CN116506275A - Communication network fault early warning method and system based on artificial intelligence - Google Patents
Communication network fault early warning method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN116506275A CN116506275A CN202310540928.8A CN202310540928A CN116506275A CN 116506275 A CN116506275 A CN 116506275A CN 202310540928 A CN202310540928 A CN 202310540928A CN 116506275 A CN116506275 A CN 116506275A
- Authority
- CN
- China
- Prior art keywords
- network
- data
- early warning
- industrial
- communication
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004891 communication Methods 0.000 title claims abstract description 137
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000000007 visual effect Effects 0.000 claims abstract description 7
- 230000004888 barrier function Effects 0.000 claims description 60
- 230000005672 electromagnetic field Effects 0.000 claims description 38
- 230000002159 abnormal effect Effects 0.000 claims description 36
- 230000007613 environmental effect Effects 0.000 claims description 20
- 230000005540 biological transmission Effects 0.000 claims description 19
- 239000000463 material Substances 0.000 claims description 19
- 238000012544 monitoring process Methods 0.000 claims description 19
- 238000012360 testing method Methods 0.000 claims description 16
- 230000001133 acceleration Effects 0.000 claims description 14
- 238000003912 environmental pollution Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 230000005484 gravity Effects 0.000 claims description 6
- 238000009776 industrial production Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 239000011521 glass Substances 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 230000035515 penetration Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 10
- 230000000903 blocking effect Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 230000017525 heat dissipation Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000149 penetrating effect Effects 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a communication network fault early warning method and system based on artificial intelligence, and relates to the technical field of industrial communication network early warning, wherein the system comprises a data acquisition module, a data processing module, a model training module, a prediction module, an early warning module and a visual interface module; the system comprises a data acquisition module network communication acquisition unit, an environment data acquisition unit and an operation state acquisition unit; the network communication acquisition unit is used for acquiring various data of a communication network to obtain industrial network communication data Xn; the environment data acquisition unit is used for acquiring environment comprehensive influence data Yx; the running state acquisition unit is used for acquiring running state data of the industrial automation equipment; the early warning module comprises an early warning unit and a scheme summarizing unit. The benefits of the computing environment comprehensive influence data Yx on the industrial network communication data Xn are mainly reflected in the aspects of optimizing network planning, predicting network performance, improving network capacity and reducing communication cost.
Description
Technical Field
The invention relates to the technical field of industrial communication network early warning, in particular to a communication network fault early warning method and system based on artificial intelligence.
Background
Artificial intelligence is a new technical science based on computer science, which is a new theory, method, technology and application system for simulating, extending and expanding human intelligence by cross-fusing multiple subjects such as computer, psychology, philosophy and the like and emerging subjects.
The communication network comprises a wired communication network and a wireless communication network, and from the professional perspective, the wireless communication technology is based on radio waves, and under the support of a wireless optical cable, the requirement of connecting the computer equipment with a network data transmission system is met. Under the introduction of science and technology, wireless communication technology is continuously permeated in the field of industrial automation, the application value is outstanding, and the diversified industrial development requirements are increasingly met. In an industrial communication network, the performance value of the network needs to be monitored and early-warned in real time, and the existing industrial network communication network simply monitors the equipment network in a manual inspection and remote monitoring mode, but in practice, many performance indexes which can influence network communication exist in the industrial environment, such as the network operation speed of the equipment can be influenced by temperature change and humidity change, the signal penetrating power of the equipment network can be influenced by excessive obstacles, and the performance of the network can be influenced by excessive dust which can influence the heat dissipation stability of the equipment.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a communication network fault early warning method and a communication network fault early warning system based on artificial intelligence,
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: a communication network fault early warning method based on artificial intelligence comprises the following steps,
s1, collecting various data of a communication network of equipment in an industrial production line in real time to obtain industrial network communication data Xn;
the industrial network communication data Xn comprises bandwidth, time delay, packet loss rate, jitter variation value and throughput;
s2, acquiring factors influencing network performance indexes in an industrial environment, and acquiring environment comprehensive influence data Yx; the environment comprehensive influence data Yx comprises an environment temperature and humidity value Ws, an environment pollution degree Wr, an electromagnetic field interference coefficient Cc, an industrial equipment jitter degree Dd and a barrier interference coefficient ZDxs;
extracting characteristics of environment comprehensive influence data Yx and industrial network communication data Xn, and combining the data with the contact influence to obtain a communication quality index Zb;
s3, acquiring a communication quality index Zb, establishing a digital model, training data machine learning, and inputting the data subjected to feature extraction into the model for training and optimizing;
s4, predicting and calculating by using the trained model, predicting network communication quality under different environmental conditions, and obtaining the influence of environmental assessment data on industrial network communication;
s5, analyzing the model prediction result, carrying out abnormal mode early warning after comparing and analyzing according to the standard network quality threshold, and carrying out optimization and adjustment by adopting corresponding measures according to the abnormal mode early warning content.
