CN113537519B - Method and device for identifying abnormal equipment - Google Patents
Method and device for identifying abnormal equipment Download PDFInfo
- Publication number
- CN113537519B CN113537519B CN202010279539.0A CN202010279539A CN113537519B CN 113537519 B CN113537519 B CN 113537519B CN 202010279539 A CN202010279539 A CN 202010279539A CN 113537519 B CN113537519 B CN 113537519B
- Authority
- CN
- China
- Prior art keywords
- fault
- maintenance
- abnormal
- dimension characteristics
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012423 maintenance Methods 0.000 claims abstract description 90
- 238000012544 monitoring process Methods 0.000 claims abstract description 61
- 238000012549 training Methods 0.000 claims abstract description 61
- 230000006870 function Effects 0.000 claims description 51
- 238000012706 support-vector machine Methods 0.000 claims description 30
- 238000000605 extraction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 7
- 230000008439 repair process Effects 0.000 description 7
- 230000005856 abnormality Effects 0.000 description 4
- 230000002547 anomalous effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000009394 selective breeding Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for identifying abnormal equipment, and relates to the technical field of computers. One embodiment of the method comprises the following steps: extracting maintenance dimension characteristics and fault dimension characteristics of each device according to historical fault original data of each device; generating a training data set according to the maintenance dimension characteristics and the fault dimension characteristics of each device and the abnormal state labels of each device; and training a monitoring model through the training data set, and monitoring the state characteristics of each device in real time by utilizing the trained monitoring model so as to identify abnormal devices, wherein the state characteristics of the devices comprise the maintenance dimension characteristics and the fault dimension characteristics. According to the embodiment, abnormal equipment can be automatically and accurately identified, and the abnormal equipment can be timely pushed to equipment maintenance personnel, so that maintenance work can be carried out more pertinently, and the working efficiency is improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for identifying an abnormal device.
Background
In order to ensure long-term stable operation of the unmanned cabin, the fault condition of equipment in the unmanned cabin needs to be counted regularly so as to find out abnormal equipment and overhaul the abnormal equipment in time. The current identification of the abnormal equipment is simply to count the severity level and the number of the faults of the equipment in a period of time, manually select the equipment with high fault level and a large number of faults as the abnormal equipment, and manually push the equipment to a warehouse equipment maintainer.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
The fault of the artificial identification equipment is relatively unilateral, so that the equipment cannot be pertinently and timely salvaged, and the working efficiency is affected.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a method and a device for identifying abnormal equipment, which can automatically and accurately identify the abnormal equipment and timely push the abnormal equipment to equipment maintenance personnel, so that the equipment maintenance personnel can carry out maintenance work more pertinently, and the working efficiency is improved.
To achieve the above object, according to one aspect of an embodiment of the present invention, there is provided a method of identifying an abnormal device.
A method of identifying an abnormal device, comprising: extracting maintenance dimension characteristics and fault dimension characteristics of each device according to historical fault original data of each device; generating a training data set according to the maintenance dimension characteristics and the fault dimension characteristics of each device and the abnormal state labels of each device; and training a monitoring model through the training data set, and monitoring the state characteristics of each device in real time by utilizing the trained monitoring model so as to identify abnormal devices, wherein the state characteristics of the devices comprise the maintenance dimension characteristics and the fault dimension characteristics.
Optionally, according to the historical fault original data of each device, the historical maintenance times and average maintenance interval time of each device are counted to obtain maintenance dimension characteristics of each device.
Optionally, according to the historical fault original data of each device, counting the number of faults and average fault intervals of each device in a plurality of counting periods before maintenance, and based on preset fault grades, counting the number of faults of each grade in the number of faults and the average fault intervals of each grade in the average fault intervals, so as to obtain the fault dimension characteristics of each device according to the number of faults of each grade and the average fault intervals of each grade of each device.
Optionally, the monitoring model is implemented based on one of a support vector machine, a random forest, and a neural network.
