CN117675522A - Power communication fault diagnosis and prevention method and system - Google Patents
Power communication fault diagnosis and prevention method and system Download PDFInfo
- Publication number
- CN117675522A CN117675522A CN202311795325.9A CN202311795325A CN117675522A CN 117675522 A CN117675522 A CN 117675522A CN 202311795325 A CN202311795325 A CN 202311795325A CN 117675522 A CN117675522 A CN 117675522A
- Authority
- CN
- China
- Prior art keywords
- fault
- power communication
- alarm
- network
- fault diagnosis
- 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
- 230000006854 communication Effects 0.000 title claims abstract description 173
- 238000004891 communication Methods 0.000 title claims abstract description 172
- 238000003745 diagnosis Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000002265 prevention Effects 0.000 title claims abstract description 23
- 238000012423 maintenance Methods 0.000 claims abstract description 71
- 230000002159 abnormal effect Effects 0.000 claims abstract description 50
- 230000005856 abnormality Effects 0.000 claims abstract description 43
- 238000011217 control strategy Methods 0.000 claims abstract description 30
- 230000003449 preventive effect Effects 0.000 claims abstract description 25
- 238000007689 inspection Methods 0.000 claims abstract description 11
- 230000000737 periodic effect Effects 0.000 claims abstract description 7
- 238000007667 floating Methods 0.000 claims description 34
- 238000011176 pooling Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- 238000005265 energy consumption Methods 0.000 claims description 7
- 231100000279 safety data Toxicity 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 238000002955 isolation Methods 0.000 claims description 3
- 230000017525 heat dissipation Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005096 rolling process Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 238000004458 analytical method Methods 0.000 abstract description 10
- 238000007726 management method Methods 0.000 description 15
- 238000013527 convolutional neural network Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 8
- 230000001965 increasing effect Effects 0.000 description 6
- 238000009826 distribution Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000012795 verification Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000008713 feedback mechanism Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 230000003442 weekly effect Effects 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
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a power communication fault diagnosis and prevention method and a system thereof, belonging to the technical field of communication fault management, wherein an edge computing device is used for identifying whether power communication has abnormal conditions and judging whether an alarm needs to be generated, when the power communication is identified to have abnormal conditions, the fault diagnosis model is used for carrying out deep analysis to determine the specific property and the influence range of a problem so as to carry out accurate diagnosis, a corresponding preventive maintenance plan is formulated according to monitoring and diagnosis results, the periodic inspection, equipment maintenance, upgrading and the like are included, a corresponding control strategy is automatically executed on a power communication network according to the fault diagnosis results, and the self-healing capacity of the power communication network is improved. The system can carry out problem diagnosis and preventive decision support on the occurrence of abnormality, effectively improves the management efficiency of the power communication network, has high decision accuracy, can enable the power communication network to recover to a normal state in time, and ensures the stable operation of the power communication network.
Description
Technical Field
The invention relates to the technical field of communication fault management, in particular to a power communication fault diagnosis and prevention method and system.
Background
The power communication is developed to meet the requirement of a power system on remote monitoring and control, and with the continuous development and expansion of the power system, the power equipment distributed in a wide area needs to be monitored and controlled in real time, so that the application and development of a power communication technology are promoted, the power communication is mainly applied to the power system, comprises links of power production, transmission, distribution, consumption and the like, and is widely applied to power equipment and systems of power plants, substations, distribution networks and the like, and the functions of remote monitoring, fault diagnosis, data acquisition, remote control and the like of a power grid are realized;
the power communication system generally comprises a large number of devices and networks, and relates to a plurality of links such as power generation, transmission, power distribution and the like, and due to the complexity of the system, faults can be widely influenced, timely diagnosis and prevention are carried out on the faults, and stable operation and quick recovery of the power communication system are ensured, so that the reliability and safety of the power system are improved.
The prior art has the following defects:
1. as the topology of the power communication network becomes more and more complex, the network fault diagnosis becomes more and more difficult, the traditional strategy that the alarm data are collected from the network management manually and the fault source is positioned by experience or rules is difficult to ensure, the accuracy and the judgment speed are difficult to ensure, if the decision error possibly has great influence on the maintenance efficiency, and the network cannot be recovered to the normal state in time;
2. When the existing management system monitors that the power communication network is abnormal, alarm information is sent to management maintenance personnel, however, due to complexity and uncertainty of the power communication network, the management system can carry out diagnosis and prevention decision support on the occurrence of the abnormality, the workload of the management maintenance personnel can be increased, and the management efficiency of the power communication network is reduced.
Disclosure of Invention
The invention aims to provide a power communication fault diagnosis and prevention method and system, which are used for solving the defects in the background technology.