Preferably, SNMP and NetFlow protocols are adopted to monitor the bandwidth, flow and equipment state of the network;
adopting PLC and DCS equipment to collect data in the industrial production process;
adopting Traceroute and Ipref tools to test bandwidth, time delay and packet loss rate indexes of the network;
the type, IP address, equipment link number, state and flow of the production equipment are acquired by adopting a network analyzer and a signal generator.
Preferably, the environmental temperature and humidity value Ws is acquired by a temperature and humidity sensor;
the environmental pollution Wr is obtained by monitoring the concentration and pollution degree of particles in the air by adopting a particle sensor;
the electromagnetic field interference coefficient Cc is obtained by detecting electromagnetic field intensity and frequency parameters in an industrial environment through an electromagnetic field intensity meter and a frequency spectrum analyzer and further monitoring and analyzing;
the industrial equipment jitter Dd monitors the equipment jitter through a jitter monitoring tool, and the change and trend of the equipment jitter are known, so that the influence of the equipment jitter on network communication data is predicted.
Preferably, the blocking object interference coefficient Zdxs includes obtaining thickness, material and blocking object of the blocking object, so as to obtain attenuation degree of influence on the signal;
identifying the thickness of the barrier in a picture for identifying the cargo barrier by an intelligent identification monitoring camera;
testing the delay condition of network transmission of network equipment and industrial equipment by adopting a transmission testing tool; placing barriers with different thicknesses between the distances of the network equipment and the industrial equipment, and recording data;
and obtaining materials of steel materials, walls and glass barriers with different thicknesses, and fitting the materials of the barriers, the thicknesses of the barriers, the attenuation degree of network signals and the network delay value to obtain a barrier interference coefficient ZDxs.
Preferably, the barrier interference coefficient Zdxs is calculated by the following formula:
Zdxs＝10 Λ (-D/10)
wherein D is the attenuation of the signal by the barrier;
the attenuation degree D is calculated by the following formula
Wherein: x represents the thickness of the barrier, y represents the material of the barrier, z represents the delay amount of the test network delay value, wherein beta is the signal penetration coefficient, and the coefficient is obtained through the barrier transparency test, wherein: and beta is more than or equal to 40 and less than or equal to 80, wherein the specific value of beta can be adjusted and corrected by a user according to actual experience, and the baffle interference coefficient ZDxs is corrected by changing the value of beta.
Preferably, the ambient temperature and humidity value Ws is obtained by the following formula:
Ws＝(a,b)
wherein: a represents a temperature value, b represents a humidity value;
the environmental pollution Wr is obtained by the following formula:
wherein: n represents an actual measured concentration value, m represents a standard concentration threshold value;
the electromagnetic field interference coefficient Cc is obtained by the following formula:
wherein: i represents the failure rate of the tested equipment under the electromagnetic field, and l represents the failure rate of the tested equipment under the condition of no electromagnetic field; the industrial equipment jitter Dd is obtained by the following formula:
Dd＝(J÷k)×100％
wherein: j represents the effective value acceleration and refers to the effective value of the vibration acceleration signal of the equipment, and k gravity acceleration refers to the gravity acceleration of the earth surface, and k is approximately equal to 9.8 m/s 2 ；
And carrying out normalization processing on the environmental temperature and humidity value Ws, the environmental pollution degree Wr, the electromagnetic field interference coefficient Cc, the industrial equipment jitter degree Dd and the barrier interference coefficient ZDxs.
Preferably, the normalized data of the environmental temperature and humidity value Ws, the environmental pollution level Wr, the electromagnetic field interference coefficient Cc, the industrial equipment jitter level Dd and the barrier interference coefficient Zdxs are correlated and summarized to form a factor influence value YS of a library, and the factor influence value YS of the library is fitted and calculated with the industrial network communication data Xn to obtain a communication quality index Zb.
Preferably, the communication quality index Zb is compared with a standard network quality threshold value, and then abnormal mode early warning is carried out, wherein the abnormal mode early warning comprises network delay abnormal early warning, transmission abnormal early warning and equipment state abnormal early warning.
The communication network fault early warning system based on artificial intelligence preferably comprises a data acquisition module, a data processing module, a model training module, a prediction module, an early warning module and a visual interface module;
the data acquisition module is used for acquiring data from an industrial communication network, including network flow, transmission speed and delay indexes;
the data processing module is responsible for processing and analyzing the acquired data, cleaning the data, extracting the characteristics and detecting the abnormality;
the model training module is responsible for training and modeling the network data by using a machine learning algorithm or a deep learning algorithm so as to identify a normal behavior mode and an abnormal behavior mode of the network;
and a prediction module: the prediction module is responsible for predicting the network data by using the trained model; obtaining a prediction result;
and the early warning module is used for: the early warning module is responsible for obtaining the prediction result in the prediction module to perform early warning, and when the network has abnormal conditions, the system automatically sends early warning information to an administrator;
the visual interface module is responsible for displaying the predicted and early-warning fault results to an administrator in the form of a chart or report, so that the administrator can conveniently analyze and make decisions.