Optionally, when the monitoring model is trained, selecting the model by adopting a ten-fold cross validation method to select the monitoring model with the smallest prediction error as the trained monitoring model.
Optionally, the training the monitoring model by the training data set includes: for the training data set, selecting a radial basis function, constructing an objective function of a support vector machine based on the selected radial basis function and the abnormal state labels of the devices, and solving the objective function under a preset constraint condition to obtain an optimal solution; calculating the intercept of a classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis function; and obtaining a decision function of the support vector machine based on the optimal solution, the intercept, the abnormal state labels of the devices and the selected radial basis function, wherein the decision function is used for the support vector machine to identify the abnormal device.
According to another aspect of the embodiment of the present invention, there is provided an apparatus for identifying an abnormal device.
An apparatus for identifying an abnormal device, comprising: the feature extraction module is used for extracting maintenance dimension features and fault dimension features of each device according to the historical fault original data of each device; the training data generation module is used for generating a training data set according to the maintenance dimension characteristics and the fault dimension characteristics of each device and the abnormal state labels of each device; the abnormal equipment identification module is used for training the monitoring model through the training data set and utilizing the trained monitoring model to monitor the state characteristics of each equipment in real time so as to identify the abnormal equipment, wherein the state characteristics of the equipment comprise the maintenance dimension characteristics and the fault dimension characteristics.
Optionally, the feature extraction module is further configured to: and according to the historical fault original data of each device, counting the historical maintenance times and average maintenance interval time of each device to obtain the maintenance dimension characteristics of each device.
Optionally, the feature extraction module is further configured to: according to the historical fault original data of each device, counting the number of faults and average fault intervals of each device in a plurality of counting periods before maintenance, and based on preset fault grades, counting the number of faults of each grade in the number of faults and the average fault intervals of each grade in the average fault intervals, so as to obtain the fault dimension characteristics of each device according to the number of faults of each grade and the average fault intervals of each grade of each device.
Optionally, the monitoring model is implemented based on one of a support vector machine, a random forest, and a neural network.
Optionally, the abnormal device identification module is further configured to: and when the monitoring model is trained, selecting the model by adopting a ten-fold cross validation method so as to select the monitoring model with the minimum prediction error as the trained monitoring model.
Optionally, the abnormal device identification module is further configured to: for the training data set, selecting a radial basis function, constructing an objective function of a support vector machine based on the selected radial basis function and the abnormal state labels of the devices, and solving the objective function under a preset constraint condition to obtain an optimal solution; calculating the intercept of a classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis function; and obtaining a decision function of the support vector machine based on the optimal solution, the intercept, the abnormal state labels of the devices and the selected radial basis function, wherein the decision function is used for the support vector machine to identify the abnormal device.
According to yet another aspect of an embodiment of the present invention, an electronic device is provided.
An electronic device, comprising: one or more processors; and the memory is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the method for identifying the abnormal equipment provided by the embodiment of the invention.
According to yet another aspect of an embodiment of the present invention, a computer-readable medium is provided.
A computer-readable medium has stored thereon a computer program which, when executed by a processor, implements a method of identifying an abnormal device provided by an embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: extracting maintenance dimension characteristics and fault dimension characteristics of each device according to the historical fault original data of each device; generating a training data set according to maintenance dimension characteristics, fault dimension characteristics and abnormal state labels of all the devices; training a monitoring model through a training data set, and monitoring the state characteristics of each device in real time by utilizing the trained monitoring model so as to identify abnormal devices. Abnormal equipment can be automatically and accurately identified, and the abnormal equipment can be timely pushed to equipment maintenance personnel, so that maintenance work can be more pertinently carried out, and the working efficiency is improved.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of a method of identifying an anomalous device in accordance with an embodiment of the invention;
FIG. 2 is a flow diagram of identifying anomalous devices in accordance with an embodiment of the invention;
FIG. 3 is a schematic diagram of a repair dimension feature and a fault dimension feature in accordance with one embodiment of the present invention;
FIG. 4 is a schematic diagram of main modules of an apparatus for identifying abnormal devices according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
Fig. 6 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of main steps of a method of identifying an abnormal device according to an embodiment of the present invention.
