CN115809950B - Machine room operation and maintenance management platform and management method - Google Patents
Machine room operation and maintenance management platform and management method Download PDFInfo
- Publication number
- CN115809950B CN115809950B CN202310069610.6A CN202310069610A CN115809950B CN 115809950 B CN115809950 B CN 115809950B CN 202310069610 A CN202310069610 A CN 202310069610A CN 115809950 B CN115809950 B CN 115809950B
- Authority
- CN
- China
- Prior art keywords
- module
- data
- inspection
- management module
- machine room
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 82
- 238000012423 maintenance Methods 0.000 title claims abstract description 68
- 238000013523 data management Methods 0.000 claims abstract description 133
- 230000002159 abnormal effect Effects 0.000 claims abstract description 54
- 238000007689 inspection Methods 0.000 claims description 133
- 230000006870 function Effects 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 238000011156 evaluation Methods 0.000 claims description 24
- 230000005856 abnormality Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 2
- 238000004904 shortening Methods 0.000 claims description 2
- 238000013461 design Methods 0.000 claims 1
- 238000007418 data mining Methods 0.000 abstract description 5
- 238000007405 data analysis Methods 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005206 flow analysis Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a machine room operation and maintenance management platform and a management method, and relates to the technical field of information processing. Through data mining and analysis, abnormal information can be pre-warned, especially, pre-judgment is performed in advance aiming at factors with serious harmfulness, and huge loss caused by the factors is prevented; in order to improve the security of data, the data management module is divided into a public data management module and a private data management module, the management terminal functional module and the mobile terminal functional module are respectively connected with the public data management module, and the public data management module is connected with the private data management module, so that the security of private data can be improved.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a machine room operation and maintenance management platform and a management method.
Background
Along with popularization of computer and internet technologies, informatization has been applied to various use scenarios, not only improving work efficiency, but also playing a positive role in equipment management and operation maintenance of enterprises, along with popularization of informatization, improving informatization and intellectualization of operation and maintenance management is one of important directions of future development.
The conventional maintenance management platform and management method have the following problems: (1) The machine room safe operation and maintenance is a complex work, comprises a plurality of work modules such as personnel training, equipment inspection, asset management, work report forms and the like, and has different work contents and flow structures according to different clients, the existing problem is that the functions are scattered, each module is an independent software system, the resource integration cannot be realized, and the work efficiency is greatly reduced; (2) Most of the machine rooms are unattended machine rooms, daily inspection is extremely important, and the maintenance personnel can finish inspection tasks on time according to inspection plans, which is a basic requirement for maintenance work; (3) The security of client data, along with the increasing severity of network security situation, the existing software cannot effectively protect the data of users; (4) And in the absence of the utilization of data mining analysis, the operation and maintenance system mostly carries out threshold judgment on the inspection data to plan the next inspection strategy, does not carry out deep mining on the inspection data, particularly carries out comprehensive evaluation on the abnormal recognition and the comprehensive risk of the equipment needing operation and maintenance, and specifies the inspection strategy based on the abnormal data and the comprehensive risk.
Disclosure of Invention
In order to solve the problems, the invention provides a machine room operation and maintenance management platform and a management method, abnormal information can be early warned through data mining and analysis, especially, the early judgment is carried out in advance aiming at the factors with serious harmfulness, and the factors are prevented from causing huge loss; in order to improve the security of data, the data management module is divided into a public data management module and a private data management module, the management terminal functional module and the mobile terminal functional module are respectively connected with the public data management module, and the public data management module is connected with the private data management module, so that the security of private data can be improved.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in one aspect, the present invention provides a machine room operation and maintenance management platform, including: the system comprises a management terminal functional module, a data management module and a mobile terminal functional module, wherein the management terminal functional module comprises a patrol management module, a knowledge base management module and a safety comprehensive judgment module, wherein the patrol management module collects patrol data based on a strategy command, and after the patrol data is judged by the safety comprehensive judgment module, the next strategy command is formulated; the knowledge base management module is used for training and learning operation and maintenance personnel; the data management module comprises a public data management module and a private data management module; one end of the public data management module is connected with the management terminal functional module and the mobile terminal functional module, and the other end of the public data management module is connected with the private data management module; the public data management module receives the instruction of the management terminal functional module or the mobile terminal functional module, controls the private data management module to acquire patrol data, transmits the required data to the public data management module for analysis, and transfers the private data of different clients to the private data management module of the corresponding client after the analysis is completed; the mobile terminal function module comprises an equipment module, a working module and a learning module, wherein the equipment module displays the state, basic information, maintenance record and technical data of equipment in a machine room, the working module comprises a patrol plan, a fault report and a system notification module, and the learning module comprises a learning plan, learning data and a grade test.
Further, the inspection management module comprises inspection report display, an alarm list, an inspection record, an operation plan and a fault report.
Further, the knowledge base management module comprises a knowledge base, a learning and examination module.