Preferably, the data acquisition module comprises a network communication acquisition unit, an environment data acquisition unit and an operation state acquisition unit;
the network communication acquisition unit is used for acquiring various data of a communication network to obtain industrial network communication data Xn;
the environment data acquisition unit is used for acquiring factors influencing network performance indexes in an industrial environment and acquiring environment comprehensive influence data Yx;
the running state acquisition unit is used for acquiring running state data of the industrial automation equipment;
the early warning module comprises an early warning unit and a scheme summarizing unit.
(III) beneficial effects
The invention provides a communication network fault early warning method and system based on artificial intelligence. The beneficial effects are as follows:
(1) According to the communication network fault early warning method and system based on artificial intelligence, industrial network communication data Xn and environment comprehensive influence data Yx are acquired and obtained through S1-S2, feature extraction is carried out, the data with connection influence are combined, after a communication quality index Zb is obtained, a digital model is built for training, optimizing and predicting analysis in S3-S5, a predicted result is obtained, the predicted result is compared and analyzed with a standard network quality threshold value in S5, abnormal mode early warning is carried out, corresponding measure schemes are obtained and summarized, in the monitoring process of industrial network communication performance, industrial environment influence parameters which influence the industrial network communication performance are monitored and analyzed, an optimized scheme of industrial environment is obtained, and the problems of delay, clamping and influence on the network communication performance caused by industrial environment influence values on the equipment network operation speed and the like are reduced.
(2) According to the communication network fault early warning method and system based on artificial intelligence, according to different network environments and application scenes, the calculated blocking object interference coefficient ZDxs is obtained through an algorithm for calculating the blocking object interference coefficient, thickness and material attenuation degree of network signals, the influence degree and influence factors of blocking objects on the network signals can be known, and accordingly corresponding measures are adopted to optimize and adjust, and stability and reliability of network communication are improved.
(3) According to the communication network fault early warning method and system based on artificial intelligence, an environment temperature and humidity value Ws, an environment pollution degree Wr, an electromagnetic field interference coefficient Cc, an industrial equipment jitter degree Dd and a barrier interference coefficient ZDxs in environment comprehensive influence data Yx are monitored, calculated and summarized to obtain a factor influence value YS of a library, wherein the factor influence value YS of the library refers to the influence degree of environment factors on wireless communication quality, and generally comprises factors such as signal attenuation, multipath effect, signal to noise ratio and the like, a communication quality index Zb is compared with a standard network quality threshold value, and then abnormal mode early warning is carried out, the abnormal mode early warning comprises network delay abnormal early warning, transmission abnormal early warning and equipment state abnormal early warning, corresponding schemes are obtained to optimize, and the network communication quality is better as the optimized environment influence value is smaller.
(4) The communication network fault early warning method and system based on artificial intelligence have the advantages that the computing environment comprehensively influences the data Yx on the industrial network communication data Xn, and the benefits are mainly reflected in the aspects of optimizing network planning, predicting network performance, improving network capacity and reducing communication cost.
Drawings
FIG. 1 is a schematic flow diagram of a communication network fault early warning system based on artificial intelligence;
FIG. 2 is a schematic diagram of steps of a communication network fault early warning method based on artificial intelligence;
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all 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.
Example 1
The communication network comprises a wired communication network and a wireless communication network, and from the professional perspective, the wireless communication technology is based on radio waves, and under the support of a wireless optical cable, the requirement of connecting the computer equipment with a network data transmission system is met. Under the introduction of science and technology, wireless communication technology is continuously permeated in the field of industrial automation, the application value is outstanding, and the diversified industrial development requirements are increasingly met. In an industrial communication network, real-time monitoring and early warning are needed for performance values of the network, and the existing industrial network communication network is used for simply monitoring the equipment network in a manual inspection and remote monitoring mode, but in practice, many performance indexes which can influence network communication exist in the industrial environment, such as temperature change and humidity change can influence the network operation speed of the equipment, too many obstacles can influence the signal penetrating power of the equipment network, and too much dust can influence the heat dissipation stability of the equipment to influence the performance of the network.
The invention provides a communication network fault early warning method based on artificial intelligence, referring to fig. 1-2, comprising the following steps,
s1, collecting various data of a communication network of equipment in an industrial production line in real time to obtain industrial network communication data Xn;
the industrial network communication data Xn comprises bandwidth, time delay, packet loss rate, jitter variation value and throughput;
bandwidth: refers to the ability of a network to transmit data per unit time, typically in bits per second (bps) or megabits per second (Mbps).
Time delay: refers to the time required from the start of transmitting data to the reception of data by the counterpart, and is typically in units of milliseconds (ms).
Packet loss rate: refers to the probability, typically expressed in percent, that a missing data packet will occur during transmission;
dithering: refers to the delay variation of a data packet during transmission, typically in milliseconds (ms);
throughput: refers to the ability of a network to process data per unit time, typically in bits per second (bps) or megabits per second (Mbps).
