CN113537519A - Method and device for identifying abnormal equipment - Google Patents
Method and device for identifying abnormal equipment Download PDFInfo
- Publication number
- CN113537519A CN113537519A CN202010279539.0A CN202010279539A CN113537519A CN 113537519 A CN113537519 A CN 113537519A CN 202010279539 A CN202010279539 A CN 202010279539A CN 113537519 A CN113537519 A CN 113537519A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- fault
- abnormal
- equipment
- failure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012423 maintenance Methods 0.000 claims abstract description 90
- 238000012544 monitoring process Methods 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 59
- 230000006870 function Effects 0.000 claims description 51
- 238000012706 support-vector machine Methods 0.000 claims description 31
- 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
- 230000002547 anomalous effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 7
- 230000008439 repair process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process 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
- 230000005856 abnormality Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (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: extracting maintenance dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device; generating a training data set according to the maintenance dimensional characteristics and the fault dimensional 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 piece of equipment in real time by using the trained monitoring model so as to identify abnormal equipment, wherein the state characteristics of the equipment comprise the maintenance dimension characteristics and the fault dimension characteristics. According to the implementation mode, abnormal equipment can be automatically and accurately identified and timely pushed to equipment maintenance personnel, so that the maintenance work can be carried out more pertinently, and the working efficiency is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for identifying abnormal equipment.
Background
In order to ensure the long-term stable operation of the unmanned storehouse, the fault conditions of the equipment in the unmanned storehouse need to be regularly counted so as to find out abnormal equipment and timely overhaul the abnormal equipment. The current identification of abnormal equipment is only to simply count the severity level and the number of the equipment faults in a period of time, manually select the equipment with high fault level and large number as the abnormal equipment, and manually push the abnormal equipment to warehouse equipment maintenance personnel.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
the artificial recognition of equipment faults is unilateral, and the equipment cannot be rush-repaired in a targeted and timely manner, so that the working efficiency is influenced.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for identifying an abnormal device, which can automatically and accurately identify the abnormal device and timely push the abnormal device to a device maintenance worker, so that the device maintenance worker can perform maintenance more specifically, and work efficiency is improved.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a method of identifying an abnormal device.
A method of identifying an anomalous device comprising: extracting maintenance dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device; generating a training data set according to the maintenance dimensional characteristics and the fault dimensional 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 piece of equipment in real time by using the trained monitoring model so as to identify abnormal equipment, wherein the state characteristics of the equipment comprise the maintenance dimension characteristics and the fault dimension characteristics.
Optionally, according to the historical failure original data of each device, the historical maintenance times and the average maintenance interval time of each device are counted to obtain the maintenance dimensional characteristics of each device.
Optionally, according to the historical failure original data of each device, the failure number and the average failure interval of each device in a plurality of statistical periods before maintenance are counted, and based on a preset failure level, the failure number of each level in the failure number and the average failure interval of each level in the average failure interval are counted, so that the failure dimension characteristic of each device is obtained according to the failure number of each level and the average failure interval of each level 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, a ten-fold cross validation method is used to select the model, so as to select the monitoring model with the smallest prediction error as the trained monitoring model.
Optionally, the training of the monitoring model by the training data set includes: selecting a radial basis kernel function for the training data set, constructing an objective function of a support vector machine based on the selected radial basis kernel 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 the classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis kernel 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 kernel function, wherein the decision function is used for the support vector machine to identify the abnormal devices.
According to another aspect of the embodiments of the present invention, there is provided an apparatus for identifying an abnormal device.
An apparatus for identifying an anomalous device comprising: the characteristic extraction module is used for extracting maintenance dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device; the training data generation module is used for generating a training data set according to the maintenance dimensional characteristics and the fault dimensional characteristics of each device and the abnormal state labels of each device; and the abnormal equipment identification module is used for training the monitoring model through the training data set and monitoring the state characteristics of each piece of equipment in real time by using the trained monitoring model so as to identify 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 failure original data of each device, counting the historical maintenance times and the 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, the fault number and the average fault interval of each device in a plurality of statistical periods before maintenance are counted, and based on preset fault levels, the fault number of each level in the fault number and the average fault interval of each level in the average fault interval are counted, so that the fault dimension characteristics of each device are obtained according to the fault number of each level and the average fault interval of each level 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, and selecting the monitoring model with the minimum prediction error as the trained monitoring model.
Optionally, the abnormal device identification module is further configured to: selecting a radial basis kernel function for the training data set, constructing an objective function of a support vector machine based on the selected radial basis kernel 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 the classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis kernel 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 kernel function, wherein the decision function is used for the support vector machine to identify the abnormal devices.