Further, the safety comprehensive judging module comprises a machine room inspection data abnormality judging module and a safety evaluating module, the safety comprehensive judging module outputs the strategy command based on the evaluation results of the machine room inspection data abnormality judging module and the safety evaluating module, the machine room inspection data abnormality judging module is used for judging whether single factor operation is abnormal or not, and the safety evaluating module is used for evaluating the risk of the machine room.
Further, the public data management module is interconnected with the mobile terminal functional module through a VPDN, the public data management module is interconnected with the management terminal functional module and the private data management module through an MPLS private line, and the data transmission adopts an encryption algorithm.
Further, the system also comprises a preposed data processing module which is connected with the public data management module through VPN, and the preposed data processing module intercepts unnecessary data transferred to the public data management module.
Furthermore, the login policy of the mobile terminal functional module is that only the public data management module is allowed to log in the private data management module, and the public network is disconnected when the mobile terminal functional module logs in the public data management module, and the public data management module is connected by dialing and accessing the VPDN private network through the private L2TP account password.
On the other hand, the invention provides a management method of the machine room operation and maintenance management platform, which comprises the following steps: issuing a patrol strategy command and collecting patrol data; analyzing the inspection data, and identifying abnormal inspection data and machine room risks; and (5) based on the abnormal inspection data and the machine room risk, formulating a next inspection strategy command.
Further, identifying abnormal inspection data based on the improved clustering algorithm includes: clustering is carried out through a hierarchical clustering CURE algorithm based on the historical normal sample data, and a cluster of the normal sample data is obtained; selecting boundary samples based on the cluster of the normal sample data; and identifying the abnormal data in the sample data to be tested based on an abnormal data identification algorithm of the boundary sample.
Further, the security evaluation module is configured to evaluate a risk of the machine room, and includes: dividing the fuzzy set based on the most clustering condition determined by the class density index, the intra-class compactness and the inter-class distributivity; adopting a triangle membership function as similarity measurement; and obtaining a final evaluation result by the primary fuzzy comprehensive evaluation and the secondary fuzzy comprehensive evaluation.
The technical scheme provided by the invention has the beneficial effects that: by setting the safety comprehensive judging module, the system risk is evaluated and the next strategy command is appointed, and compared with the existing operation and maintenance platform, the scientificity of the operation and maintenance strategy command is greatly improved; through data mining and analysis, abnormal information can be pre-warned, especially, pre-judgment is performed in advance aiming at factors with serious harmfulness, and huge loss caused by the factors is prevented; secondly, in order to improve the security of the data, the data management module is divided into a public data management module and a private data management module, the management terminal functional module and the mobile terminal functional module are respectively connected with the public data management module, and the public data management module is connected with the private data management module, so that the security of the private data can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a machine room operation and maintenance management platform according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating a connection of a mobile terminal function module according to an embodiment of the present invention;
fig. 3 is a flowchart of a management method of a machine room operation and maintenance management platform according to a second embodiment of the present invention.
Reference numerals: 1-a management terminal function module; 10-a patrol management module; 11-a knowledge base management module; 12, a safety comprehensive judging module; 2-a data management module; 20-a public data management module; 21-a private data management module; 3-a mobile terminal function module; 30-an equipment module; 31-a work module; 32-a learning module.
Detailed Description
In order to better understand the technical solutions of the present invention, the following description will clearly and completely describe the technical solutions of the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
As shown in fig. 1, the present invention provides a machine room operation and maintenance management platform, including: the system comprises a management terminal functional module 1, a data management module 2 and a mobile terminal functional module 3, wherein the management terminal functional module comprises a patrol management module 10, a knowledge base management module 11 and a safety comprehensive judgment module 12, wherein the patrol management module 10 collects patrol data based on strategy commands, and after the safety comprehensive judgment module 12 judges the patrol data, the next strategy command is formulated; the knowledge base management module 11 is used for training and learning operation and maintenance personnel; the data management module 2 comprises a public data management module 20 and a private data management module 21; one end of the public data management module 20 is connected with the management terminal function module 1 and the mobile terminal function module 3, and the other end of the public data management module is connected with the private data management module 21; the public data management module 20 receives the instruction of the management terminal function module 1 or the mobile terminal function module 3, controls the private data management module 21 to collect inspection data, transmits required data to the public data management module 20 for analysis, and after analysis, transfers the private data of different clients to the private data management module 21 of the corresponding client; the mobile terminal function module comprises an equipment module 30, a working module 31 and a learning module 32, wherein the equipment module 30 displays the state, basic information, maintenance record and technical data of equipment in a machine room, the working module 31 comprises a patrol plan, fault reporting and system notification module, and the learning module 32 comprises a learning plan, learning data and level testing.