In order to achieve the above object, the present invention provides the following technical solutions: a power communication fault diagnosis and prevention method, the prevention method comprising the steps of:
s1: the acquisition end collects real-time data from the power communication network and sends the collected real-time data to the edge computing equipment;
s2: the edge computing equipment analyzes the real-time data, identifies whether an abnormal condition exists in the power communication network and judges whether an alarm needs to be generated or not;
s3: when the abnormal condition of the power communication is identified, diagnosing the abnormality through a fault diagnosis model, and determining the nature and the influence range of the abnormality;
s4: the management end makes a corresponding preventive maintenance plan according to the diagnosis result, and automatically executes a corresponding control strategy on the power communication network according to the fault diagnosis result;
S5: uploading the operation state, fault information and maintenance record of the power communication network to a cloud record after generating a report;
s6: and providing a user interface to enable operation and maintenance personnel to know the operation state, fault information and maintenance record of the power communication network.
In a preferred embodiment, in step S2, the edge computing device analyzing the real-time data, identifying whether an anomaly exists in the power communication network and determining whether an alarm needs to be generated comprises the steps of:
s201: acquiring network data, equipment data and safety data of an electric power communication network, wherein the network data comprises a network signal floating coefficient, the equipment data comprises an equipment performance floating coefficient, and the safety data comprises a communication state floating coefficient;
s202: the edge computing device establishes an abnormal coefficient yc after normalizing the network signal floating coefficient, the device performance floating coefficient and the communication state floating coefficient x ;
S203: if the anomaly coefficient yc x The method comprises the steps of identifying that an abnormal condition does not exist in the power communication network and generating no alarm when the power communication network is larger than or equal to an abnormal threshold value;
s204: if the anomaly coefficient yc x If the power communication network is smaller than the abnormality threshold, an abnormality is identified, and an alarm needs to be generated.
In a preferred embodiment, the network signal floating coefficient is calculated as: Wherein W (t) is the real-time variation of the bandwidth of the network signal, [ t ] a ,t b ]Time period of signal intensity over-frequency, [ t ] c ,t d ]A time period for network delay early warning;
the calculation expression of the device performance floating coefficient is as follows:wherein S (t) is the real-time variation of the load of the equipment, [ t ] e ,t f ]For the time period of early warning of the energy consumption of the equipment, [ t ] g ,t h ]A time period for device temperature pre-warning;
the communication stateThe calculated expression of the state floating coefficient is:wherein T (T) is the real-time variation of communication flow, [ T ] i ,t j ]For the period of abnormal attack early warning, [ t ] k ,t l ]And verifying the early warning time period for the communication.
In a preferred embodiment, in step S3, the establishment of the fault diagnosis model includes the steps of:
s301: inputting the fault state matrix obtained in the data processing stage into a CNN network, and extracting different fault class feature diagrams by convolution operation;
s302: after the convolution layer obtains the fault feature map, the feature map is input to a pooling layer, and the pooling layer samples partial data of the feature map through the maximum pooling operation;
s303: after the rolling and pooling operation, the CNN network extracts feature graphs of different fault categories;
s304: the full-connection layer combines the fault class feature graphs output by the pooling layer, and then sends the fault class feature graphs into a softmax classifier to classify different fault class feature graphs to obtain fault feature output;
S305: comparing the fault characteristic output with a true value, calculating an error between the fault characteristic output and the true value, and if the CNN network has no convergence, returning the error between the fault characteristic output and the true value to each layer of the network;
s306: and correcting the weight of each layer of nodes by using a BP algorithm, and recalculating the error between the fault characteristic output and the true value until the CNN network is converged and then outputting the CNN network, thereby completing the establishment of a fault diagnosis model.
In a preferred embodiment, in step S301, the fault state matrix acquisition comprises the steps of:
s3011: collecting all alarm information in the power communication network to obtain an original alarm information database;
s3012: based on the characteristics of the original alarm information data and the fault diagnosis purpose, carrying out standardized processing on the alarm information fields to obtain a target alarm information database;
s3013: the method comprises the steps of synchronously extracting alarm transactions from time and sites by adopting a time window mode for data of a target alarm information database;
s3014: and carrying out alarm transaction coding on alarm information of the power communication network according to the site unit to obtain a topological connection and a fault state matrix representing the whole network, and finally marking a label for the fault state matrix with a root fault.