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; a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for identifying an abnormal device provided by embodiments of the present invention.
According to yet another aspect of an embodiment of the present invention, a computer-readable medium is provided.
A computer readable medium, on which a computer program is stored, 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 dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device; generating a training data set according to the maintenance dimensional characteristics and the fault dimensional characteristics of each device and the abnormal state labels of each device; and training the monitoring model through the training data set, and monitoring the state characteristics of each device in real time by using the trained monitoring model so as to identify abnormal devices. Abnormal equipment can be automatically and accurately identified and timely pushed to equipment maintenance personnel, so that the maintenance work can be carried out more pertinently, and the working efficiency is improved.
Further effects of the above-mentioned non-conventional alternatives will be 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 one embodiment of the invention;
FIG. 2 is a schematic flow diagram of an apparatus for identifying anomalies, according to one embodiment of the invention;
FIG. 3 is a schematic diagram of a repair dimensional feature and a fault dimensional feature according to one embodiment of the invention;
FIG. 4 is a schematic diagram of the main modules of an apparatus for identifying abnormal devices according to one embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as 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 the main steps of a method of identifying an abnormal device according to one embodiment of the present invention.
As shown in fig. 1, the method for 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 dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device.
Step S102: and generating a training data set according to the maintenance dimensional characteristics and the fault dimensional characteristics of each device and the abnormal state labels of each device.
Step S103: and training the monitoring model through a training data set, and monitoring the state characteristics of each device in real time by using 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, according to historical failure original data of each device, historical maintenance times and average maintenance interval time of each device are counted to obtain maintenance dimensional characteristics of each device.
The historical failure raw data of each equipment can be obtained according to the historical maintenance records of the warehouse, and specifically, the failure raw data of a certain time period before the equipment is maintained, including failure codes, failure severity levels, failure occurrence time and the like, are extracted according to the equipment and the maintenance time corresponding to each record.
In one embodiment, the fault number and the average fault interval of each device in a plurality of statistical periods before maintenance are counted according to historical fault original data of each device, and the fault number of each level in the fault number and the average fault interval of each level in the average fault interval are counted on the basis of preset fault levels, so that the fault dimension characteristics of each device are obtained according to the fault number of each level and the average fault interval of each level of each device.
The abnormal state label of the device indicates the category of the device, and the category includes abnormal and normal, for example, the abnormal state label is 1 to indicate abnormal, and the abnormal state label is-1 to indicate normal.
In one embodiment, the monitoring model is based on one implementation of a support vector machine, a random forest, a neural network.
In one embodiment, when the monitoring model is trained, a ten-fold cross validation method is adopted to select the model, so that the monitoring model with the smallest prediction error is selected as the trained monitoring model. Specifically, the training data set may be divided into a plurality of subsets, and a plurality of combinations of the training set and the test set may be generated according to the plurality of subsets, for example, the number of the subsets is 10, and then each combination takes one of the subsets as the test set and the other subsets as the training set, so that 10 combinations may be obtained. And training the monitoring model 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, the monitoring model is trained with a training data set, comprising: selecting a radial basis kernel function for the training data set, constructing an objective function of a support vector machine based on the selected radial basis kernel function and the abnormal state labels of the devices, and solving the objective function under a preset constraint condition to obtain an optimal solution, wherein the preset constraint condition is the 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 kernel function; and obtaining a decision function of the support vector machine based on the optimal solution, the intercept, the abnormal state label of each device and the selected radial basis kernel function, wherein the decision function represents an optimal hyperplane (classification plane) of the support vector machine and is used for the support vector machine to identify the abnormal device. As will be described in more detail below.
In one embodiment, after the abnormal device is identified, pushing the abnormal device information to the specified client is further included. The designated client may be a client of a person involved in maintenance or the like.
In the prior art, only the equipment fault condition in the current statistical period is considered, the equipment fault condition in the current 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 cycles, thereby improving the identification accuracy.
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 conditions of the equipment. On the basis of fault data, the embodiment of the invention trains the model by using the frequency information and the historical fault information, comprehensively reflects the abnormal condition of the equipment, realizes automatic and accurate identification of the abnormal equipment, and overcomes the defect that the conventional method for artificially selecting the abnormal equipment lacks a unified and fixed standard.
The method for identifying the abnormal equipment in the embodiment of the invention can be used for identifying the abnormal equipment in various equipment sets. The following describes the method for identifying abnormal devices according to the embodiment of the present invention in detail by taking a device set formed by devices in an unmanned warehouse as an example.
