CN110765486B - Asset fault identification method - Google Patents
Asset fault identification method Download PDFInfo
- Publication number
- CN110765486B CN110765486B CN201911012875.2A CN201911012875A CN110765486B CN 110765486 B CN110765486 B CN 110765486B CN 201911012875 A CN201911012875 A CN 201911012875A CN 110765486 B CN110765486 B CN 110765486B
- Authority
- CN
- China
- Prior art keywords
- data
- asset
- fault
- operation information
- information data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013145 classification model Methods 0.000 claims abstract description 21
- 238000012423 maintenance Methods 0.000 claims abstract description 9
- 238000007726 management method Methods 0.000 claims description 54
- 230000006870 function Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 12
- 238000013501 data transformation Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011551 log transformation method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 108010028984 3-isopropylmalate dehydratase Proteins 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Debugging And Monitoring (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an asset fault identification method which is used for carrying out fault detection on information infrastructure assets. The invention installs the baseboard management controller on the managed asset, and constructs the operation and maintenance data network and the out-of-band management system, so as to acquire the collected managed asset operation information data on the baseboard management controller, marks and preprocesses the managed asset operation information data, inputs the preprocessed managed asset operation information data into the constructed classification model based on cost sensitive learning, thereby outputting the prediction probability that the asset is a device fault, and comparing the prediction probability with the set threshold value to judge whether the asset is a fault device. The invention solves the problem that the staff can not rapidly and accurately judge the fault equipment and the defect of the fault sample in the asset equipment in the prior art, realizes the informationized management of the asset and improves the working efficiency.
Description
Technical Field
The invention relates to the technical field of asset management, in particular to an asset fault identification method.
Background
Information infrastructure assets include general purpose storage devices, networks, and communication devices, among others. Currently, with the development of informatization technology, information infrastructure is applied to businesses to provide support and assistance for the businesses. The normal operation of the information infrastructure is an important guarantee for ensuring sustainable operation of organization services.
In the conventional management of information infrastructure, a worker is required to periodically check the information infrastructure according to a working experience, and confirm the operation state of the infrastructure by performing on-site detection on the information infrastructure, determine the fault type of the information infrastructure, and repair or replace the failed infrastructure. Due to the large number of infrastructures, the distribution is wide. In the prior art, workers cannot rapidly and accurately judge fault equipment and fault types, and the working efficiency is greatly reduced.
Disclosure of Invention
The application provides an asset fault identification method, which solves the problem that in the prior art, a worker cannot quickly and accurately judge fault equipment and a fault sample in asset equipment.
The asset fault identification method provided by the application comprises the following steps:
step S1: the baseboard management controller monitors and collects the managed asset operation information data;
step S2: the out-of-band management system acquires the managed asset operation information data from the baseboard management controller through the operation and maintenance data network;
step S3: the out-of-band management system marks the acquired managed asset operation information data to form tag data;
step S4: performing data preprocessing operation on the tag data, and taking the tag data subjected to the preprocessing operation as training data;
step S5: constructing a classification model based on cost sensitive learning, inputting training data into the classification model for training to obtain a trained classification model based on cost sensitive learning, inputting preprocessed real-time data into the trained classification model based on cost sensitive learning to obtain a prediction probability of the managed asset as fault equipment;
step S6: comparing the prediction probability with a preset threshold value, and judging whether the managed asset is faulty equipment or normal equipment according to a comparison result;
step S7: and the out-of-band management system outputs a final judging result.
Preferably, an out-of-band management interface technology is adopted to construct a transport data network, and a B/S framework is adopted to construct an out-of-band management system.
Preferably, the out-of-band management system receives the data of the baseboard management controller and stores the collected data in a system event log by using an instruction specified in the intelligent platform management interface specification.
Preferably, in step S2, the managed asset operation information data includes temperature, voltage, fan rotation speed, power status, CPU, memory utilization, and fault asset operation information data, and the fault asset operation information data includes actual fault asset operation information data and artificial simulated fault asset operation information data.
Preferably, in step S3, the asset operation information data is manually marked, and both the actual fault asset operation information data and the manually simulated fault asset operation information data are marked as fault devices, and the other asset operation information data are marked as normal devices.
Preferably, in step S4, the process of preprocessing the training data includes data cleaning, data transformation and data normalization; the data cleaning is used for removing abnormal data; the data transformation is carried out by carrying out logarithmic transformation on long-tail distribution data to ensure that the long-tail distribution data accords with normal distribution and meets the assumption condition of a linear model; the data normalization reduces the size difference between characteristic values by carrying out dimensionless processing on numerical characteristics, and avoids the interference of data with larger orders of magnitude to data with smaller orders of magnitude.