According to the invention, the safety comprehensive judging module is arranged to evaluate the system risk and assign the next strategy command, so that compared with the existing operation and maintenance platform, the scientificity of the assignment of the operation and maintenance strategy command is greatly improved; through data mining and analysis, abnormal information can be pre-warned, especially, pre-judgment is performed in advance aiming at factors with serious harmfulness, and huge loss caused by the factors is prevented; secondly, in order to improve the security of the data, the data management module is divided into a public data management module and a private data management module, the management terminal functional module and the mobile terminal functional module are respectively connected with the public data management module, and the public data management module is connected with the private data management module, so that the security of the private data can be improved.
It can be understood that the data management module is a server, and can store data and execute commands for managing the terminal function module and the mobile terminal function module; in order to improve the security of data, the data management module comprises a public data management module and a private data management module, wherein the public data management module is used for storing public data for a long time, the private data management module is used for storing private data for a long time, the public data management module is a cloud management server, and the private data management module is a server arranged at a local place of a client; it should be noted that, when responding to the instruction sent by the management terminal function module or the mobile terminal function module, the public data management module will call the private data to calculate, process and analyze, and after the analysis is completed, the data is transferred to the local server to be stored, and the private data will not be stored in the public data management module for a long time.
The mobile terminal functional module can be a special handheld mobile tool, has a corresponding module for completing a corresponding task or is a mobile phone APP and is communicated with the public data management module through the mobile phone APP.
In the invention, the division of private data and public data is determined depending on the confidentiality level of client information, and the specific content is not limited. The inspection data comprises data obtained by issuing a digital policy command to corresponding network equipment of a corresponding machine room of a client, and also can be inspected by installing an identification device on a related instrument, for example, a camera is installed above the instrument in a fixed point manner when the instrument is required to be checked on site for the environment of the machine room, a high-definition photo of the instrument shot by the camera during inspection is returned to a public data management module, and the background reads inspection parameters in the picture through an OCR text recognition technology, and further comprises data obtained by issuing the digital policy or the inspection task to an inspection personnel in a message pushing mode for on-site inspection.
The inspection management module comprises inspection report display, an alarm list, an inspection record, an operation plan and a fault report. The inspection management module issues the access policy command to collect inspection data based on an operation plan at preset inspection time, so that an inspection report and an inspection record can be obtained, and secondly, after the inspection data is subjected to identification of abnormal data and integral security risk assessment of a machine room through the security comprehensive judgment module, an alarm list, a fault report and the next access policy command are provided, and an operation and maintenance personnel can upload equipment fault information through the mobile terminal function module to form a corresponding fault report.
The knowledge base management module comprises a knowledge base and a learning and examination module. The knowledge base provides corresponding knowledge and skills based on the level of the operation and maintenance personnel and the management equipment, the learning module provides a systematic learning framework for the operation and maintenance personnel, the examination module examines the mastered knowledge and skills for the operation and maintenance personnel, and when the examination passes, the examination module can allow the learning of high-order technical knowledge or the reinforcement of wrong knowledge points or technical points.
The safety comprehensive judging module comprises a machine room inspection data abnormality judging module and a safety evaluating module, the safety comprehensive judging module outputs the strategy command based on the evaluating results of the machine room inspection data abnormality judging module and the safety evaluating module, the machine room inspection data abnormality judging module is used for judging whether single factor operation is abnormal or not, and the safety evaluating module is used for evaluating the risk of the machine room. Specifically, according to the invention, abnormal values in the inspection data are identified through a clustering algorithm, the risk size of the machine room is evaluated based on a multi-stage fuzzy evaluation model, and the abnormal values and the risk size are combined to specify the next inspection strategy command.
The public data management module is interconnected with the mobile terminal functional module through the VPDN, the public data management module is interconnected with the management terminal functional module and the private data management module through the MPLS private line, and the data transmission adopts an encryption algorithm. By the arrangement, the data security can be improved. The encryption algorithm preferably adopts an SM9 national encryption algorithm to encrypt, and the data is verified in a public-private key comparison mode.
The operation and maintenance management platform also comprises a preposed data processing module, wherein the preposed data processing module is connected with the public data management module through a VPN, and the preposed data processing module intercepts unnecessary data transmitted to the public data management module. Specifically, the front-end data processing module is connected with the cloud management server through the VPN, interacts operation and maintenance data required by the cloud management server, such as alarms, flow analysis results, script verification and the like, does not need to return a large amount of operation and maintenance data which are directly collected, such as mirror image flow analysis data, operation and maintenance logs and the like, and data which need high bandwidth support are stored in the local server, so that bandwidth resources can be effectively saved, and the localization management effect of the operation and maintenance management platform of the cloud management server can be realized through small network resources.
