the minimum target distance, and allocating the faulty device to the maintenance object category for maintenance.
Specifically, a third characteristic index set of the first category of equipment in the target equipment is obtained, a data set is formed according to a third characteristic element in the third index set and the maintenance object category and serves as a second sample, and the expression form of the second sample is as follows: i { (x)1,z1),(x2,z2),...,(xn,zn)}，xi(i ═ 1.. times, n) is an attribute value of the third feature element, z is an attribute value of the third feature element, and z is an attribute value of the third feature elementi(i ═ 1, …, n) is a repair object category, for example: the value of the maintenance object class can be 1, 2 and 3, wherein 1 is a supplier, 2 is an experiment teacher, and 3 is a software and hardware professional student. Acquiring a fourth characteristic index set of the fault equipment, wherein the expression form of the third characteristic index set is as follows: s. thei＝(Si1,...,Siq)，Sia(a 1.. q.) is the value of the attribute of the a-th third feature element; the expression form of the fourth characteristic index set is as follows: x is the number ofj＝(xj1,...,xjq)，xja(a 1.,. q.) is the value of the attribute of the a-th fourth feature element. Acquiring a target distance of a fourth characteristic index set of a third characteristic index set:
Figure BDA0003604958410000091
wherein, CpFor the repair object category, it is understood that the representation form of the third feature index set in the second sample is different from the representation form in the process of obtaining the target distance, but the content of the representation is the same, and a different representation form is adopted for distinguishing in calculation. And acquiring a third characteristic index element with the minimum distance from the target of the fourth characteristic element, acquiring the maintenance object category corresponding to the selected third characteristic index element according to the second sample, namely acquiring the maintenance object category corresponding to the fourth characteristic element, and allocating fault equipment to the maintenance object category for processing. When the maintenance object checks and maintains the fault, if the fault which is not corresponding to the maintenance object is found, the maintenance object corresponding to the third characteristic element is modified, or if the fault cannot be solved by all the distributed maintenance objects, the maintenance object corresponding to the third characteristic element is modified. Through the method, the influence on the progress of teaching and scientific research is reduced, the human resources are reduced, the maintenance efficiency is improved, meanwhile, the maintenance object comprises students, and the ability of the students to process faults can be exercised.
In one aspect, referring to fig. 3, this embodiment provides a maintenance management device for laboratory equipment, which at least includes: a first module 310, a second module 320, a third module 330, a fourth module 340, a fifth module 350, and a sixth module 360.
Specifically, the first module 310 obtains a first performance index set of the target device in a first time period, the second module 320 obtains a fault category of the target device according to the first performance index and inputs the fault category into the third module 330, the third module 330 performs feature extraction on the first performance index set to obtain a first feature index set, the fourth module 340 constructs a first model according to a first sample composed of a first feature element in the first feature index set and the fault category, the fifth model 350 obtains a first feature index set of the target device in a second time period, the sixth model 360 inputs the first feature index set of the fifth model 350 into the first model to obtain a fault prediction concept of the target device, and obtains a fault device in the target device according to the fault prediction probability.
Referring to fig. 4, the present embodiment provides an electronic device, which includes a processor 410 and a memory 420 coupled to the processor 410, wherein the memory 420 stores program instructions executable by the processor 410, and the experimental device maintenance management method is implemented when the processor 410 executes the program instructions stored in the memory 420. The processor 410 may also be referred to as a Central Processing Unit (CPU), among others. The processor 410 may be an integrated circuit chip having signal processing capabilities. The processor 410 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The general purpose processor may be a microprocessor, but in the alternative, the general purpose processor may be any conventional processor or the like. Memory 420 may include various components (e.g., machine-readable media) including, but not limited to, random access memory components, read-only components, and any combination thereof. The memory 420 may also include: instructions (e.g., software) (e.g., stored on one or more machine-readable media); the instruction implements the experimental equipment maintenance management method in the above embodiment. The electronic device has a function of loading and operating a software system for maintenance management of the experimental device provided by the embodiment of the invention, for example, a Personal Computer (PC), a mobile phone, a smart phone, a Personal Digital Assistant (PDA), a wearable device, a pocket PC (ppc), a tablet PC, and the like.
The present embodiment provides a computer-readable storage medium storing a program executed by a processor to implement the above-described experimental facility maintenance management method.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read by a processor of the computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the experimental device repair management method described above.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following technologies, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (10)