As shown in fig. 1, the method of identifying an abnormal device according to an embodiment of the present invention mainly includes the following steps S101 to S103.
Step S101: and extracting maintenance dimension characteristics and fault dimension characteristics of each device according to the historical fault original data of each device.
Step S102: and generating a training data set according to the maintenance dimension characteristic, the fault dimension characteristic and the abnormal state label of each device.
Step S103: training a monitoring model through a training data set, and monitoring the state characteristics of each device in real time by utilizing the trained monitoring model so as to identify abnormal devices, wherein the state characteristics of the devices comprise maintenance dimension characteristics and fault dimension characteristics.
In one embodiment, historical maintenance times and average maintenance interval time of each device are counted according to the historical fault original data of each device to obtain maintenance dimension characteristics of each device.
The historical fault original data of each device can be obtained according to a warehouse historical maintenance record, specifically, the fault original data of a certain period of time before the device is maintained is extracted according to the corresponding device and maintenance time of each record, and the fault original data comprises fault codes, fault severity level, fault occurrence time and the like.
In one embodiment, according to historical fault raw data of each device, the number of faults and average fault intervals of each device in a plurality of statistical periods before maintenance are counted, and based on preset fault grades, the number of faults of each grade in the number of faults and the average fault interval of each grade in the average fault interval are counted, so that fault dimension characteristics of each device are obtained according to the number of faults of each grade and the average fault interval of each grade of each device.
The abnormal state label of the device indicates the class of the device, which includes abnormality and normal, for example, abnormal state label=1 indicates abnormality, and abnormal state label= -1 indicates normal.
In one embodiment, the monitoring model is based on one of a support vector machine, a random forest, a neural network implementation.
In one embodiment, when training the monitoring model, a ten-fold cross validation method is adopted to select the model, so as to select the monitoring model with the smallest prediction error as the trained monitoring model. Specifically, the training data set may be divided into a plurality of subsets, and a plurality of combinations of training sets and test sets are generated according to the plurality of subsets, for example, the number of the subsets is 10, and then each combination uses one subset as the test set and the other subsets as the training sets, so that 10 combinations can be obtained. And training the monitoring models by using each combined training set, verifying each trained monitoring model by using a corresponding test set to calculate the prediction error of the monitoring model, and selecting the monitoring model with the minimum prediction error as the trained monitoring model.
In one embodiment, training a monitoring model through a training data set includes: for the training data set, selecting a radial basis function, constructing an objective function of a support vector machine based on the selected radial basis function and abnormal state labels of all devices, and solving the objective function under a preset constraint condition to obtain an optimal solution, wherein the preset constraint condition is a constraint condition of the objective function when the optimal solution is solved; calculating the intercept of a classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis function; and obtaining a decision function of the support vector machine based on the optimal solution, the intercept, the abnormal state labels of the devices and the selected radial basis function, wherein the decision function represents an optimal hyperplane (classification plane) of the support vector machine and is used for identifying abnormal devices by the support vector machine. And in particular will be described in more detail below.
In one embodiment, after identifying the abnormal device, pushing the device abnormality information to the specified client is further included. The designated client may be a client of a person for maintenance or the like.
Because the prior art only considers the equipment fault condition in the current statistical period, the equipment fault condition in the past period is not considered, and the accuracy is low through artificial identification. The embodiment of the invention judges whether the equipment is abnormal or not based on a plurality of statistical periods, and improves the accuracy of identification.
In addition, the prior art only considers the severity level and the number of faults to identify abnormal equipment, and cannot comprehensively reflect the abnormal condition of the equipment. The embodiment of the invention trains the model by utilizing the frequency information and the historical fault information on the basis of the fault data, comprehensively reflects the abnormal condition of the equipment, realizes automatic and accurate identification of the abnormal equipment, and overcomes the defect that the existing artificial selection of the abnormal equipment lacks a unified and fixed standard.