The login policy of the mobile terminal functional module is that only the public data management module is allowed to log in the private data management module, and the public network is disconnected when the mobile terminal functional module logs in the public data management module, and the public data management module is connected by dialing and accessing the VPDN private network through the private L2TP account password. Specifically, the mobile terminal functional module can only be connected with the private data management module through the public data management module, and is not allowed to log in by direct Telnet or SSH, as shown in fig. 2, fig. 2 shows a communication connection mode of the mobile terminal functional module, the public data management module and the private data management module, an operation and maintenance person logs in the system through the mobile terminal functional module, and the public data management module issues viewing and operation rights according to account information; when the operation and maintenance personnel apply for customer assets and inspection information through the mobile terminal function module, the public data management module transmits the application information to the private data management module, and when the request passes, the public data management module returns related data and transmits the related data to the mobile terminal module function module; when operation and maintenance personnel report inspection and fault data, after the public data management module analyzes the data, the public data management module forwards the data to the corresponding private data management module according to the client ID; the knowledge base data are stored in the public data management module, when the mobile terminal functional module applies for learning data, the public data management module directly provides relevant data for the mobile terminal functional module, and after the learning of operation and maintenance personnel is completed, examination results are uploaded to the public data management module. It should be noted that, when related information needs to be obtained from the private data management module, the private data management server will check the operation authority of the operation and maintenance personnel, the operation environment will ensure that the public data management module is connected by dialing access to the VPDN private network through the private L2TP account password only when the public data management module is required to be disconnected by the request when the operation environment, such as the mobile terminal function module, logs in the public data management module.
Example 2
The embodiment of the invention provides a management method of a machine room operation and maintenance management platform, as shown in fig. 3, comprising the following steps:
s1, issuing a patrol strategy command and collecting patrol data;
in the invention, a patrol module of a management terminal functional module issues a patrol strategy command, acquires patrol data, and the patrol data comprises: (1) The method comprises the steps of issuing a strategy command to data obtained from corresponding network equipment of a corresponding machine room of a client; (2) The method comprises the steps that an identification device is arranged on a related instrument for inspection, for example, for a machine room environment type, the instrument needs to be checked on site, a camera is arranged above the instrument in a fixed point mode, a high-definition photo of the instrument is shot through the camera during inspection and is transmitted back to a public data management module, and inspection parameters in pictures are read through an OCR text recognition technology in the background; (3) The method also comprises the step of sending the taking strategy or the inspection task to an inspector in a message pushing mode for field inspection and reporting inspection data. After the data is acquired, the pre-processing module intercepts unnecessary data in the detected data, the necessary data is transmitted to the public data management module, and the pre-processing module is similar to the private data management module, namely a client local server, and is arranged at the client local, so that bandwidth resources can be saved, and data congestion can be prevented.
S2, analyzing the inspection data, and identifying abnormal inspection data and machine room risks;
the safety comprehensive judging module comprises a machine room inspection data abnormality judging module and a safety evaluating module.
The inspection data abnormity judging module adopts an improved clustering algorithm to judge, specifically, firstly clusters through an improved CURE clustering algorithm based on historical normal sample data, and the clustering is carried out twice, outliers are deleted after the first clustering is finished, classes with sample points smaller than a certain value in the clusters are deleted after the second clustering is finished, and the rest data points are clustered into the nearest clusters to finish clustering, so that normal cluster samples are obtained. The certain value is not particularly limited here, and is set based on the situation of the client's own device.
The sample is selected, the calculated amount of data can be reduced by selecting the sample, but in order to obtain the optimal normal cluster sample from the clustering result, the sampling mode of the embodiment of the invention is as follows: let S be the fraction of possible cluster objects that are obtained, S ε [0,1], for a cluster of size n, under the condition of 1- α probability, the sample size m should be:
wherein n is 0 For the number of objects
The class with very slow first-stage clustering growth is used as the outlier to be deleted, and the sample points are judged by the outlier degree judgment value, so that the first-stage clustering outlier can be effectively deleted.
Clustering each divided data block, and representing the obtained data cluster asWherein p is i Representing the ith cluster, mp in a block i Represented as the center point, w, of the ith cluster i The weight value representing each center point is the number of data in each cluster.
Let the set of representative points be P, each representative point P i The distance of deviation of the center point of (c) to any point outside the cluster is expressed as the degree of outlier:
where n is the total dimension of the data, j represents the j-th dimension, x of the data ji ,y ji Two attributes of the data; the euclidean distance is used to represent the deviation degree of a point, and the more a certain sample is far from the cluster center point, the larger the value of the deviation degree is.
The outlier degree determination value AD is:
wherein d is i Is any value in the outlier degree set D.
The outlier parameters were:
max(d i ) Is the maximum value of outlier degree, min (d i ) And if the degree of outlier is the minimum, the outlier is.
Boundary samples are selected based on clusters of normal sample data. Firstly, taking normal cluster samples and the number of boundary samples as input data; secondly, calculating the mass center of the normal cluster sample; taking a normal cluster sample point farthest from the centroid as a first boundary sample; calculating the distance from the first boundary sample point, and selecting the point with the largest distance value as a second boundary sample; then, selecting the point with the largest sum of the distances from the first two sample points as a boundary sample until the coverage rate of the selected boundary sample reaches n 1 Stopping the selection; finally, all boundary samples are output.