The bandwidth, the flow and the equipment state of the network are monitored by adopting SNMP and NetFlow protocols;
adopting PLC and DCS equipment to collect data in the industrial production process;
adopting Traceroute and Ipref tools to test bandwidth, time delay and packet loss rate indexes of the network;
the type, IP address, equipment link number, state and flow of the production equipment are acquired by adopting a network analyzer and a signal generator.
S2, acquiring factors influencing network performance indexes in an industrial environment, and acquiring environment comprehensive influence data Yx; the environment comprehensive influence data Yx comprises an environment temperature and humidity value Ws, an environment pollution degree Wr, an electromagnetic field interference coefficient Cc, an industrial equipment jitter degree Dd and a barrier interference coefficient ZDxs;
the environmental temperature and humidity value Ws is acquired by adopting a temperature and humidity sensor;
the environmental pollution Wr is obtained by monitoring the concentration and pollution degree of particles in the air by adopting a particle sensor;
the electromagnetic field interference coefficient Cc is obtained by detecting electromagnetic field intensity and frequency parameters in an industrial environment through an electromagnetic field intensity meter and a frequency spectrum analyzer and further monitoring and analyzing;
the industrial equipment jitter Dd monitors the equipment jitter through a jitter monitoring tool, and the change and trend of the equipment jitter are known, so that the influence of the equipment jitter on network communication data is predicted.
Extracting characteristics of environment comprehensive influence data Yx and industrial network communication data Xn, and combining the data with the contact influence to obtain a communication quality index Zb;
s3, acquiring a communication quality index Zb, establishing a digital model, training data machine learning, and inputting the data subjected to feature extraction into the model for training and optimizing;
s4, predicting and calculating by using the trained model, predicting network communication quality under different environmental conditions, and obtaining the influence of environmental assessment data on industrial network communication;
s5, analyzing the model prediction result, carrying out abnormal mode early warning after comparing and analyzing according to the standard network quality threshold, and carrying out optimization and adjustment by adopting corresponding measures according to the abnormal mode early warning content.
In this embodiment, the industrial network communication data Xn and the environmental comprehensive influence data Yx are acquired in the steps S1-S2, the feature extraction is performed, the data with related influence are combined, the communication quality index Zb is obtained, then, in the steps S3-S5, a digital model is built to train, optimize and predict and analyze, the predicted result is obtained, and in the step S5, the predicted result is compared and analyzed with the standard network quality threshold, then, the abnormal mode early warning is performed, the corresponding measure scheme is obtained and summarized, in the monitoring process of the industrial network communication performance, the monitoring analysis is performed on the industrial environmental influence parameters which influence the industrial network communication performance, the scheme for optimizing the industrial environment is obtained, and the problems of delay, blocking, influence on the network operation speed of equipment and the like caused by the industrial environmental influence value on the network communication performance are reduced.
Example 2
The present embodiment is explained in embodiment 1, specifically, the barrier interference coefficient Zdxs includes obtaining the thickness, the material, and the barrier of the barrier, so as to obtain the attenuation degree of the influence on the signal;
identifying the thickness of the barrier in a picture for identifying the cargo barrier by an intelligent identification monitoring camera;
testing the delay condition of network transmission of network equipment and industrial equipment by adopting a transmission testing tool; placing barriers with different thicknesses between the distances of the network equipment and the industrial equipment, and recording data;
and obtaining materials of steel materials, walls and glass barriers with different thicknesses, and fitting the materials of the barriers, the thicknesses of the barriers, the attenuation degree of network signals and the network delay value to obtain a barrier interference coefficient ZDxs.
The barrier disturbance factor Zdxs is calculated by the following formula:
Zdxs＝10 Λ (-D/10)
wherein D is the attenuation of the signal by the barrier; calculating the signal attenuation amount: the amount of attenuation in decibels (dB) of a signal as it passes through a barrier is calculated by testing the signal strength before barriers of different thickness and materials.
The attenuation degree D is calculated by the following formula
Wherein: x represents the thickness of the barrier, y represents the material of the barrier, z represents the delay amount of the test network delay value, wherein beta is the signal penetration coefficient, and the coefficient is obtained through the barrier transparency test, wherein: and beta is more than or equal to 40 and less than or equal to 80, wherein the specific value of beta can be adjusted and corrected by a user according to actual experience, and the baffle interference coefficient ZDxs is corrected by changing the value of beta.
Calculating the attenuation degree: by calculating the signal attenuation and the signal transmission distance, the signal attenuation coefficient in units of decibels/meter (dB/m) is calculated.
Calculating the total attenuation: the total attenuation of the signal after passing through the plurality of barriers is calculated by adding the attenuation coefficients of the barriers with different thicknesses and materials.