One embodiment of the present invention utilizes historical failure raw data to identify and establish a monitoring model with supervised learning for abnormal equipment in an unmanned storehouse, and a flow diagram for identifying abnormal equipment is shown in fig. 2, and includes: acquiring historical fault original data; constructing a training data set; training a monitoring model; evaluating and online-putting the monitoring model; and monitoring the state of the equipment in real time and pushing abnormal information of the equipment.
Specifically, according to historical maintenance records of the warehouse, for equipment and maintenance time corresponding to each record, original fault data of a certain time period before the equipment is maintained is extracted, the time period comprises a plurality of statistical cycles, for example, one statistical cycle is 1 month, the time period of the embodiment of the invention is taken as 3 months, and the length of the statistical cycles and the number of the statistical cycles can be adjusted according to actual services. The failure raw data comprises failure codes, failure severity levels, failure occurrence time and the like.
Features describing the state of the equipment are constructed from both the repair and fault dimensions based on the fault raw data for the equipment.
The maintenance dimension characteristics comprise two indexes of historical maintenance times and average maintenance interval time, and the two indexes can basically reflect the historical maintenance condition of the equipment. Wherein the historical maintenance times of the equipment is the total maintenance times after the equipment is put into use. 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 the fault quantity and the fault interval, and the index counts fault dimension data within 3 months before equipment maintenance. It should be noted that, when the equipment has multiple maintenance records, the number of faults in the fault dimension feature is the average value of the number of faults of 3 months before each maintenance, wherein if the interval between two times of maintenance is less than 3 months, the actual number of faults is converted into the number of 3 months in proportion to time as the number of faults, for example, if a certain equipment has three maintenance records, and the maintenance time is respectively 4 months 1 day, 8 months 1 day, and 9 months 1 day, the number of faults of three months before 4 months 1 day is calculated and recorded as a 1; the number of failures three months before 8 months and 1 day is recorded as a 2; the number of faults from 8 month 1 to 9 month 1 is denoted as a3, and the number of faults a3 from 8 month 1 to 9 month 1 is converted into the number of faults for three months, denoted as a3', that is, a3' is 3 × y ÷ x, where x is the time between two repairs, in this case y is 1, i.e., one month apart, and y is the number of faults between two repairs, in this case y is a3, and then a3' is 3 × a 3.
The fault interval included in the fault dimension feature is specifically a mean value of fault intervals between every two repairs, and may also be referred to as a mean fault interval.
On the basis of the fault number and the average fault interval, respectively counting the fault number and the fault interval of 3 months before the fault maintenance of different levels according to preset fault levels to obtain the fault number and the average fault interval of each level.
Assuming n failure levels, each record contains 2+2 × n features. Taking the fault grades divided into three grades of general fault, serious fault and fatal fault as an example, a schematic diagram of the maintenance dimensional characteristic and the fault dimensional characteristic of one embodiment of the invention is shown in fig. 3, wherein the fault quantity of each grade comprises general fault quantity, serious fault quantity and fatal fault quantity; the average fault intervals of each grade comprise average fault intervals of general faults, average fault intervals of serious faults and average fault intervals of fatal faults.
If the device with the historical repair time > 1 is defined as an abnormal device, a training data set D for model input can be obtained, and the form of D is shown in table 1.
TABLE 1 training data set
And taking the obtained training data set as input data of a support vector machine, carrying out model training, selecting a model with the minimum prediction error as a final model by adopting a ten-fold cross validation method.
According to the embodiment of the invention, whether the equipment is abnormal or not is judged through the fault and maintenance record, the support vector machine model is trained through the training data set, and the trained support vector machine model is used for identifying abnormal equipment. Assuming a total of N devices, each device being considered as a sample point, the data of the N sample points form a training data set D { (x1, y1), (x2, y2), …, (xN, yN) }, where x is equal to x, y, and x is equal to y, x, y, and y, x, yi∈X＝Rn，yiE.y { -1,1}, i { -1, 2,3, …, N, taking (xi, yi) as an example, represents the feature X of the i-th equipment, i.e., the set of the maintenance dimension feature and the fault dimension feature of the equipment, YiA class indicating the ith device, i.e. an abnormal status tag, in particular abnormal or normal, where yi1 denotes an abnormality, yiNormal is indicated by-1.
For the above training data set, the radial basis kernel function is selected, and the following optimization problem is constructed and solved:
solving for the optimal solution
Wherein alpha isiIn order to be a lagrange multiplier,
Selection of alpha*A positive component of
Calculating the intercept b of the classification plane as:
constructing a decision function:
K(x,xi) Is a radial basis kernel function.