Preferably, in the data transformation process, log transformation is performed on long tail distribution characteristics through data exploration and analysis, and the specific calculation process is as follows:
A'=log(A);
wherein A is long tail distribution characteristics, A' is the result of logarithmic transformation of the long tail distribution characteristics A;
the calculation formula for normalizing the data is:
wherein X is the value of a certain column of features, mu represents the mean value of the features X, and sigma represents the standard deviation of the features X;
after the characteristic value X is centered according to the mean value mu and scaled according to the standard deviation sigma, the characteristic value X obeys normal distribution with the mean value 0 and the variance 1.
Preferably, in step S5, the objective function of the classification model based on cost sensitive learning is:
wherein C is 0 And C 1 Penalty factors for misclassification of normal equipment and fault equipment respectively; l (y) i ,f θ (x i ) Is a loss function; y is i Representing the true tag class of the ith device; f (f) θ (x i ) A prediction function of a classification model based on cost sensitive learning; θ represents the prediction function f θ (x i ) Parameters of (2); x is x i Characteristic data representing an ith device, λR (θ) being a regularization term representing a penalty to the complex model; lambda is equal to or greater than 0 and is a regularization coefficient used for balancing experience risks and model complexity; r (θ) is the model complexity.
The calculation formula for calculating the prediction probability of the managed asset as the faulty device is:
p(x i )=f θ (x i );
preferably, in step S5, the process of preprocessing the real-time data includes two steps of data transformation and data normalization.
Preferably, in step S6, if the prediction probability is greater than the threshold value, the managed asset is determined to be a faulty device, and if the prediction probability is less than the threshold value, the managed asset is determined to be a normal device; the specific formula for comparing the predicted probability of a managed asset being a faulty device to a threshold value is as follows:
wherein F represents equipment failure, T represents equipment normal, y (x i ) The prediction result of the ith device is shown, and only two results of the fault device and the normal device are taken; p (x) i ) Representing a predicted probability of the i-th device; alpha is a threshold value.
From the above technical scheme, the application has the following advantages:
according to the method, the base plate management controller is installed on the managed asset, collected managed asset operation information data on the base plate management controller is obtained through construction of the operation and maintenance data network and the out-of-band management system, then the managed asset operation information data are marked and preprocessed, the preprocessed managed asset operation information data are input into the constructed classification model based on cost sensitive learning, so that the prediction probability that the asset is equipment failure is output, and the prediction probability is compared with a set threshold value to judge whether the asset is failure equipment.
According to the technical scheme, the managed asset operation information data is collected, the managed asset is automatically detected based on the collected data, whether the asset is a fault asset or not is judged, the defect that the detection needs to be carried out manually in the prior art is overcome, the time cost and the labor cost are greatly saved, and the working efficiency is greatly improved;
another of the above technical solutions has the following advantages: the out-of-band management interface technology is used for collecting the running state information data of the information infrastructure installed on the managed asset to realize asset informatization management, so that the asset management efficiency is improved, and a classification model based on cost sensitive learning is used in the process of discriminating the asset, so that the problem of unbalanced classification can be effectively solved, and the fault equipment can be accurately identified.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of one embodiment of an asset fault identification method provided by the present invention;
fig. 2 is a structural framework diagram of an embodiment of an asset fault identification method provided by the present invention.
Detailed Description
The embodiment of the invention provides an asset fault identification method, which is used for solving the defect that the information infrastructure needs to be checked manually and periodically in the management process of the information infrastructure in the prior art, so that the purposes, the characteristics and the advantages of the invention can be more obvious and understandable, the technical scheme in the embodiment of the invention is clearly and completely described below by combining the drawings in the embodiment of the invention, and obviously, the embodiment described below is only a part of the embodiments of the invention and not all the embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1 and fig. 2, fig. 1 is a flowchart of an asset fault identification method according to an embodiment of the present invention. Fig. 2 is a structural framework diagram of an asset fault identification method according to an embodiment of the present invention.
The asset fault identification method provided by the embodiment, as shown in fig. 1, includes the following steps:
step S1: as shown in fig. 2, a baseboard management controller (Baseboard Management Controller, BMC) is installed in the managed asset, and the baseboard management controller is responsible for monitoring and collecting the managed asset operation information data;
step S2: constructing a transport data network and an out-of-band management system by adopting an out-of-band management interface technology (Intelligent Platform Management Interface, IPMI); the out-of-band management system accesses a baseboard management controller of the managed asset through the operation and maintenance data network, and collects the managed asset operation information data from the baseboard management controller; the out-of-band management system performs centralized management on the asset equipment through a dedicated operation and maintenance data network channel independent of service data, realizes connection between the operation and maintenance asset equipment and the out-of-band management system through the baseboard management controller, transmits control information and data information through an operation and maintenance data network which is separated from the service data network, performs data acquisition on various physical indexes of the managed asset, transmits the data to the out-of-band management system, and executes various control instructions from the out-of-band management system to realize automatic discovery and operation state monitoring of the managed asset equipment.