According to different network environments and application scenes, the calculated interference coefficient Zdxs of the barrier is obtained through an algorithm for calculating the interference coefficient, thickness and material attenuation degree of the barrier to the network signals, and the influence degree and influence factors of the barrier to the network signals can be known, so that corresponding measures are adopted to optimize and adjust, and the stability and reliability of network communication are improved.
Example 3
This example is an explanation made in example 1, specifically:
the ambient temperature and humidity value Ws is obtained by the following formula:
Ws＝(a,b)
wherein: a represents a temperature value, b represents a humidity value;
the environmental pollution Wr is obtained by the following formula:
wherein: n represents an actual measured concentration value, m represents a standard concentration threshold value;
the measured concentration refers to the concentration of a certain pollutant measured in the air, and the standard concentration refers to the allowable concentration limit value of the pollutant in the air. For example, the national standard concentration limit for PM2.5 is 75 micrograms/cubic meter. If the measured PM2.5 concentration in a region is 100 micrograms/cubic meter, the air pollution level in that region is:
(100÷75)×100％＝133.3％
this means that the PM2.5 concentration in the area has exceeded the national standard limit of 133.3%.
The electromagnetic field interference coefficient Cc is obtained by the following formula:
wherein: i represents the failure rate of the tested equipment under the electromagnetic field, and l represents the failure rate of the tested equipment under the condition of no electromagnetic field;
the electromagnetic field interference coefficient is a parameter describing the degree of interference of an electromagnetic field with an electronic device.
The failure rate of the tested device under the electromagnetic field refers to the probability of the device to fail under the electromagnetic field environment, and the failure rate of the tested device under the electromagnetic field-free environment refers to the probability of the device to fail under the electromagnetic field-free environment.
For example, if the failure rate of a certain device in an electromagnetic field-free environment is 1% and the failure rate in an electromagnetic field environment is 5%, the electromagnetic field interference coefficient of the device in the electromagnetic field environment is:
(5÷1)×100％＝500％
this means that the electromagnetic field environment interferes to a great extent with the device, and corresponding measures need to be taken to reduce the influence of the electromagnetic field on the device.
The industrial equipment jitter Dd is obtained by the following formula:
Dd＝(J÷k)×100％
wherein: j represents the effective value acceleration and refers to the effective value of the vibration acceleration signal of the equipment, and k gravity acceleration refers to the gravity acceleration of the earth surface, and k is approximately equal to 9.8 m/s 2 ；
Industrial equipment jitter is a parameter describing the vibration of the equipment, usually expressed using acceleration.
For example, if the effective value of the vibration acceleration signal of a certain device is0.5 m/s 2 The jitter of the device is:
(0.5÷9.8)×100％≈5.1％
this means that the vibration conditions of the device are small, in the normal range. If the jitter exceeds the allowable range of the device, corresponding measures need to be taken to reduce the vibration of the device.
And carrying out normalization processing on the environmental temperature and humidity value Ws, the environmental pollution degree Wr, the electromagnetic field interference coefficient Cc, the industrial equipment jitter degree Dd and the barrier interference coefficient ZDxs.
Preferably, the normalized data of the environmental temperature and humidity value Ws, the environmental pollution level Wr, the electromagnetic field interference coefficient Cc, the industrial equipment jitter level Dd and the barrier interference coefficient Zdxs are correlated and summarized to form a factor influence value YS of a library, and the factor influence value YS of the library is fitted and calculated with the industrial network communication data Xn to obtain a communication quality index Zb.
And comparing the communication quality index Zb with a standard network quality threshold value, and further carrying out abnormal mode early warning, wherein the abnormal mode early warning comprises network delay abnormal early warning, transmission abnormal early warning and equipment state abnormal early warning.
In this embodiment, the data Yx is comprehensively influenced by the environment; the environment comprehensive influence data Yx comprises an environment temperature and humidity value Ws, an environment pollution degree Wr, an electromagnetic field interference coefficient Cc, an industrial equipment jitter degree Dd and a barrier interference coefficient Zdxs, the environment comprehensive influence data Yx are monitored, calculated and summarized to obtain a factor influence value YS of a library, the factor influence value YS of the library refers to the influence degree of environment factors on wireless communication quality, the factor influence value YS generally comprises factors such as signal attenuation, multipath effect and signal to noise ratio, the communication quality index Zb is compared with a standard network quality threshold value, and then abnormal mode early warning is carried out, the abnormal mode early warning comprises network delay abnormal early warning, transmission abnormal early warning and equipment state abnormal early warning, a corresponding scheme is obtained to optimize, and the network communication quality is better as the optimized environment influence value is smaller.