In a preferred embodiment, in step S3012, the normalization of the alert information field includes the steps of:
s30121: selecting an alarm information field related to fault diagnosis, and performing deduplication on an original alarm information database;
s30122: the defined field name and attribute value are used as the standard format of the alarm information to carry out standardized processing on the alarm data of the webmaster of all manufacturers
S30123: the alarm information of each site at the moment of failure is synchronously processed by a time window size method to form an alarm transaction;
s30124: the importance of each alarm for each fault judgment is set by using the historical data, the alarm weight of each alarm for final fault diagnosis is calculated, all alarm types are ordered according to the alarm weight from large to small, and the higher the alarm weight is, the higher the alarm priority is.
In a preferred embodiment, the alarm weight is calculated as: wherein qz A Represents the alarm weight, qz x The weight of the alarm on the x-th fault effect is represented, and x=1, 2, 3, y represents the type of fault, and y is a positive integer, s A Representing qz x A number not equal to 0.
In a preferred embodiment, in step S3, when an abnormality in power communication is identified, diagnosis is performed by a fault diagnosis model, determining abnormality properties and influence ranges includes the steps of:
s307: collecting detailed information related to the abnormality, and extracting related features from the abnormality information;
s308: when an abnormal situation occurs, inputting abnormal information into a fault diagnosis model, and outputting the nature and the influence range of the abnormality by the fault diagnosis model;
s309: based on the output of the fault diagnosis model, a diagnosis report is generated, the report including the cause of the abnormality, the solution, the maintenance operation.
In a preferred embodiment, in step S4, the management end makes a corresponding preventive maintenance plan according to the diagnosis result, and automatically executes a corresponding control strategy for the power communication network according to the fault diagnosis result, including the following steps:
s401: analyzing the output of the fault diagnosis model, and knowing the nature and influence range of the abnormality;
s402: classifying the abnormality, and determining priority according to the severity of the abnormality and the urgency;
s403: making a periodic equipment inspection and maintenance plan, including inspection of equipment states, power supplies, communication modules and heat dissipation systems;
S404: making an upgrade plan for firmware and software running on the equipment, installing updated firmware and software versions in time and repairing known vulnerabilities;
s405: selecting a control strategy according to the fault diagnosis result, wherein the control strategy comprises equipment restarting, network topology adjustment, signal strength optimization and fault equipment isolation;
s406: generating a control signal for automatically executing the control strategy, and automatically executing the selected control strategy, wherein the control strategy comprises restarting equipment, adjusting network configuration and sending out a signal optimization instruction.
The invention also provides a power communication fault diagnosis and prevention system, which comprises an acquisition module, an edge calculation module, a fault diagnosis module, a prevention maintenance module, an automatic control module, a report recording module and a user interface module;
and the acquisition module is used for: collecting real-time data from the power communication network;
and an edge calculation module: analyzing the real-time data, identifying whether the power communication has abnormal conditions and judging whether an alarm needs to be generated;
and a fault diagnosis module: when the abnormal condition of the power communication is identified, diagnosing through a fault diagnosis model, and determining the abnormal property and the influence range;
and a preventive maintenance module: according to the fault diagnosis result, a corresponding preventive maintenance plan is formulated;
And the automatic control module is used for: automatically executing a corresponding control strategy on the power communication network according to the fault diagnosis result;
report recording module: uploading the operation state, fault information and maintenance record of the power communication network to a cloud record after generating a report;
a user interface module: and providing a user interface to enable operation and maintenance personnel to know the operation state, fault information and maintenance record of the power communication network.
In the technical scheme, the invention has the technical effects and advantages that:
according to the invention, whether the power communication has abnormal conditions or not is identified through the edge computing equipment, whether an alarm needs to be generated is judged, when the abnormal conditions of the power communication are identified, the fault diagnosis model is used for carrying out deep analysis, the specific nature and the influence range of the problem are determined, so that accurate diagnosis is carried out, corresponding preventive maintenance plans are formulated according to monitoring and diagnosis results, including periodic inspection, equipment maintenance, upgrading and the like, corresponding control strategies are automatically executed on the power communication network according to the fault diagnosis results, and the self-healing capacity of the power communication network is improved. The system can carry out problem diagnosis and preventive decision support on the occurrence of abnormality, effectively improves the management efficiency of the power communication network, has high decision accuracy, can enable the power communication network to recover to a normal state in time, and ensures the stable operation of the power communication network.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a block diagram of a system according to the present invention.