And identifying the abnormal data in the sample data to be tested based on an abnormal data identification algorithm of the boundary sample. The boundary sample set of normal cluster samples is b= { B 1 ,b 2 ,…,b n Normal cluster samples have an identification radius r. The sample to be tested is t= { T 1 ,t 2 ,…,t m S is the identified non-anomaly monitoring information, and N is the identified anomaly monitoring information. Taking the boundary sample set as a plane detector, the anomaly information recognition rule is expressed as:
wherein l 1 For the minimum value of the distance sequence from the sample point to be identified to the boundary sample, l 2 D, for the distance value from the sample to be identified to the furthest point of the boundary sample m For the sample to be identified to the centroid distance, r is the identification radius of the normal cluster sample.
Table 1 analysis and comparison of different outlier deletion algorithms
For the outlier deleting algorithm in the normal sample acquisition process, the detection rate of several outlier detection algorithms is tested, and the test results are shown in table 1
The safety evaluation module is used for evaluating the risk of the machine room, factors influencing the safety condition of the machine room are many, and the factors influencing the safety condition of the machine room are divided into two levels based on the actual condition of the machine room, for example, the detection data of IT equipment of the machine room are primary factors, and the secondary factors comprise monitoring data of server equipment, safety equipment, monitoring equipment, network equipment, monitoring equipment, storage equipment and the like, and other factors are not repeated. Comprising the following steps:
the fuzzy sets are partitioned based on the most favorable clustering conditions determined by the class density index, the intra-class compactness and the inter-class distributivity. The monitoring data attribute set is X, the clustering number is C, and the deviation delta is:
wherein x is k And the value of each monitoring data attribute is the average value of the monitoring data attribute. Similarly, the bias of the ith cluster can be obtained:
wherein X is i For the i-th class data element attribute, for X i The average deviation of C clusters is:
and (3) clustering clusters with n pieces of monitoring information are arranged, wherein the average distance between the clusters is as follows:
wherein the average measure of the distance between clusters is the center of the ith and jth clusters, r i 、r j The cluster center dataset is represented by R.
Assuming that each data point is in a potential clusterHeart, calculate sample points according to Euclidean distance indexDensity index of (2);
the optimal clustering condition is as follows:
the smaller the optimal clustering condition value is, the better the obtained clustering result is. Given the clustering number c, continuously adjusting the clustering number by using a fuzzy mean value clustering algorithm, detecting the results by using an optimal clustering number to obtain ideal clustering results, and dividing the data sets of the given points into n fuzzy sets by the found clustering number and the center of each cluster to further determine fuzzy division.
The fuzzy membership and membership function are determined, a triangle membership function is used as similarity measure,for the cluster center point set, the membership functions are:
and establishing a secondary fuzzy security assessment model. The factor set is generally expressed asN is represented as n elements in the factor set, and represents a common set formed by abstractions of the effect factors of the result; a review set, commonly referred to asM is represented as m elements in the evaluation set, and m is represented as four levels of A, B, C and D for the set formed by the abstraction of the evaluation results,respectively correspond to safe, safer, more dangerous and dangerous.
The weight of each layer influence factor in the invention is determined by a layer analysis method and a final weight vector is obtained as follows:as for the algorithm for obtaining the weight vector, the prior art is used.
The result obtained by the first-level fuzzy comprehensive judgment is expressed as follows:
r ij and (5) representing the membership degree corresponding to the kth element, wherein. "operator," the embodiment of the invention adopts(product, bounded operator) synthesizing the fuzzy matrix, and then calculating its comprehensive evaluation vector B
Performing secondary fuzzy comprehensive judgment on the primary evaluation result, wherein the weight set is represented as an obtained resultFinal evaluation result ∈>Adopts->The fuzzy matrix is synthesized by (product, bounded operator).
Compared with other model algorithms, the result obtained by adopting the weighted average algorithm is more consistent with the reality through model formula calculation.
And S3, based on the abnormal inspection data and the machine room risk, formulating an inspection strategy command for the next time.
Specifically, when no abnormal inspection data exists, the risk of the machine room is A, and the machine room is inspected according to a conventional inspection plan, wherein the conventional inspection plan is that
Wherein delta T is the patrol interval time recommended by a manufacturer or specified by a client based on the self condition of a company, and T 0 The service life of the equipment is designed, t is the service time of the equipment and is the maintenance frequency of the equipment.
And when no abnormal inspection data exists, and the risk of the machine room is B, shortening the inspection interval time to 70-85% on the basis of a conventional inspection plan.
When the abnormal inspection data is more than 0 and less than 1% of the total data, the risk of the machine room is A or B, a maintenance list is formulated, abnormal points of the inspection data are positioned and issued to a mobile terminal functional module of an inspection personnel, the inspection personnel uploads an inspection record to a data management module through the mobile terminal functional module after finishing maintenance, and the next inspection interval time is calculated according to a conventional inspection plan.