Example 4
This embodiment is explained in embodiment 1, please refer to fig. 1-2, specifically:
the communication network fault early warning system based on artificial intelligence preferably comprises a data acquisition module, a data processing module, a model training module, a prediction module, an early warning module and a visual interface module;
the data acquisition module is used for acquiring data from an industrial communication network, including network flow, transmission speed and delay indexes;
the data processing module is responsible for processing and analyzing the acquired data, cleaning the data, extracting the characteristics and detecting the abnormality;
the model training module is responsible for training and modeling the network data by using a machine learning algorithm or a deep learning algorithm so as to identify a normal behavior mode and an abnormal behavior mode of the network;
and a prediction module: the prediction module is responsible for predicting the network data by using the trained model; obtaining a prediction result;
and the early warning module is used for: the early warning module is responsible for obtaining the prediction result in the prediction module to perform early warning, and when the network has abnormal conditions, the system automatically sends early warning information to an administrator;
the visual interface module is responsible for displaying the predicted and early-warning fault results to an administrator in the form of a chart or report, so that the administrator can conveniently analyze and make decisions.
Preferably, the data acquisition module comprises a network communication acquisition unit, an environment data acquisition unit and an operation state acquisition unit;
the network communication acquisition unit is used for acquiring various data of a communication network to obtain industrial network communication data Xn;
the environment data acquisition unit is used for acquiring factors influencing network performance indexes in an industrial environment and acquiring environment comprehensive influence data Yx;
the running state acquisition unit is used for acquiring running state data of the industrial automation equipment;
the early warning module comprises an early warning unit and a scheme summarizing unit.
The system has the beneficial effects that the network planning is optimized: through measurement and analysis of environmental impact values, the propagation condition of wireless signals in different environments can be known, so that network planning is optimized, and network coverage rate and communication quality are improved.
Predicting network performance: according to the change trend of the environmental impact value, the change condition of the network communication quality can be predicted, and measures can be timely taken for adjustment and optimization.
Network capacity is improved: by reducing the environmental impact value, the influence of factors such as signal attenuation, multipath effect and the like on wireless signals can be reduced, and the network capacity and the data transmission rate are improved.
The communication cost is reduced: by optimizing network planning and improving network capacity, communication cost can be reduced, communication efficiency can be improved, and better communication service can be provided for users.
In summary, the benefits of the computing environment comprehensive influence data Yx on the industrial network communication data Xn are mainly reflected in the aspects of optimizing network planning, predicting network performance, improving network capacity, reducing communication cost, and the like.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A communication network fault early warning method based on artificial intelligence is characterized in that: comprises the steps of,
s1, collecting various data of a communication network of equipment in an industrial production line in real time to obtain industrial network communication data Xn;
the industrial network communication data Xn comprises bandwidth, time delay, packet loss rate, jitter variation value and throughput;
s2, acquiring factors influencing network performance indexes in an industrial environment, and acquiring environment comprehensive influence data Yx; the environment comprehensive influence data Yx comprises an environment temperature and humidity value Ws, an environment pollution degree Wr, an electromagnetic field interference coefficient Cc, an industrial equipment jitter degree Dd and a barrier interference coefficient ZDxs;
extracting characteristics of environment comprehensive influence data Yx and industrial network communication data Xn, and combining the data with the contact influence to obtain a communication quality index Zb;
s3, acquiring a communication quality index Zb, establishing a digital model, training data machine learning, and inputting the data subjected to feature extraction into the model for training and optimizing;
s4, predicting and calculating by using the trained model, predicting network communication quality under different environmental conditions, and obtaining the influence of environmental assessment data on industrial network communication;
s5, analyzing the model prediction result, carrying out abnormal mode early warning after comparing and analyzing according to the standard network quality threshold, and carrying out optimization and adjustment by adopting corresponding measures according to the abnormal mode early warning content.
2. The communication network fault early warning method based on artificial intelligence according to claim 1, wherein the communication network fault early warning method based on artificial intelligence is characterized in that:
the bandwidth, the flow and the equipment state of the network are monitored by adopting SNMP and NetFlow protocols;
adopting PLC and DCS equipment to collect data in the industrial production process;
adopting Traceroute and Ipref tools to test bandwidth, time delay and packet loss rate indexes of the network;
the type, IP address, equipment link number, state and flow of the production equipment are acquired by adopting a network analyzer and a signal generator.
3. The communication network fault early warning method based on artificial intelligence according to claim 1, wherein the communication network fault early warning method based on artificial intelligence is characterized in that:
the environmental temperature and humidity value Ws is acquired by adopting a temperature and humidity sensor;
the environmental pollution Wr is obtained by monitoring the concentration and pollution degree of particles in the air by adopting a particle sensor;
the electromagnetic field interference coefficient Cc is obtained by detecting electromagnetic field intensity and frequency parameters in an industrial environment through an electromagnetic field intensity meter and a frequency spectrum analyzer and further monitoring and analyzing;
the industrial equipment jitter Dd monitors the equipment jitter through a jitter monitoring tool, and the change and trend of the equipment jitter are known, so that the influence of the equipment jitter on network communication data is predicted.