1. A maintenance management method for experimental equipment is characterized by comprising the following steps:
acquiring a first performance index set of target equipment in a first time period;
obtaining a fault category of the target device according to the first performance index set, wherein the fault category is divided into a first category and a second category, the first category is that a performance element in the first performance index set shows that a fault occurs, and the second category is that the performance element in the first performance index set shows that no fault occurs;
performing feature extraction on the first performance index set to obtain a first feature index set;
building a first model from a first sample, wherein the first sample is used to characterize a data set consisting of a first feature element in the first feature index set and the fault category;
acquiring a second characteristic index set of the target equipment in a second time period;
and inputting a second characteristic index set to the first model to obtain the fault prediction probability of the target equipment, and determining fault equipment according to the fault prediction probability.
2. The method for repairing and managing laboratory equipment according to claim 1, wherein the obtaining the fault category of the target equipment according to the first set of performance indicators comprises:
the target device of which the fault category is the first category is a first device;
determining that a ratio of the first device in the target device is less than a first threshold, then randomly sampling the target device of the second class such that the ratio is greater than or equal to the first threshold;
if the performance element is determined to be a time sequence index, performing statistical processing on the time sequence index to obtain at least one of a continuity index and a non-continuity index;
if the performance element is determined to be a continuity index, performing normalization processing on the continuity index to be used as a statistical element in a statistical index set;
and if the performance element is determined to be a non-continuity index, encoding the non-continuity index to be used as a statistical element in the statistical index set.
3. The method for maintaining and managing laboratory equipment according to claim 2, wherein said extracting features of the first performance index set to obtain a first feature index set comprises:
obtaining a target correlation according to a first average correlation and a second average correlation, wherein the first average correlation is an average correlation between the statistical elements and the fault categories, and the second average correlation is an average correlation between two random different statistical elements;
obtaining a correlation formula of the target correlation as follows:
Figure FDA0003604958400000011
wherein, MeritsIn order for the target to be a correlation,
Figure FDA0003604958400000012
for the first average correlation value,
Figure FDA0003604958400000013
and k is the number of the statistical elements.
4. The method for maintaining and managing laboratory equipment according to claim 3, wherein said extracting features of said first set of performance indicators to obtain a first set of feature indicators comprises:
randomly extracting two different statistical elements from the statistical index set to serve as a first test index and a second test index, wherein the average value of the first correlation is the first average correlation, and the average value of the second correlation is the second average correlation; r isff＝rXY，rXYFor the second correlation, the first test metric is expressed in the form of: x ═ X1,x2,...,xn) (ii) a The expression form of the second test index is as follows: y ═ Y1,y2,...,yn) N is the total number of the statistical elements in the statistical index set;
determining that the first test index and the second test index are both continuity indexes, and acquiring a first formula of the second correlation as follows:
Figure FDA0003604958400000021
wherein the content of the first and second substances,
Figure FDA0003604958400000022
is xiThe average value of (a) of (b),
Figure FDA0003604958400000023
is yiThe mean value of (a);
determining that the first test index and the second test index are both discontinuity indexes, and obtaining a second formula of the second correlation is as follows:
Figure FDA0003604958400000024
wherein n isxThe value number of the discrete value in the first test index is 1x，xkiThe values of (A) are as follows: if xkX is ═ ikiIf x is 1kNot equal to i, then xki＝0；nyThe value number of the discrete value in the second test index is 1y，ykjThe values of (A) are as follows: if ykJ, then ykjIf y is 1kNot equal to j, then ykj＝0；Pxi＝Sum(xk＝i)/n，Pyj＝Sum(yk＝j)/n，Pij＝Sum(xk＝i,yk＝j)/n；
If one of the first test index and the second test index is determined to be a continuity index and the other is determined to be a non-continuity index, a third formula for obtaining the second correlation is as follows:
Figure FDA0003604958400000025
wherein n isxThe value number of the discrete value in the first test index is 1x，xkiThe values of (A) are as follows: if xkX is ═ iki1, xkNot equal to i, then xki＝0；
Figure FDA0003604958400000026
Is yiMean value of (P)xi＝Sum(xk＝i)/n。
5. The method for repairing and managing laboratory equipment according to claim 4, wherein the extracting the features of the first performance index set to obtain a first feature index set comprises:
a first step of determining that the number of the statistical elements is 1, obtaining the target correlation of the statistical elements according to the correlation formula, obtaining a statistical index corresponding to a reference value as a first characteristic element in a first characteristic index set, marking the statistical elements, and updating the number of the statistical elements, wherein the reference value is the maximum value of the target correlation obtained in the statistical index set;
a second step of determining that the number of the statistical elements is not 1, obtaining the target correlation of the statistical elements which are not marked in a statistical index set according to the correlation formula, if the maximum value of the target correlation is greater than the reference value, obtaining the corresponding statistical elements as the first characteristic elements in a first characteristic index set, marking the statistical elements, and updating the number of the statistical elements;
and a third step of repeating the second step until the maximum value of the target correlation of the statistical elements is less than or equal to the reference value, or the number of the statistical elements is equal to the number of the statistical elements in the statistical index set.
6. The method for laboratory equipment repair management according to claim 1, the constructing the first model from the first sample, comprising:
obtaining a first derivative and a second derivative through the first sample and a loss function;
when the first characteristic element is determined to be a continuity index, discretizing the first characteristic element to obtain a discontinuity index;
obtaining a gain value of the first sample, and selecting the first sample with the largest gain value as a splitting point;
splitting according to the splitting point to obtain a target tree, determining that the depth of the target tree is equal to a second threshold, stopping splitting, and acquiring the target tree as a first model;
and obtaining the weight of the node of the first model, and obtaining a predicted value according to the weight.
7. The maintenance management method for laboratory equipment according to claim 1, further comprising:
the target device of which the fault category is the first category is a first device;
acquiring a third characteristic index set of the first equipment, and forming a data set according to a third characteristic element of the third characteristic index set and the class of the maintenance object to serve as a second sample;
acquiring a fourth characteristic index set of the fault equipment;
obtaining a target distance according to the third characteristic index set and the fourth characteristic index set;
and acquiring the maintenance object class corresponding to the third characteristic element with the minimum target distance, and allocating the fault equipment to the other places of the maintenance object class for maintenance.
8. An experimental facilities maintenance management device which characterized in that includes:
a first module, configured to obtain a first set of performance indicators of a target device for a first time period;
a second module, configured to obtain a fault category of the target device according to the first performance index set, where the fault category is divided into a first category and a second category, the first category indicates that a fault occurs in a performance element in the first performance index set, and the second category indicates that no fault occurs in the performance element in the first performance index set;
a third module, configured to perform feature extraction on the first performance index set to obtain a first feature index set;
a fourth module for constructing a first model from a first sample, wherein the first sample is used for characterizing a data set consisting of a first feature element in the first feature index set and the fault category;
a fifth module, configured to obtain a second feature index set of the target device in a second time period;
and the sixth module is used for inputting a second characteristic index set to the first model to obtain the fault prediction probability of the target equipment, and determining the fault equipment according to the fault prediction probability.
9. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program implementing the method of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method according to any one of claims 1-7.
CN202210414474.5A 2022-04-20 2022-04-20 Method, device, equipment and medium for experimental equipment maintenance management Pending CN114781670A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210414474.5A CN114781670A (en) 2022-04-20 2022-04-20 Method, device, equipment and medium for experimental equipment maintenance management