When the abnormal inspection data is not less than 1%, and the risk of the machine room is C or D, alarm information is sent out to remind a user to switch a standby system, a fault point is issued to a mobile terminal functional module of an inspection personnel, the inspection personnel uploads an inspection record to a data management module through the mobile terminal functional module after maintenance is finished, and the next inspection interval time is calculated according to a conventional inspection plan.
When no abnormal inspection data exists and the risk of the machine room is C, immediately informing operation and maintenance personnel to immediately maintain and check the whole system of the machine room, if equipment is abnormal, maintaining, uploading inspection records to a data management module, and calculating the next inspection interval time by a conventional inspection plan based on the condition of maintenance by the data management module.
When no abnormal inspection data exists and the risk of the machine room is D, alarm information is sent out to remind a user to switch a standby system, operation and maintenance personnel are immediately informed of maintenance and inspection of the whole system of the machine room, if equipment is abnormal, maintenance is performed, inspection records are uploaded to a data management module, and the data management module calculates the next inspection interval time through a conventional inspection plan based on the condition of repair.
According to the invention, by detecting the abnormality of the inspection data and calculating the overall risk of the system, a corresponding inspection plan is formulated, the scientificity of the formulated inspection plan is improved, the reliability of equipment is improved, and larger loss is avoided.
The embodiment of the invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of: issuing a patrol strategy command and collecting patrol data; analyzing the inspection data, identifying abnormal inspection data and machine room risk, and identifying the abnormal inspection data based on an improved clustering algorithm, including: clustering is carried out through a hierarchical clustering CURE algorithm based on the historical normal sample data, and a cluster of the normal sample data is obtained; selecting boundary samples based on the cluster of the normal sample data; based on an abnormal data identification algorithm of the boundary sample, identifying abnormal data in the sample data to be tested; the safety evaluation module is used for evaluating the risk of the machine room, and comprises the following steps: dividing the fuzzy set based on the most clustering condition determined by the class density index, the intra-class compactness and the inter-class distributivity; adopting a triangle membership function as similarity measurement; and obtaining a final evaluation result by the primary fuzzy comprehensive evaluation and the secondary fuzzy comprehensive evaluation.
The embodiment of the invention also provides a computer device, which comprises: a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the memory and the processor are both disposed on a bus and the processor performs the following steps when executing the program: issuing a patrol strategy command and collecting patrol data; analyzing the inspection data, identifying abnormal inspection data and machine room risk, and identifying the abnormal inspection data based on an improved clustering algorithm, including: clustering is carried out through a hierarchical clustering CURE algorithm based on the historical normal sample data, and a cluster of the normal sample data is obtained; selecting boundary samples based on the cluster of the normal sample data; based on an abnormal data identification algorithm of the boundary sample, identifying abnormal data in the sample data to be tested; the safety evaluation module is used for evaluating the risk of the machine room, and comprises the following steps: dividing the fuzzy set based on the most clustering condition determined by the class density index, the intra-class compactness and the inter-class distributivity; adopting a triangle membership function as similarity measurement; and obtaining a final evaluation result by the primary fuzzy comprehensive evaluation and the secondary fuzzy comprehensive evaluation.
The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (10)
1. Computer lab fortune dimension management platform, its characterized in that includes:
a management terminal function module, a data management module and a mobile terminal function module,
the management terminal functional module comprises a patrol management module, a knowledge base management module and a safety comprehensive judgment module, wherein the patrol management module collects patrol data based on strategy commands, and after the patrol data is judged by the safety comprehensive judgment module, the next strategy command is formulated; the knowledge base management module is used for training and learning operation and maintenance personnel;
the data management module comprises a public data management module and a private data management module; one end of the public data management module is connected with the management terminal functional module and the mobile terminal functional module, and the other end of the public data management module is connected with the private data management module; the public data management module receives the instruction of the management terminal functional module or the mobile terminal functional module, controls the private data management module to acquire patrol data, transmits the required data to the public data management module for analysis, and transfers the private data of different clients to the private data management module of the corresponding client after the analysis is completed;
the mobile terminal function module comprises an equipment module, a working module and a learning module, wherein the equipment module displays the state, basic information, maintenance record and technical data of equipment in a machine room, the working module comprises a patrol plan, a fault report and a system notification module, and the learning module comprises a learning plan, learning data and a grade test;
specifying a next inspection policy command based on the abnormal inspection data and the machine room risk, including:
when no abnormal inspection data exists, the risk of the machine room is A, and the machine room is inspected according to a conventional inspection plan, wherein the conventional inspection plan is as follows:
wherein the method comprises the steps ofFor the inspection interval time, delta T is the recommended inspection interval time of a manufacturer or the inspection interval time specified by a client based on the self condition of a company, T 0 Design life for the device, t is the time the device has been used, < >>The maintenance times of the equipment;
when no abnormal inspection data exists and the risk of the machine room is B, shortening the inspection interval time to 70-85% on the basis of a conventional inspection plan;
when the abnormal inspection data is more than 0 and less than 1% of the total data, making a maintenance list when the risk of the machine room is A or B, positioning the abnormal points of the inspection data and issuing the abnormal points to a mobile terminal functional module of an inspection personnel, uploading the inspection record to a data management module through the mobile terminal functional module after the inspection personnel finishes maintenance, and calculating the next inspection interval time according to a conventional inspection plan;
when the abnormal inspection data is not less than 1% and the risk of the machine room is C or D, sending out alarm information to remind a user to switch a standby system, issuing a fault point to a mobile terminal functional module of an inspector, uploading an inspection record to a data management module through the mobile terminal functional module after the inspector finishes maintenance, and calculating the next inspection interval time according to a conventional inspection plan;
when no abnormal inspection data exists and the risk of the machine room is C, immediately informing operation and maintenance personnel to immediately maintain and check the whole system of the machine room, if the equipment is abnormal, maintaining, uploading inspection records to a data management module, and calculating the next inspection interval time by a conventional inspection plan based on the condition of maintenance by the data management module;
when no abnormal inspection data exists and the risk of the machine room is D, alarm information is sent out to remind a user to switch a standby system, operation and maintenance personnel are immediately informed of maintenance and inspection of the whole system of the machine room, if equipment is abnormal, maintenance is performed, inspection records are uploaded to a data management module, and the data management module calculates the next inspection interval time according to a conventional inspection plan based on the condition of repair;
the A, B, C and D are four grades, and are respectively corresponding to safety, safer, more dangerous and dangerous.