4. The communication network fault early warning method based on artificial intelligence according to claim 1, wherein the communication network fault early warning method based on artificial intelligence is characterized in that: the barrier interference coefficient ZDxs comprises the steps of obtaining the thickness, the material and the barrier of the barrier, and further obtaining the influence attenuation degree of the signal;
identifying the thickness of the barrier in a picture for identifying the cargo barrier by an intelligent identification monitoring camera;
testing the delay condition of network transmission of network equipment and industrial equipment by adopting a transmission testing tool; placing barriers with different thicknesses between the distances of the network equipment and the industrial equipment, and recording data;
and obtaining materials of steel materials, walls and glass barriers with different thicknesses, and fitting the materials of the barriers, the thicknesses of the barriers, the attenuation degree of network signals and the network delay value to obtain a barrier interference coefficient ZDxs.
5. The communication network fault early warning method based on artificial intelligence according to claim 1, wherein the communication network fault early warning method based on artificial intelligence is characterized in that: the barrier disturbance factor Zdxs is calculated by the following formula:
Zdxs＝10 Λ (-D/10)
wherein D is the attenuation of the signal by the barrier;
the attenuation degree D is calculated by the following formula
Wherein: x represents the thickness of the barrier, y represents the material of the barrier, z represents the delay amount of the test network delay value, wherein beta is the signal penetration coefficient, and the coefficient is obtained through the barrier transparency test, wherein: and beta is more than or equal to 40 and less than or equal to 80, wherein the specific value of beta can be adjusted and corrected by a user according to actual experience, and the baffle interference coefficient ZDxs is corrected by changing the value of beta.
6. The communication network fault early warning method based on artificial intelligence according to claim 1, wherein the communication network fault early warning method based on artificial intelligence is characterized in that: the ambient temperature and humidity value Ws is obtained by the following formula:
Ws＝(a,b)
wherein: a represents a temperature value, b represents a humidity value;
the environmental pollution Wr is obtained by the following formula:
wherein: n represents an actual measured concentration value, m represents a standard concentration threshold value;
the electromagnetic field interference coefficient Cc is obtained by the following formula:
wherein: i represents the failure rate of the tested equipment under the electromagnetic field, and l represents the failure rate of the tested equipment under the condition of no electromagnetic field;
the industrial equipment jitter Dd is obtained by the following formula:
Dd＝(J÷k)×100％
wherein: j represents the effective value acceleration, namely the effective value of a vibration acceleration signal of the equipment, and k gravity acceleration is the gravity acceleration of the earth surface, wherein k is approximately 9.8 m/s < 2 >;
and carrying out normalization processing on the environmental temperature and humidity value Ws, the environmental pollution degree Wr, the electromagnetic field interference coefficient Cc, the industrial equipment jitter degree Dd and the barrier interference coefficient ZDxs.
7. The communication network fault early warning method based on artificial intelligence according to claim 1, wherein the communication network fault early warning method based on artificial intelligence is characterized in that: and correlating and summarizing the data of the environment temperature and humidity value Ws, the environment pollution degree Wr, the electromagnetic field interference coefficient Cc, the industrial equipment jitter degree Dd and the barrier interference coefficient ZDxs after normalization processing to form a factor influence value YS of a library, and carrying out fitting calculation on the factor influence value YS of the library and the industrial network communication data Xn to obtain a communication quality index Zb.
8. The communication network fault early warning method based on artificial intelligence according to claim 1, wherein the communication network fault early warning method based on artificial intelligence is characterized in that:
and comparing the communication quality index Zb with a standard network quality threshold value, and further carrying out abnormal mode early warning, wherein the abnormal mode early warning comprises network delay abnormal early warning, transmission abnormal early warning and equipment state abnormal early warning.
9. A communication network fault early warning system based on artificial intelligence is characterized in that: the system comprises a data acquisition module, a data processing module, a model training module, a prediction module, an early warning module and a visual interface module;
the data acquisition module is used for acquiring data from an industrial communication network, including network flow, transmission speed and delay indexes;
the data processing module is responsible for processing and analyzing the acquired data, cleaning the data, extracting the characteristics and detecting the abnormality;
the model training module is responsible for training and modeling the network data by using a machine learning algorithm or a deep learning algorithm so as to identify a normal behavior mode and an abnormal behavior mode of the network;
and a prediction module: the prediction module is responsible for predicting the network data by using the trained model; obtaining a prediction result;
and the early warning module is used for: the early warning module is responsible for obtaining the prediction result in the prediction module to perform early warning, and when the network has abnormal conditions, the system automatically sends early warning information to an administrator;
the visual interface module is responsible for displaying the predicted and early-warning fault results to an administrator in the form of a chart or report, so that the administrator can conveniently analyze and make decisions.