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210414474.5A CN114781670A (en) 2022-04-20 2022-04-20 Method, device, equipment and medium for experimental equipment maintenance management

Publications (1)

Publication Number Publication Date
CN114781670A true CN114781670A (en) 2022-07-22

Family

ID=82430945

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210414474.5A Pending CN114781670A (en) 2022-04-20 2022-04-20 Method, device, equipment and medium for experimental equipment maintenance management

Country Status (1)

Country Link
CN (1) CN114781670A (en)

Similar Documents

Publication Publication Date Title
Liu et al. An interactive method to improve crowdsourced annotations
CN111459700B (en) Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium
CN108683530B (en) Data analysis method and device for multi-dimensional data and storage medium
Harris SKA: split kmer analysis toolkit for bacterial genomic epidemiology
de Vienne et al. Phylo-MCOA: a fast and efficient method to detect outlier genes and species in phylogenomics using multiple co-inertia analysis
Rulik et al. Using taxonomic consistency with semi‐automated data pre‐processing for high quality DNA barcodes
O'BRIEN et al. Two issues in archaeological phylogenetics: taxon construction and outgroup selection
Barley et al. Assessing the performance of DNA barcoding using posterior predictive simulations
CN102498445A (en) Supervised fault learning using rule-generated samples for machine condition monitoring
CA2937919A1 (en) Evaluating data quality of clinical trials
CN113343696A (en) Electronic medical record named entity identification method, device, remote terminal and system
CN110232130B (en) Metadata management pedigree generation method, apparatus, computer device and storage medium
CN111768820A (en) Paper medical record digitization and target detection model training method, device and storage medium
CN114357858A (en) Equipment deterioration analysis method and system based on multi-task learning model
DE112021003550T5 (en) DOWNSAMPLING GENOMIC SEQUENCE DATA
CN113724059A (en) Federal learning model training method and device and electronic equipment
CN114781670A (en) Method, device, equipment and medium for experimental equipment maintenance management
CN115169426B (en) Anomaly detection method and system based on similarity learning fusion model
US20230022030A1 (en) Systems and methods for processing images for image matching
CN116013546A (en) Death factor chain detection model training and detection method based on disease Chinese interpretation
O’Leary et al. Crowds replicate performance of scientific experts scoring phylogenetic matrices of phenotypes
CN114528333A (en) Test question implicit knowledge attribute association mining and related test question pushing method and system based on attribute exploration
DE112021003147T5 (en) PRACTICES FOR PROACTIVE TROUBLESHOOTING OF DEPLOYMENT WORKFLOWS FOR EFFICIENT CLOUD OPERATIONS
Araujo et al. The profession of public health informatics: Still emerging?
Mahapatra et al. Deformity Index: A Semi-Reference Clade-Based Quality Metric of Phylogenetic Trees

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