The method for identifying the abnormal equipment can be used for identifying the abnormal equipment in various equipment sets. The method for identifying abnormal equipment according to the embodiment of the invention is described in detail below by taking an equipment set formed by the equipment in the unmanned cabin as an example.
An embodiment of the invention utilizes historical fault original data to establish a supervised learning monitoring model for identifying abnormal equipment in an unmanned cabin, and a flow chart for identifying the abnormal equipment is shown in fig. 2, and comprises the following steps: acquiring original data of historical faults; constructing a training data set; training a monitoring model; performing monitoring model evaluation and online; and monitoring the state of the equipment in real time and pushing the abnormal information of the equipment.
Specifically, according to historical maintenance records of a warehouse, for equipment and maintenance time corresponding to each record, fault original data of a certain period of time before equipment maintenance is extracted, the period of time comprises a plurality of statistical periods, 1 month is taken as an example of one statistical period, the period of time in the embodiment of the invention is taken as 3 months, and the length of the statistical period and the number of the statistical periods can be adjusted according to actual business. The fault raw data includes fault codes, fault severity levels, fault occurrence times, etc.
And constructing the characteristics describing the state of the equipment from two dimensions of maintenance and failure according to the original data of the failure of the equipment.
The maintenance dimension characteristics include two indicators of historical maintenance times and average maintenance interval time, and the two indicators can basically reflect the historical maintenance condition of the equipment. Wherein the historical number of repairs of the apparatus is the total number of repairs after the apparatus is put into service. The average maintenance interval time of the equipment is the average value of the maintenance interval time of the equipment, the maintenance interval time is the time of two adjacent maintenance intervals, and the average value of all the maintenance interval time is obtained to obtain the average maintenance interval time of the equipment.
The fault dimension characteristics comprise two indexes of fault quantity and fault interval, and the indexes are counted as fault dimension data within 3 months before equipment maintenance. It should be noted that, when there are multiple maintenance records on a device, the number of faults in the fault dimension feature is a mean value of the number of faults of 3 months before each maintenance, where if the interval between two maintenance is less than 3 months, the actual number of faults is converted into the number of 3 months according to a time proportion as the number of faults, for example, a device has three maintenance records, the maintenance time is respectively 4 months 1 day, 8 months 1 day, and 9 months 1 day, and then the number of faults of three months before 4 months 1 day is calculated and denoted as a1; the number of failures three months before 8 months 1 day was designated as a2; the number of failures from 8 months 1 to 9 months 1 is denoted as a3, and the number of failures from 8 months 1 to 9 months 1, a3, is converted into the number of failures for three months, denoted as a3', i.e. a3' =3×y/x, where x is the time between two repairs, in this example y=1, i.e. one month apart, y is the number of failures between two repairs, in this example y=a3, then a3' =3×a3.
The fault interval included in the fault dimension feature is specifically an average value of fault intervals between every two repairs, which may also be referred to as an average fault interval.
Based on the number of faults and the average fault interval, respectively counting the number of faults and the fault interval of 3 months before the maintenance of faults of different grades according to preset fault grades, and obtaining the number of faults of each grade and the average fault interval of each grade.
Assuming n failure levels, each record contains 2+2×n features. Taking three levels of failure class as an example, namely a general failure, a serious failure and a fatal failure, a schematic diagram of maintenance dimension characteristics and failure dimension characteristics of one embodiment of the present invention is shown in fig. 3, and the number of the failures of each level includes a general failure number, a serious failure number and a fatal failure number; the average fault intervals of each class include a general fault average interval, a serious fault average interval and a fatal fault average interval.
Defining the device with history maintenance number > =1 as an abnormal device, the training data set D, D for model input can be obtained in the form shown in table 1.
Table 1 training data set
And taking the acquired training data set as input data of a support vector machine, performing model training, selecting a model by adopting a ten-fold cross validation method, and selecting a model with the minimum prediction error as a final model.