10. The communication network fault early warning system based on artificial intelligence according to claim 9, characterized in that: the data acquisition module comprises a network communication acquisition unit, an environment data acquisition unit and an operation state acquisition unit;
the network communication acquisition unit is used for acquiring various data of a communication network to obtain industrial network communication data Xn;
the environment data acquisition unit is used for acquiring factors influencing network performance indexes in an industrial environment and acquiring environment comprehensive influence data Yx;
the running state acquisition unit is used for acquiring running state data of the industrial automation equipment;
the early warning module comprises an early warning unit and a scheme summarizing unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310540928.8A CN116506275A (en) | 2023-05-15 | 2023-05-15 | Communication network fault early warning method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310540928.8A CN116506275A (en) | 2023-05-15 | 2023-05-15 | Communication network fault early warning method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116506275A true CN116506275A (en) | 2023-07-28 |
Family
ID=87318166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310540928.8A Pending CN116506275A (en) | 2023-05-15 | 2023-05-15 | Communication network fault early warning method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116506275A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116884193A (en) * | 2023-08-03 | 2023-10-13 | 上海创芯致锐互联网络有限公司 | Chip factory intelligent production monitoring alarm system based on multi-terminal induction fusion |
| CN117082561A (en) * | 2023-10-12 | 2023-11-17 | 北京绿色苹果技术有限公司 | Intelligent monitoring and evaluating method, system and medium for communication network |
| CN117406731A (en) * | 2023-10-24 | 2024-01-16 | 东莞东晟装备科技有限公司 | Unmanned moving target vehicle cooperative formation control method and system |
| CN117499443A (en) * | 2023-12-28 | 2024-02-02 | 湖南信健科技有限公司 | Distributed control system DCS communication loose coupling management system |
-
2023
- 2023-05-15 CN CN202310540928.8A patent/CN116506275A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116884193A (en) * | 2023-08-03 | 2023-10-13 | 上海创芯致锐互联网络有限公司 | Chip factory intelligent production monitoring alarm system based on multi-terminal induction fusion |
| CN116884193B (en) * | 2023-08-03 | 2024-02-06 | 上海创芯致锐互联网络有限公司 | Chip factory intelligent production monitoring alarm system based on multi-terminal induction fusion |
| CN117082561A (en) * | 2023-10-12 | 2023-11-17 | 北京绿色苹果技术有限公司 | Intelligent monitoring and evaluating method, system and medium for communication network |
| CN117082561B (en) * | 2023-10-12 | 2024-01-02 | 北京绿色苹果技术有限公司 | Intelligent monitoring and evaluating method, system and medium for communication network |
| CN117406731A (en) * | 2023-10-24 | 2024-01-16 | 东莞东晟装备科技有限公司 | Unmanned moving target vehicle cooperative formation control method and system |
| CN117406731B (en) * | 2023-10-24 | 2024-05-24 | 东莞东晟装备科技有限公司 | Unmanned moving target vehicle cooperative formation control method and system |
| CN117499443A (en) * | 2023-12-28 | 2024-02-02 | 湖南信健科技有限公司 | Distributed control system DCS communication loose coupling management system |
| CN117499443B (en) * | 2023-12-28 | 2024-03-29 | 湖南信健科技有限公司 | Distributed control system DCS communication loose coupling management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116506275A (en) | Communication network fault early warning method and system based on artificial intelligence | |
| CN103856789B (en) | The system and method that OTT quality of services are ensured is realized based on user behavior analysis | |
| EP1727375A1 (en) | Assessment of perceived quality of a packetized video stream | |
| CN116839682B (en) | Cable processing and manufacturing real-time monitoring system based on Internet of things | |
| CN113485268B (en) | Industrial Internet of things-based multi-scene distributed information control system | |
| CN116365711A (en) | Intelligent monitoring system for power supply and distribution of vehicle-mounted shelter based on Internet of things | |
| CN115566804B (en) | Electric power monitoring system based on distributed optical fiber sensing technology | |
| CN114004306A (en) | Equipment fault evaluation system and method based on multi-dimensional data of Internet of things | |
| CN116300835B (en) | Automatic detection equipment remote diagnosis system based on Internet | |
| CN116593495B (en) | Operation and maintenance intelligent control system and method for flue gas online monitoring equipment | |
| CN116181416A (en) | Multi-parameter advanced early warning system and method for rock burst | |
| CN113422690A (en) | Service quality degradation prediction method and system | |
| CN113763667A (en) | Fire early warning and state monitoring device and method based on 5G edge calculation | |
| CN117319047A (en) | Network path analysis method and system based on network security anomaly detection | |
| CN115022908A (en) | Method for predicting and positioning abnormity of core network and base station transmission network | |
| CN115986918A (en) | Intelligent monitoring system for power transmission line | |
| CN111289812A (en) | Power transmission and transformation equipment state monitoring and management method and system | |
| KR20220132824A (en) | Distribution facility condition monitoring system and method | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN114925867A (en) | Internet of things maintenance prediction system for key equipment in seamless steel tube production | |
| CN112345648B (en) | High-voltage circuit breaker cam crack fault detection device and method | |
| KR20230072164A (en) | Product quality management system for zero defect rate | |
| CN112218320A (en) | Mobile communication data traffic abnormity monitoring system and method | |
| CN112505501A (en) | Partial discharge severity grade judging and early warning method based on electroacoustic combination | |
| CN116828513A (en) | Real-time maintenance method for mobile communication network |
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 |