FIG. 3 is a flow chart of the processing of alarm data by an edge computing device in accordance with the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. 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: referring to fig. 1, the method for diagnosing and preventing power communication faults according to the present embodiment includes the following steps:
The acquisition end collects real-time data from the power communication network, wherein the real-time data comprise equipment states, signal intensity, data transmission conditions and the like, and specifically comprises the following steps:
the method comprises the steps of terminating a collection device at a collection end, ensuring that the device can be normally connected with an electric power communication network, carrying out necessary configuration, including network setting, data collection frequency and the like, ensuring that the collection device is successfully connected with the electric power communication network through a proper interface or communication protocol, possibly comprising a gateway connected with the electric power communication system or directly communicating with the communication device, monitoring and collecting state information related to the electric power communication device in real time, possibly comprising whether the device is online, working state, power state and the like, measuring the strength of a communication signal to know the signal quality of the device in the communication network, and monitoring the transmission condition of real-time data in the communication network, including parameters such as data transmission rate, packet loss rate and the like, so as to ensure reliable transmission of the data, formatting the collected data according to a pre-defined standard, and ensuring consistency and easy processing of the data.
The collected data are sent to edge computing equipment for rapid diagnosis and analysis, and the edge computing equipment identifies whether the power communication has abnormal conditions and judges whether an alarm needs to be generated or not, specifically comprises the following steps:
The edge computing device analyzing the real-time data, identifying whether an abnormal condition exists in the power communication network and judging whether an alarm needs to be generated or not comprises the following steps:
acquiring network data, equipment data and safety data of an electric power communication network, wherein the network data comprises a network signal floating coefficient, the equipment data comprises an equipment performance floating coefficient, and the safety data comprises a communication state floating coefficient;
the edge computing device establishes an abnormal coefficient yc after normalizing the network signal floating coefficient, the device performance floating coefficient and the communication state floating coefficient x The expression is:wherein WF is the network signal floating coefficient, SF is the device performance floating coefficient, TF is the communication state floating coefficient, alpha, beta and gamma are the weighting coefficients of the network signal floating coefficient, the device performance floating coefficient and the communication state floating coefficient respectively, and 1>β>α>γ>0。
Obtaining an anomaly coefficient yc x After that, the anomaly coefficient yc x Comparing with a preset abnormal threshold value, if the abnormal coefficient yc x If the abnormality threshold is greater than or equal to the abnormality threshold, the power communication network is identified that no abnormality exists, an alarm is not required to be generated, and if the abnormality coefficient yc is the abnormality coefficient yc x If the power communication network is smaller than the abnormality threshold value, recognizing that the power communication network has abnormality, and generating an alarm;
The calculation expression of the floating coefficient of the network signal is as follows:wherein W (t) is the real-time variation of the bandwidth of the network signal, [ t ] a ,t b ]Time period of signal intensity over-frequency, [ t ] c ,t d ]A time period for network delay early warning;
during operation of the power communication network, the signal strength is typically within a signal strength range x min ~x max In the time period of stable signal transmission of the power communication network, when the signal intensity exceeds the maximum value x of the signal intensity range in real time occasionally max When the network bandwidth increases, the power communication speed is increased, and therefore, the real-time signal strength exceeds the maximum value x of the signal strength range max The time period of the power communication network is the time period of the signal intensity over-frequency, and the communication speed of the power communication network is accelerated in the time period;
in the running process of the power communication network, the larger the network delay is, the communication problem or network congestion can occur, so that the real-time bandwidth is reduced, the longer the duration that the network delay exceeds the delay threshold value is, the more likely the power communication network is abnormal, and therefore, the time period that the network delay exceeds the delay threshold value is the time period of network delay early warning;
in summary, the larger the network signal floating coefficient value obtained through the integral operation is, the more no abnormality exists in the power communication network.
The calculation expression of the device performance floating coefficient is as follows:wherein S (t) is the real-time variation of the load of the equipment, [ t ] e ,t f ]For the time period of early warning of the energy consumption of the equipment, [ t ] g ,t h ]A time period for device temperature pre-warning;
in the running process of the power communication network, the lower the energy consumption of the equipment is, the more normal the equipment is, so that the time period when the energy consumption of the equipment exceeds the energy consumption threshold is the time period of equipment energy consumption early warning, and in the time period, the load of the equipment is increased, and the equipment is easy to fail;
for normal load of the equipment, when the operating temperature of the equipment is higher, the operating load of the equipment is increased, so that the period when the temperature of the equipment exceeds the temperature threshold value is a period when the temperature of the equipment is early-warned, and during the period, the load of the equipment is increased, and the equipment is easy to break down.
The calculation expression of the communication state floating coefficient is:wherein T (T) is the real-time variation of communication flow, [ T ] i ,t j ]For the period of abnormal attack early warning, [ t ] k ,t l ]A time period of early warning is verified for communication;
in the running process of the power communication network, when the communication network is subjected to abnormal attack, the power communication network is more easy to be abnormal, so that the period of the abnormal attack duration exceeding the duration threshold is the period of abnormal attack early warning, the power communication network is easy to be abnormal in the period, and in the communication process, if verification errors occur frequently, the power communication network is possibly invaded, and the period of the verification errors exceeding the frequency threshold is the period of communication verification early warning, and the period indicates that the power communication network is possibly invaded abnormally.