According to the embodiment of the invention, whether the equipment is abnormal or not is judged through fault and maintenance records, the support vector machine model is trained through the training data set, and the trained support vector machine model is used for identifying the abnormal equipment. Assuming that there are N devices in total, each device being considered as one sample point, the data of the N sample points constitutes a training data set d= { (X1, Y1), (X2, Y2), …, (xN, yN) }, where X i∈X＝Rn,yi e y= { -1,1}, i=1, 2,3, …, N, representing the feature X of the i-th device, i.e. the set of maintenance dimension feature, failure dimension feature of the device, Y i representing the class of the i-th device, i.e. the abnormal status tag, in particular abnormal or normal, where Y i =1 represents abnormal and Y i = -1 represents normal, for example.
For the training data set, a radial basis function is selected, and the following optimization problem is constructed and solved:
Obtaining an optimal solution Wherein alpha i is Lagrange multiplier,
Sample points (x 1, y 1), (x 2, y 2), …, (xN, yN) corresponding to the optimal lagrangian multiplier; c is penalty parameter. /(I)In order to support the objective function of the vector machine,Is a constraint.
Selecting a positive component of alpha * Calculating the intercept b of the classification plane as:
Constructing a decision function:
K (x, x i) is a radial basis function.
The final model is deployed on the line for real-time monitoring of the equipment state, dynamically and accurately identifying abnormal equipment, and timely pushing related personnel to overhaul the abnormal equipment, so that equipment faults are effectively reduced, and efficient and stable operation of a warehouse is ensured.
The model of the embodiment of the invention is not limited to a support vector machine, and other machine-learned classification models (such as random forests, neural networks and the like) can be selected.
Fig. 4 is a schematic diagram of main modules of an apparatus for identifying an abnormality device according to an embodiment of the present invention.
As shown in fig. 4, an apparatus 400 for identifying an abnormal device according to an embodiment of the present invention mainly includes: a feature extraction module 401, a training data generation module 402, and an abnormal device identification module 403.
The feature extraction module 401 is configured to extract maintenance dimension features and fault dimension features of each device according to historical fault original data of each device.
The training data generating module 402 is configured to generate a training data set according to the maintenance dimension feature, the fault dimension feature, and the abnormal state label of each device.
The abnormal device identification module 403 is configured to train the monitoring model through the training data set, and monitor the status features of each device in real time by using the trained monitoring model, so as to identify the abnormal device, where the status features of the device include maintenance dimension features and fault dimension features.
In one embodiment, the feature extraction module 401 is specifically configured to: and according to the historical fault original data of each device, counting the historical maintenance times and average maintenance interval time of each device to obtain maintenance dimension characteristics of each device.
The feature extraction module 401 is specifically further configured to: according to historical fault original data of each device, counting the number of faults and average fault intervals of each device in a plurality of counting periods before maintenance, and based on preset fault grades, counting the number of faults of each grade in the number of faults and average fault intervals of each grade in the average fault intervals, so as to obtain fault dimension characteristics of each device according to the number of faults of each grade and the average fault intervals of each grade of each device.
The monitoring model of the embodiment of the invention is realized based on one of a support vector machine, a random forest and a neural network.
In one embodiment, the abnormal device identification module 403 may also be configured to: when the monitoring model is trained, a ten-fold cross validation method is adopted to select the monitoring model with the minimum prediction error as the trained monitoring model.
In one embodiment, the abnormal device identification module 403 may also be configured to: for a training data set, selecting a radial basis function, constructing an objective function of a support vector machine based on the selected radial basis function and abnormal state labels of all devices, and solving the objective function under a preset constraint condition to obtain an optimal solution; calculating the intercept of a classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis function; and obtaining a decision function of the support vector machine based on the optimal solution, the intercept, the abnormal state labels of the devices and the selected radial basis function, wherein the decision function is used for identifying the abnormal devices by the support vector machine.