And deploying the final model on a line for monitoring the state of the equipment in real time, dynamically and accurately identifying abnormal equipment, and timely pushing related personnel to overhaul the abnormal equipment, so that equipment faults are effectively reduced, and the efficient and stable operation of a warehouse is guaranteed.
The model of the embodiment of the invention is not limited to the support vector machine, and other machine learning classification models (such as random forest, neural network and the like) can be selected.
Fig. 4 is a schematic diagram of main blocks of an apparatus for identifying an abnormal device according to an embodiment of the present invention.
As shown in fig. 4, the 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 a maintenance dimension feature and a fault dimension feature of each device according to historical fault original data of each device.
A training data generating module 402, configured to generate a training data set according to the maintenance dimensional feature and the fault dimensional feature of each device 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 characteristics of each device in real time by using the trained monitoring model to identify an abnormal device, where the status characteristics of the device include a maintenance dimension characteristic and a fault dimension characteristic.
In one embodiment, the feature extraction module 401 is specifically configured to: and according to the historical failure original data of each device, counting the historical maintenance times and the average maintenance interval time of each device to obtain the maintenance dimension characteristics of each device.
The feature extraction module 401 is further specifically configured to: according to historical fault original data of each device, the fault number and the average fault interval of each device in a plurality of statistical periods before maintenance are counted, and based on preset fault levels, the fault number of each level in the fault number and the average fault interval of each level in the average fault interval are counted, so that the fault dimension characteristics of each device are obtained according to the fault number of each level and the average fault interval of each level 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 be further configured to: when the monitoring model is trained, a ten-fold cross validation method is adopted to select the model, and the monitoring model with the minimum prediction error is selected as the trained monitoring model.
In one embodiment, the abnormal device identification module 403 may be further configured to: selecting a radial basis kernel function for a training data set, constructing a target function of a support vector machine based on the selected radial basis kernel function and the abnormal state labels of each device, and solving the target 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 kernel 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 kernel function, wherein the decision function is used for the support vector machine to identify the abnormal devices.
The embodiment of the invention comprehensively considers the factors of equipment maintenance, fault types and quantity in a period of time, establishes the monitoring model for automatically identifying the abnormal equipment, and dynamically and accurately identifies the abnormal equipment, so that the worker can directly replace and repair the abnormal equipment after directly obtaining the information of the abnormal equipment, and the operating efficiency of the unmanned storehouse is effectively improved.
In addition, the detailed implementation of the apparatus for identifying abnormal devices in the embodiment of the present invention has been described in detail in the above method for identifying abnormal devices, so that the repeated description is not repeated here.
Fig. 5 illustrates an exemplary system architecture 500 to which the method of identifying an abnormal device or the apparatus for identifying an abnormal device of the embodiments of the present 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 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the terminal devices 501, 502, 503. The backend management server may analyze and perform other processing on the received data such as the information query request, and feed back a processing result (for example, device information — just an example) to the terminal device.
It should be noted that the method for identifying an abnormal device provided by 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, shown is a block diagram of a computer system 600 suitable for use in implementing a terminal device or server of an embodiment of the present application. The terminal device or the server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the 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 that 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 necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via 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, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; 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 driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the 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 illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the present application are executed when the computer program is executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination 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 present application, 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 this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. 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 flowchart 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 described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises a feature extraction module, a training data generation module and an abnormal equipment identification module. The names of the modules do not constitute a limitation to the modules themselves in some cases, 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 separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: extracting maintenance dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device; generating a training data set according to the maintenance dimensional characteristics and the fault dimensional 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 piece of equipment in real time by using the trained monitoring model so as to identify abnormal equipment, wherein the state characteristics of the equipment comprise the maintenance dimension characteristics and the fault dimension characteristics.
According to the technical scheme of the embodiment of the invention, maintenance dimensional characteristics and fault dimensional characteristics of each device are extracted according to historical fault original data of each device; generating a training data set according to the maintenance dimensional characteristics and the fault dimensional characteristics of each device and the abnormal state labels of each device; and training the monitoring model through the training data set, and monitoring the state characteristics of each device in real time by using the trained monitoring model so as to identify abnormal devices. Abnormal equipment can be automatically and accurately identified and timely pushed to equipment maintenance personnel, so that the maintenance work can be carried out more pertinently, and the working efficiency is improved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of identifying an anomalous device comprising:
extracting maintenance dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device;
generating a training data set according to the maintenance dimensional characteristics and the fault dimensional 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 piece of equipment in real time by using the trained monitoring model so as to identify abnormal equipment, wherein the state characteristics of the equipment comprise the maintenance dimension characteristics and the fault dimension characteristics.