Step S3: the out-of-band management system marks the collected managed asset operation information data to form tag data;
step S4: performing data preprocessing operation on the tag data, and taking the preprocessed tag data as training data;
step S5: constructing a cost-sensitive learning-based classification model, inputting training data into the cost-sensitive learning-based classification model for training to obtain a trained cost-sensitive learning-based classification model, and inputting preprocessed real-time data into the trained cost-sensitive learning-based classification model to obtain the probability that the managed asset is a fault device;
step S6: setting a threshold value in the out-of-band management system, comparing the prediction probability of the managed asset as the fault device with the threshold value, judging the managed asset as the fault device if the prediction probability is larger than the threshold value, and judging the managed asset as the normal device if the prediction probability is smaller than the threshold value;
step S7: and the out-of-band management system outputs a final judging result.
As a preferred embodiment, in step S2, an out-of-band management interface technology is adopted to construct an operation and maintenance data network, a B/S framework is adopted to construct an out-of-band management system, and the out-of-band management system realizes automatic discovery and operation state monitoring of assets by remotely accessing a baseboard management controller of the managed assets;
as a preferred embodiment, the out-of-band management system receives the baseboard management controller data and saves the collected data in a system event log using instructions specified in the intelligent platform management interface specification.
As a preferred embodiment, the managed asset operation information data includes temperature, voltage, fan rotation speed, power status, CPU, memory utilization, and fault asset operation information data including actual fault asset operation information data and artificial simulated fault asset operation information data in step S2.
As a preferred embodiment, in step S3, the asset operation information data is manually marked, both the actual fault asset operation information data and the manually simulated fault asset operation information data are marked as fault devices, and the other asset operation information data are marked as normal devices; in the actual situation, the number of the fault devices is small, and the number of the normal devices is large, so that the number of the fault devices is small, the number of the normal devices is large, and the problem of unbalanced categories in the actual situation is solved.
As a preferred embodiment, in step S4, the process of preprocessing data includes data cleansing, data transformation, and data normalization; the data cleaning eliminates the data with the characteristic value not conforming to the common business knowledge, eliminates the characteristic containing a large number of null values, and reduces the influence of noise, missing values and other data on the model; the data transformation is carried out by carrying out logarithmic transformation on long-tail distribution data to ensure that the long-tail distribution data accords with normal distribution and meets the assumption condition of a linear model; the data normalization reduces the size difference between characteristic values by carrying out dimensionless processing on numerical characteristics, and avoids the interference of data with larger orders of magnitude to data with smaller orders of magnitude.
As a preferred embodiment, in the data transformation process, log transformation is performed on long tail distribution characteristics through data exploration and analysis, and the specific calculation process is as follows:
A'=log(A);
wherein A is long tail distribution characteristics, A' is the result of logarithmic transformation of the long tail distribution characteristics A;
the calculation formula for normalizing the data is:
wherein X is the value of a certain column of features, mu represents the mean value of the features X, and sigma represents the standard deviation of the features X;
after the characteristic value X is centered according to the mean value mu and scaled according to the standard deviation sigma, the characteristic value X obeys normal distribution with the mean value 0 and the variance 1.
As a preferred embodiment, in step S5, the objective function of the classification model based on cost sensitive learning is:
wherein C is 0 And C 1 Penalty factors for misclassification of normal equipment and fault equipment respectively; l (y) i ,f θ (x i ) A loss function, such as a logarithmic loss function (Logarithmic Loss Function) or a hinge loss function (Hinge Loss Function); y is i Representing the true tag class of the ith device; f (f) θ (x i ) A prediction function of a classification model based on cost sensitive learning; θ represents the prediction function f θ (x i ) Parameters of (2); x is x i Characteristic data representing an ith device, λR (θ) being a regularization term representing a penalty to the complex model; lambda is equal to or greater than 0 and is a regularization coefficient used for balancing experience risks and model complexity; r (θ) is the model complexity, e.g., L 1 Norms or L 2 Norms.