According to the embodiment of the invention, the factors of equipment maintenance, fault types and quantity in a period are comprehensively considered, a monitoring model for automatically identifying abnormal equipment is established, and the abnormal equipment is dynamically and accurately identified, so that workers can directly replace and repair the abnormal equipment after directly obtaining the information of the abnormal equipment, and the operation efficiency of the unmanned cabin is effectively improved.
In addition, the specific implementation of the device for identifying an abnormal device in the embodiment of the present invention is already described in detail in the method for identifying an abnormal device, so the description is not repeated here.
Fig. 5 illustrates an exemplary system architecture 500 to which a method of identifying an anomalous device or an apparatus of identifying an anomalous device of embodiments of the invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 is used as a medium to provide communication links between the terminal devices 501, 502, 503 and the server 505. The network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 505 via the network 504 using the terminal devices 501, 502, 503 to receive or send messages or the like. Various communication client applications may be installed on the terminal devices 501, 502, 503, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server (by way of example only) providing support for websites browsed by users using the terminal devices 501, 502, 503. The background management server may analyze and process the received data such as the information query request, and feed back the processing result (e.g., device information—only an example) to the terminal device.
It should be noted that, the method for identifying an abnormal device according to the embodiment of the present invention is generally executed by the server 505, and accordingly, the apparatus for identifying an abnormal device is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, there is illustrated a schematic diagram of a computer system 600 suitable for use in implementing a terminal device or server in accordance with an embodiment of the present application. The terminal device or server shown in fig. 6 is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 601.
The computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. 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 involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor comprises a feature extraction module, a training data generation module and an abnormal equipment identification module. The names of these modules do not limit the module itself in some cases, and for example, the feature extraction module may also be described as "a module for extracting maintenance dimension features and fault dimension features of each device according to historical fault raw data of each device".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include: extracting maintenance dimension characteristics and fault dimension characteristics of each device according to historical fault original data of each device; generating a training data set according to the maintenance dimension characteristics and the fault dimension characteristics of each device and the abnormal state labels of each device; and training a monitoring model through the training data set, and monitoring the state characteristics of each device in real time by utilizing the trained monitoring model so as to identify abnormal devices, wherein the state characteristics of the devices comprise the maintenance dimension characteristics and the fault dimension characteristics.
According to the technical scheme of the embodiment of the invention, the maintenance dimension characteristics and the fault dimension characteristics of each device are extracted according to the historical fault original data of each device; generating a training data set according to maintenance dimension characteristics, fault dimension characteristics and abnormal state labels of all the devices; training a monitoring model through a training data set, and monitoring the state characteristics of each device in real time by utilizing the trained monitoring model so as to identify abnormal devices. Abnormal equipment can be automatically and accurately identified, and the abnormal equipment can be timely pushed to equipment maintenance personnel, so that maintenance work can be more pertinently carried out, and the working efficiency is improved.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of identifying an abnormal device, comprising:
extracting maintenance dimension characteristics and fault dimension characteristics of each device according to historical fault original data of each device; the historical fault original data at least comprises fault codes, fault severity grades, fault occurrence time and fault quantity;
generating a training data set according to the maintenance dimension characteristics and the fault dimension characteristics of each device and the abnormal state labels of each device;
And training a monitoring model through the training data set, and monitoring the state characteristics of each device in real time by utilizing the trained monitoring model so as to identify abnormal devices, wherein the state characteristics of the devices comprise the maintenance dimension characteristics and the fault dimension characteristics.
2. The method of claim 1, wherein the historical maintenance times and average maintenance intervals for each device are counted based on the historical failure raw data for each device to obtain maintenance dimension characteristics for each device.
3. The method of claim 1, wherein the number of faults and average fault intervals of each device in a plurality of statistical periods before maintenance are counted according to the historical fault raw data of each device, and the number of faults of each grade in the number of faults and average fault intervals of each grade in the average fault intervals are counted based on preset fault grades, so that fault dimension characteristics of each device are obtained according to the number of faults of each grade and the average fault intervals of each grade of each device.