2. The machine room operation and maintenance management platform according to claim 1, wherein the inspection management module comprises inspection report presentation, an alarm list, inspection records, an operation plan and a fault report.
3. The machine room operation and maintenance management platform of claim 1, wherein the knowledge base management module comprises a knowledge base, learning and testing module.
4. The machine room operation and maintenance management platform according to claim 1, wherein the safety comprehensive judging module comprises a machine room inspection data abnormality judging module and a safety evaluating module, the safety comprehensive judging module outputs the policy command based on the evaluation results of the machine room inspection data abnormality judging module and the safety evaluating module, the machine room inspection data abnormality judging module is used for judging whether single factor operation is abnormal, and the safety evaluating module is used for evaluating the risk of the machine room.
5. The machine room operation and maintenance management platform according to claim 1, wherein the public data management module is interconnected with the mobile terminal function module through a VPDN, the public data management module is interconnected with the management terminal function module and the private data management module through an MPLS dedicated line, and the data transmission adopts an encryption algorithm.
6. The machine room operation and maintenance management platform of claim 1, further comprising a pre-data processing module connected to the common data management module through a VPN, the pre-data processing module intercepting unnecessary data transferred to the common data management module.
7. The machine room operation and maintenance management platform according to claim 1, wherein the login policy of the mobile terminal function module is that the mobile terminal function module is only allowed to log in the private data management module through the public data management module, and the mobile terminal function module needs to disconnect the public network when logging in the public data management module, dial in the VPDN private network through the private L2TP account password to connect the public data management module.
8. The method for managing a machine room operation and maintenance platform according to any one of claims 1 to 7, comprising:
issuing a patrol strategy command and collecting patrol data;
analyzing the inspection data, and identifying abnormal inspection data and machine room risks;
and (5) based on the abnormal inspection data and the machine room risk, formulating a next inspection strategy command.
9. The method of managing as set forth in claim 8, wherein identifying abnormal inspection data based on a modified clustering algorithm includes:
clustering is carried out through a hierarchical clustering CURE algorithm based on the historical normal sample data, and a cluster of the normal sample data is obtained;
selecting boundary samples based on the cluster of the normal sample data;
and identifying the abnormal data in the sample data to be tested based on an abnormal data identification algorithm of the boundary sample.