2. The method according to claim 1, wherein historical maintenance times and average maintenance interval time of each device are counted according to historical failure raw data of the devices to obtain maintenance dimensional characteristics of the devices.
3. The method according to claim 1, wherein the failure number and the average failure interval of each device in a plurality of statistical cycles before maintenance are counted according to the historical failure raw data of each device, and the failure number of each level in the failure number and the average failure interval of each level in the average failure interval are counted based on preset failure levels, so that the failure dimension characteristics of each device are obtained according to the failure number of each level and the average failure interval of each level 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 according to claim 1, wherein in training the monitoring model, a ten-fold cross validation method is used to select a model, so as to select a monitoring model with the smallest prediction error as the trained monitoring model.
6. The method of claim 1, wherein training a monitoring model with the training data set comprises:
selecting a radial basis kernel function for the training data set, constructing an objective function of a support vector machine based on the selected radial basis kernel 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 the classification plane of the support vector machine based on the optimal solution, the abnormal state labels of the devices and the selected radial basis kernel 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 kernel function, wherein the decision function is used for the support vector machine to identify the abnormal devices.
7. An apparatus for identifying an abnormal device, comprising:
the characteristic extraction module is used for extracting maintenance dimensional characteristics and fault dimensional characteristics of each device according to historical fault original data of each device;
the training data generation module is used for generating a training data set according to the maintenance dimensional characteristics and the fault dimensional characteristics of each device and the abnormal state labels of each device;
and the abnormal equipment identification module is used for training the monitoring model through the training data set and monitoring the state characteristics of each piece of equipment in real time by using the trained monitoring model so as to identify 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 configured to: and according to the historical failure original data of each device, counting the historical maintenance times and the 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 recited in any of claims 1-6.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010279539.0A CN113537519B (en) | 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 | Method and device for identifying abnormal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113537519A true CN113537519A (en) | 2021-10-22 |
| CN113537519B CN113537519B (en) | 2024-05-24 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681427A (en) * | 2023-08-03 | 2023-09-01 | 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 (10)
| 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 |
| US20200104224A1 (en) * | 2018-09-27 | 2020-04-02 | Kabushiki Kaisha Toshiba | Anomaly detection device, anomaly detection method and storage medium |
Patent Citations (10)
| 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 |
| US20200104224A1 (en) * | 2018-09-27 | 2020-04-02 | Kabushiki Kaisha Toshiba | Anomaly detection device, anomaly detection method and storage medium |
| 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 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116681427A (en) * | 2023-08-03 | 2023-09-01 | 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 |
| 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 |
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 | |
| CN109471783B (en) | Method and device for predicting task operation parameters | |
| CN106570778A (en) | Big data-based data integration and line loss analysis and calculation method | |
| CN109960635B (en) | Monitoring and alarming method, system, equipment and storage medium of real-time computing platform | |
| CN113918139A (en) | Identifying non-technical losses using machine learning | |
| 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 | |
| CN111181757B (en) | Information security risk prediction method and device, computing equipment and storage medium | |
| CN117234844A (en) | Cloud server abnormality management method and device, computer equipment and storage medium | |
| CN116843395A (en) | Alarm classification method, device, equipment and storage medium of service system | |
| CN112163154A (en) | Data processing method, device, equipment and storage medium | |
| CN113537519B (en) | Method and device for identifying abnormal equipment | |
| CN115759401A (en) | Method and system for generating bidding behavior prediction labels of members in power market | |
| CN113537519A (en) | Method and device for identifying abnormal equipment | |
| CN111448551A (en) | Method and system for tracking application activity data from a remote device and generating corrective action data structures for the remote device | |
| US11869060B2 (en) | Automated and customized entitlement recommendation | |
| CN113052509A (en) | Model evaluation method, model evaluation apparatus, electronic device, and storage medium | |
| CN112734352A (en) | Document auditing method and device based on data dimensionality | |
| CN110704390B (en) | Method, device, electronic equipment and medium for acquiring server maintenance script | |
| 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 | |
| CN116956086A (en) | Data monitoring and early warning method and device, electronic equipment and storage medium | |
| CN115409381A (en) | Line loss cause determination method and device, electronic equipment and storage medium | |
| CN112580971A (en) | Method and device for checking effectiveness of external institution rating |
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 |