4. The method of claim 1, wherein the monitoring model is implemented based on one of a support vector machine, a random forest, and a neural network.
5. The method of claim 1, wherein the model is selected by a ten-fold cross-validation method to select the monitoring model with the smallest prediction error as the trained monitoring model when training the monitoring model.
6. The method of claim 1, wherein the training a monitoring model with the training data set comprises:
For the training data set, selecting a radial basis function, constructing an objective function of a support vector machine based on the selected radial basis function and the abnormal state labels of the devices, and solving the objective function under a preset constraint condition to obtain an optimal solution;
calculating the intercept of a classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis function;
And obtaining a decision function of the support vector machine based on the optimal solution, the intercept, the abnormal state labels of the devices and the selected radial basis function, wherein the decision function is used for the support vector machine to identify the abnormal device.
7. An apparatus for identifying an abnormal device, comprising:
the feature extraction module is used for extracting maintenance dimension features and fault dimension features of each device according to the historical fault original data of each device; the historical fault original data at least comprises fault codes, fault severity grades, fault occurrence time and fault quantity;
The training data generation module is used for generating a training data set according to the maintenance dimension characteristics and the fault dimension characteristics of each device and the abnormal state labels of each device;
The abnormal equipment identification module is used for training the monitoring model through the training data set and utilizing the trained monitoring model to monitor the state characteristics of each equipment in real time so as to identify the abnormal equipment, wherein the state characteristics of the equipment comprise the maintenance dimension characteristics and the fault dimension characteristics.
8. The apparatus of claim 7, wherein the feature extraction module is further to: and according to the historical fault original data of each device, counting the historical maintenance times and average maintenance interval time of each device to obtain the maintenance dimension characteristics of each device.
9. An electronic device, comprising:
One or more processors;
A memory for storing one or more programs,
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-6.
10. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010279539.0A CN113537519B (en) | 2020-04-10 | 2020-04-10 | Method and device for identifying abnormal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010279539.0A CN113537519B (en) | 2020-04-10 | 2020-04-10 | Method and device for identifying abnormal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113537519A CN113537519A (en) | 2021-10-22 |
| CN113537519B true CN113537519B (en) | 2024-05-24 |
Family
ID=78087743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010279539.0A Active CN113537519B (en) | 2020-04-10 | 2020-04-10 | Method and device for identifying abnormal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113537519B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681427B (en) * | 2023-08-03 | 2024-01-05 | 深圳市新启发汽车用品有限公司 | Self-help purchasing method and system for automobile accessories based on intelligent algorithm |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102221655A (en) * | 2011-06-16 | 2011-10-19 | 河南省电力公司济源供电公司 | Random-forest-model-based power transformer fault diagnosis method |
| CN107590506A (en) * | 2017-08-17 | 2018-01-16 | 北京航空航天大学 | A kind of complex device method for diagnosing faults of feature based processing |
| CN108108765A (en) * | 2017-12-28 | 2018-06-01 | 北京理工大学 | It is a kind of based on probability density than data fusion equipment fault diagnosis method |
| CN108344812A (en) * | 2017-11-24 | 2018-07-31 | 北京国网富达科技发展有限责任公司 | A kind of Diagnosis Method of Transformer Faults, device and storage medium |
| CN108491580A (en) * | 2018-02-26 | 2018-09-04 | 上海理工大学 | A kind of equipment fault diagnosis apparatus and system |
| CN109204389A (en) * | 2018-09-12 | 2019-01-15 | 济南轨道交通集团有限公司 | A kind of subway equipment fault diagnosis and self-healing method, system |
| CN109254577A (en) * | 2018-08-08 | 2019-01-22 | 佛山科学技术学院 | A kind of intelligence manufacture procedure fault classification method and device based on deep learning |