As a preferred embodiment, in step S5, a predictive probability p (x i ) The calculation formula of (2) is as follows:
p(x i )=f θ (x i );
as a preferred embodiment, in step S6, the specific formula for comparing the predicted probability of the managed asset being a faulty device with the threshold value is as follows:
wherein F represents equipment failure, T represents equipment normal, y (x i ) The prediction result of the ith device is shown, and only two results of the fault device and the normal device are taken; p (x) i ) Representing a predicted probability of the i-th device; alpha is a threshold value.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (3)
1. An asset fault identification method, comprising the steps of:
step S1: the baseboard management controller monitors and collects managed asset operation information data, wherein the managed asset is an information infrastructure asset, the asset operation information data comprises temperature, voltage, fan rotation speed, power state, CPU, memory utilization rate and fault asset operation information data, and the fault asset operation information data comprises actual fault asset operation information data and artificial simulation fault asset operation information data;
step S2: the out-of-band management system acquires the managed asset operation information data from the baseboard management controller through the operation and maintenance data network;
step S3: the out-of-band management system marks the acquired managed asset operation information data to form tag data;
step S4: performing data preprocessing operation on the tag data, and taking the tag data subjected to the preprocessing operation as training data;
step S5: constructing a classification model based on cost sensitive learning, inputting training data into the classification model for training to obtain a trained classification model based on cost sensitive learning, inputting preprocessed real-time data into the trained classification model based on cost sensitive learning to obtain a prediction probability of the managed asset as fault equipment;
step S6: comparing the prediction probability with a preset threshold value, and judging whether the managed asset is faulty equipment or normal equipment according to the comparison result;
step S7: the out-of-band management system outputs a final judging result;
in step S2, an out-of-band management interface technology is adopted to construct a running data network, and a B/S framework is adopted to construct an out-of-band management system;
the out-of-band management system receives the data of the baseboard management controller and stores the acquired data in a system event log by using an instruction specified in an intelligent platform management interface specification;
in step S3, the asset operation information data is marked manually, the actual fault asset operation information data and the manually simulated fault asset operation information data are marked as fault devices, and other asset operation information data are marked as normal devices;
in step S4, the process of preprocessing the training data includes data cleaning, data transformation and data normalization; the data cleaning is used for removing abnormal data; the data transformation is carried out by carrying out logarithmic transformation on long-tail distribution data to ensure that the long-tail distribution data accords with normal distribution and meets the assumption condition of a linear model; the data standardization reduces the size difference between characteristic values by carrying out dimensionless treatment on the numerical value type characteristics, and avoids the interference of data with larger orders of magnitude to data with smaller orders of magnitude;
in the data transformation process, the long tail distribution characteristics are subjected to logarithmic transformation through data exploration and analysis, and the specific calculation process is as follows:
A'=log(A);
wherein A is long tail distribution characteristics, A' is the result of logarithmic transformation of the long tail distribution characteristics A;
the calculation formula for normalizing the data is:
wherein X' is data after standardized calculation, X is a certain column of characteristic values, mu represents the mean value of the characteristic values X, and sigma represents the standard deviation of the characteristic values X;
after the characteristic value X is centralized according to the mean value mu and scaled according to the standard deviation sigma, the characteristic value X obeys normal distribution with the mean value 0 and the variance 1;
in step S5, the objective function of the classification model based on cost-sensitive learning is:
wherein C is 0 And C 1 Penalty factors for misclassification of normal equipment and fault equipment respectively; l (y) i ,f θ (x i ) Is a loss function; y is i Representing the true tag class of the ith device; f (f) θ (x i ) A prediction function of a classification model based on cost sensitive learning; θ represents the prediction function f θ (x i ) Parameters of (2); x is x i Characteristic data representing an ith device, λR (θ) being a regularization term representing a penalty to the complex model; lambda is more than or equal to 0 and is a regularization coefficient used for balancing experience risk and model complexity; r (θ) is model complexity;
calculating a predictive probability p (x i ) The calculation formula of (2) is as follows:
p(x i )=f θ (x i )。
2. the asset fault identification method according to claim 1, wherein the preprocessing of the real-time data in step S5 comprises two steps of data transformation and data normalization.