10. The method of claim 9, wherein the security assessment module is configured to assess a risk level of the machine room, and comprises:
dividing the fuzzy set based on the most clustering condition determined by the class density index, the intra-class compactness and the inter-class distributivity;
adopting a triangle membership function as similarity measurement;
and obtaining a final evaluation result by the primary fuzzy comprehensive evaluation and the secondary fuzzy comprehensive evaluation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310069610.6A CN115809950B (en) | 2023-02-07 | 2023-02-07 | Machine room operation and maintenance management platform and management method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310069610.6A CN115809950B (en) | 2023-02-07 | 2023-02-07 | Machine room operation and maintenance management platform and management method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115809950A CN115809950A (en) | 2023-03-17 |
CN115809950B true CN115809950B (en) | 2023-05-19 |
Family
ID=85487497
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310069610.6A Active CN115809950B (en) | 2023-02-07 | 2023-02-07 | Machine room operation and maintenance management platform and management method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115809950B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109670340A (en) * | 2018-12-29 | 2019-04-23 | 湖南网数科技有限公司 | A kind of secure and trusted exchange sharing method and system of medical data |
CN109726922A (en) * | 2018-12-29 | 2019-05-07 | 杭州趣链科技有限公司 | A kind of computer room patrolling and checking management system and method based on block chain |
WO2019095910A1 (en) * | 2017-11-15 | 2019-05-23 | 天津市普迅电力信息技术有限公司 | Daily patrol working method and system in substation |
CN112287915A (en) * | 2020-12-28 | 2021-01-29 | 北京蒙帕信创科技有限公司 | Equipment fault warning method and system based on deep learning |
CN115052128A (en) * | 2022-04-07 | 2022-09-13 | 水利部信息中心 | Machine room safety management method integrating video monitoring and network anomaly detection |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030046392A1 (en) * | 2001-08-29 | 2003-03-06 | Sayling Wen | Automatic network connecting system and method |
CN108052058B (en) * | 2018-01-31 | 2023-11-24 | 广州市建筑科学研究院有限公司 | Construction engineering site safety patrol transaction flow system based on Internet +' |
CN109934356B (en) * | 2019-01-11 | 2023-01-31 | 平安科技(深圳)有限公司 | Machine room inspection method based on big data and related equipment |
CN110633855B (en) * | 2019-09-17 | 2022-12-13 | 江南大学 | Bridge health state detection and management decision making system and method |
CN112711509A (en) * | 2020-12-25 | 2021-04-27 | 信通达智能科技有限公司 | Method and system for improving operation and maintenance safety of data center machine room |
CN113689013A (en) * | 2021-08-27 | 2021-11-23 | 国网新疆电力有限公司吐鲁番供电公司 | Intelligent monitoring and operation and maintenance system for transformer |
-
2023
- 2023-02-07 CN CN202310069610.6A patent/CN115809950B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019095910A1 (en) * | 2017-11-15 | 2019-05-23 | 天津市普迅电力信息技术有限公司 | Daily patrol working method and system in substation |
CN109670340A (en) * | 2018-12-29 | 2019-04-23 | 湖南网数科技有限公司 | A kind of secure and trusted exchange sharing method and system of medical data |
CN109726922A (en) * | 2018-12-29 | 2019-05-07 | 杭州趣链科技有限公司 | A kind of computer room patrolling and checking management system and method based on block chain |
CN112287915A (en) * | 2020-12-28 | 2021-01-29 | 北京蒙帕信创科技有限公司 | Equipment fault warning method and system based on deep learning |
CN115052128A (en) * | 2022-04-07 | 2022-09-13 | 水利部信息中心 | Machine room safety management method integrating video monitoring and network anomaly detection |
Non-Patent Citations (2)
Title |
---|
基于BLE的机房巡更管理系统研究与应用;袁绪;;智能计算机与应用(第06期);20-21 * |
基于NFC技术的机房巡更管理系统的设计与实现;刘友旗;;金融科技时代(第10期);45-48 * |
Also Published As
Publication number | Publication date |
---|---|
CN115809950A (en) | 2023-03-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112769796B (en) | Cloud network side collaborative defense method and system based on end side edge computing | |
US10178566B2 (en) | Radio access network (RAN) cell site diagnostic test tool system and method | |
CN114584405B (en) | Electric power terminal safety protection method and system | |
CN109934356B (en) | Machine room inspection method based on big data and related equipment | |
US20240142063A1 (en) | Method for troubleshooting potential safety hazards of compressor in smart gas pipeline network and internet of things system thereof | |
US7894357B2 (en) | Capability-based testing and evaluation of network performance | |
CN111881452A (en) | Safety test system for industrial control equipment and working method thereof | |
CN108170566A (en) | Product failure information processing method, system, equipment and collaboration platform | |
CN112463892A (en) | Early warning method and system based on risk situation | |
CN111723217A (en) | Engineering construction management robot control system, management method and robot | |
CN114255784A (en) | Substation equipment fault diagnosis method based on voiceprint recognition and related device | |
CN114550336B (en) | Equipment inspection method and device, computer equipment and storage medium | |
CN116030943A (en) | Big data intelligent operation and maintenance control system and method | |
CN116010456A (en) | Equipment processing method, server and rail transit system | |
CN115145788A (en) | Detection data generation method and device for intelligent operation and maintenance system | |
US20130317888A1 (en) | Reporting and Management of Computer Systems and Data Sources | |
CN115809950B (en) | Machine room operation and maintenance management platform and management method | |
CN116073520B (en) | Power grid inspection method and device, electronic equipment and storage medium | |
CN115545452A (en) | Operation and maintenance method, operation and maintenance system, equipment and storage medium | |
CN114648256A (en) | Data security check method, system and equipment | |
TWI696401B (en) | Fault identification server and method for base station | |
CN112615812A (en) | Information network unified vulnerability multi-dimensional security information collection, analysis and management system | |
CN111865699A (en) | Fault identification method and device, computing equipment and medium | |
CN115423126B (en) | Fire control maintenance management system based on big data | |
Imani | Prediction of Content Error in Cloud Computing based on Perceptron Neural Network and Radial Basis Function (RBF) |
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 |