| CN109657709A (en) * | 2018-12-06 | 2019-04-19 | 湖北博华自动化系统工程有限公司 | A kind of equipment fault prediction technique based on particle group optimizing support vector regression |
| CN110879971A (en) * | 2019-10-23 | 2020-03-13 | 上海宝信软件股份有限公司 | Method and system for predicting abnormal operation condition of industrial production equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7086803B2 (en) * | 2018-09-27 | 2022-06-20 | 株式会社東芝 | Anomaly detection device, anomaly detection method and program |
-
2020
- 2020-04-10 CN CN202010279539.0A patent/CN113537519B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102221655A (en) * | 2011-06-16 | 2011-10-19 | 河南省电力公司济源供电公司 | Random-forest-model-based power transformer fault diagnosis method |
| CN107590506A (en) * | 2017-08-17 | 2018-01-16 | 北京航空航天大学 | A kind of complex device method for diagnosing faults of feature based processing |
| CN108344812A (en) * | 2017-11-24 | 2018-07-31 | 北京国网富达科技发展有限责任公司 | A kind of Diagnosis Method of Transformer Faults, device and storage medium |
| CN108108765A (en) * | 2017-12-28 | 2018-06-01 | 北京理工大学 | It is a kind of based on probability density than data fusion equipment fault diagnosis method |
| CN108491580A (en) * | 2018-02-26 | 2018-09-04 | 上海理工大学 | A kind of equipment fault diagnosis apparatus and system |
| CN109254577A (en) * | 2018-08-08 | 2019-01-22 | 佛山科学技术学院 | A kind of intelligence manufacture procedure fault classification method and device based on deep learning |
| CN109204389A (en) * | 2018-09-12 | 2019-01-15 | 济南轨道交通集团有限公司 | A kind of subway equipment fault diagnosis and self-healing method, system |
| CN109657709A (en) * | 2018-12-06 | 2019-04-19 | 湖北博华自动化系统工程有限公司 | A kind of equipment fault prediction technique based on particle group optimizing support vector regression |
| CN110879971A (en) * | 2019-10-23 | 2020-03-13 | 上海宝信软件股份有限公司 | Method and system for predicting abnormal operation condition of industrial production equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113537519A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107809331B (en) | Method and device for identifying abnormal flow | |
| US11144582B2 (en) | Method and system for parsing and aggregating unstructured data objects | |
| CN106716454B (en) | Identifying non-technical losses using machine learning | |
| CN109471783B (en) | Method and device for predicting task operation parameters | |
| CN109446274A (en) | The method and apparatus of big data platform BI metadata management | |
| CN112348321A (en) | Risk user identification method and device and electronic equipment | |
| CN112016793B (en) | Resource allocation method and device based on target user group and electronic equipment | |
| CN113780329A (en) | Method, apparatus, server and medium for identifying data anomalies | |
| CN113379391A (en) | Work order processing method and device, electronic equipment and computer readable storage medium | |
| CN116302893A (en) | Device performance evaluation method and device, electronic device and storage medium | |
| CN115860694A (en) | Business expansion process management and control method and system based on instant message technology | |
| CN113537519B (en) | Method and device for identifying abnormal equipment | |
| CN112163154A (en) | Data processing method, device, equipment and storage medium | |
| CN117132315A (en) | Active user prediction method, device, equipment and storage medium | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN113052509B (en) | Model evaluation method, model evaluation device, electronic apparatus, and storage medium | |
| CN115718806A (en) | System commissioning problem management method, apparatus, device, medium, and program product | |
| US11869060B2 (en) | Automated and customized entitlement recommendation | |
| CN114897613A (en) | Abnormal transaction behavior detection method and system, electronic device and storage medium | |
| CN112508631A (en) | User policy distribution method and device and electronic equipment | |
| CN109726882A (en) | The method and apparatus that a kind of pair of object is evaluated | |
| US20240242159A1 (en) | Automated enterprise information technology alerting system | |
| Chu et al. | Enhancing the customer service experience in call centers using preemptive solutions and queuing theory | |
| CN117371856A (en) | Data quality monitoring method and device, storage medium and computer equipment | |
| Goyal et al. | Data-driven risk analysis for poles in the electric grid |
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 |