3. The asset fault identification method according to claim 2, wherein in step S6, if the prediction probability is greater than the threshold value, the managed asset is determined to be a faulty device, and if the prediction probability is less than the threshold value, the managed asset is determined to be a normal device; the specific formula for comparing the predicted probability of a managed asset being a faulty device to a threshold value is as follows:
wherein F represents equipment failure, T represents equipment normal, y (x i ) The prediction result of the ith device is shown, and only two results of the fault device and the normal device are taken; p (x) i ) Representing a predicted probability of the i-th device; alpha is a threshold value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911012875.2A CN110765486B (en) | 2019-10-23 | 2019-10-23 | Asset fault identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911012875.2A CN110765486B (en) | 2019-10-23 | 2019-10-23 | Asset fault identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110765486A CN110765486A (en) | 2020-02-07 |
CN110765486B true CN110765486B (en) | 2024-01-26 |
Family
ID=69333798
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911012875.2A Active CN110765486B (en) | 2019-10-23 | 2019-10-23 | Asset fault identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110765486B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112434082A (en) * | 2020-11-25 | 2021-03-02 | 平安普惠企业管理有限公司 | Operation and maintenance resource management method, device, equipment and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107070726A (en) * | 2017-05-22 | 2017-08-18 | 郑州云海信息技术有限公司 | A kind of integrated management approach based on MDC |
CN107918379A (en) * | 2017-11-29 | 2018-04-17 | 东北大学 | Based on the industrial big data incipient fault detection method for scheming semi-supervised cost-sensitive |
CN108491305A (en) * | 2018-03-09 | 2018-09-04 | 网宿科技股份有限公司 | A kind of detection method and system of server failure |
CN108768772A (en) * | 2018-05-29 | 2018-11-06 | 南京航空航天大学 | The fault detection method of self-organizing network based on cost-sensitive |
CN110110905A (en) * | 2019-04-17 | 2019-08-09 | 华电国际电力股份有限公司十里泉发电厂 | A kind of electrical equipment fault based on CNN judges method for early warning, terminal and readable storage medium storing program for executing |
-
2019
- 2019-10-23 CN CN201911012875.2A patent/CN110765486B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107070726A (en) * | 2017-05-22 | 2017-08-18 | 郑州云海信息技术有限公司 | A kind of integrated management approach based on MDC |
CN107918379A (en) * | 2017-11-29 | 2018-04-17 | 东北大学 | Based on the industrial big data incipient fault detection method for scheming semi-supervised cost-sensitive |
CN108491305A (en) * | 2018-03-09 | 2018-09-04 | 网宿科技股份有限公司 | A kind of detection method and system of server failure |
CN108768772A (en) * | 2018-05-29 | 2018-11-06 | 南京航空航天大学 | The fault detection method of self-organizing network based on cost-sensitive |
CN110110905A (en) * | 2019-04-17 | 2019-08-09 | 华电国际电力股份有限公司十里泉发电厂 | A kind of electrical equipment fault based on CNN judges method for early warning, terminal and readable storage medium storing program for executing |
Also Published As
Publication number | Publication date |
---|---|
CN110765486A (en) | 2020-02-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112097365A (en) | Air conditioner fault detection and identification method and device based on prediction and classification model | |
CN114328198A (en) | System fault detection method, device, equipment and medium | |
JP2019028834A (en) | Abnormal value diagnostic device, abnormal value diagnostic method, and program | |
CN112629905A (en) | Equipment anomaly detection method and system based on deep learning and computer medium | |
US20210232104A1 (en) | Method and system for identifying and forecasting the development of faults in equipment | |
CN113282000A (en) | Fault diagnosis method and device of data center and dynamic loop monitoring system | |
CN112379325A (en) | Fault diagnosis method and system for intelligent electric meter | |
CN110765486B (en) | Asset fault identification method | |
KR20220073314A (en) | A System and Method for Monitoring Manufacturing Process | |
CN117391675B (en) | Data center infrastructure operation and maintenance management method | |
CN117193088B (en) | Industrial equipment monitoring method and device and server | |
CN113868948A (en) | User-oriented dynamic threshold model training system and method | |
CN110727669B (en) | Electric power system sensor data cleaning device and cleaning method | |
CN110413482B (en) | Detection method and device | |
JP7062505B2 (en) | Equipment management support system | |
CN108664696B (en) | Method and device for evaluating running state of water chiller | |
US10564204B2 (en) | Method and system for diagnostics and monitoring of electric machines | |
CN115437886A (en) | Fault early warning method, device and equipment based on storage and calculation integrated chip and storage | |
KR20230081759A (en) | Integrated management systme for clean room management based on artifical intelligence and method thereof | |
CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
CN115307670B (en) | Method, apparatus and medium for locating central air conditioning system anomaly sensors | |
CN117764422B (en) | Intelligent energy-saving operation and maintenance management cloud platform | |
CN117272246B (en) | Transformer voiceprint fault diagnosis method and system based on multiple regression model | |
CN117783769B (en) | Power distribution network fault positioning method, system, equipment and storage medium based on visual platform | |
CN112187555B (en) | Real-time KPI data anomaly detection method and device based on machine learning |
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 |