To sum up, the anomaly coefficient yc x The smaller the value, the more likely an anomaly is present in the power communication network, and therefore, by the anomaly coefficient yc x The value is compared to an anomaly threshold value to distinguish whether an anomaly exists in the power communication network.
When the abnormal condition of the power communication is identified, the fault diagnosis model is used for carrying out deep diagnosis, and the abnormal property and the influence range are determined, specifically:
collecting detailed information related to the anomaly, including time, place, equipment involved, signal strength, data transmission conditions, etc., extracting relevant features from the anomaly information, which may include statistical features, frequency domain features, pattern recognition features, etc. of the time series data, selecting features to reduce redundant information and reduce computational complexity, inputting the anomaly information into a fault diagnosis model when a new anomaly occurs, the model outputting the nature and scope of influence of the anomaly, e.g., indicating possible fault causes, location of the anomaly equipment, influence of the anomaly on the communication system, etc., generating detailed diagnosis reports based on the output of the model, the reports may include information of the root cause of the anomaly, possible solutions, suggested maintenance operations, etc., feeding back actual diagnosis results to the system for constantly optimizing and updating the fault diagnosis model to improve its accuracy and adaptability.
According to the diagnosis result, a corresponding preventive maintenance plan is formulated, including periodic inspection, equipment maintenance, upgrading and the like, specifically:
carefully analyzing the output of the fault diagnosis model, knowing the nature and scope of influence of the abnormality, determining the cause of the abnormality, affecting the equipment and the root factors that may cause problems, classifying the abnormality, determining priority according to its severity and urgency, which helps to formulate a targeted maintenance plan, preferentially solving the abnormality that affects the system most, formulating a periodic equipment inspection and maintenance plan including inspection of equipment status, power supply, communication module, cooling system, etc., ensuring the normal operation of the equipment and maintaining its performance, formulating an upgrade plan for firmware and software running on the equipment, installing updated firmware and software versions in time to repair known vulnerabilities, improving system stability and performance, considering optimizing and expanding the power communication network according to the nature of the abnormality, which may include increasing bandwidth, optimizing network topology, enhancing signal coverage, etc., enhancing security measures of the system including updating rules, reinforcing access control, encrypting communication, etc., ensuring the power communication system from malicious attacks and unauthorized accesses;
Training activities are developed, the skill level of operation and maintenance personnel is improved, various abnormal conditions can be better handled, a knowledge sharing mechanism is established, information communication among teams is promoted, a monitoring mechanism is deployed, the state of an electric power communication system is monitored in real time, a feedback mechanism is established, problems found in actual operation are fed back to a preventive maintenance plan, the plan is continuously improved and optimized, a strategy for regularly backing up data is formulated, quick recovery can be ensured when system faults or data are lost, a recovery strategy is tested, effectiveness is ensured, performance monitoring tools are deployed, system performance is monitored in real time, a regular report is generated, the overall health condition of the system is evaluated, potential problems are found, corresponding preventive measures are adopted, the execution condition of the preventive maintenance plan is tracked, the plan is ensured to be implemented according to a preset time schedule, and the plan is adjusted according to the actual execution condition, so that the preventive maintenance effect is improved.
According to the fault diagnosis result, a corresponding control strategy is automatically executed on the power communication network, so that the self-healing capacity of the power communication network is improved, and the method specifically comprises the following steps:
analyzing the output of the fault diagnosis model, analyzing the diagnosis results, determining the nature of the abnormality, affecting the device, the possible root cause and the urgency of executing the corresponding control strategy, selecting the appropriate control strategy according to the fault diagnosis results, wherein the control strategy can comprise device restarting, network topology adjustment, signal strength optimization, fault device isolation and the like, generating a control signal for automatically executing the control strategy, which can involve communication with the device, the sensor or the actuator to trigger the corresponding operation, ensure that the operation for executing the control strategy has the appropriate authority and meets the safety and compliance requirements, and performing authority verification to prevent unauthorized operation;
Automatically executing the selected control strategy, such as restarting a specific device, adjusting network configuration, sending out a signal optimization instruction, and the like, ensuring that the executed operation is targeted to solve the detected abnormal situation, monitoring the execution result of the control strategy, ensuring that the operation is successfully completed, collecting relevant data in real time during the execution to further monitor and verify, periodically checking the system state after executing the control strategy, if a new abnormality or problem is found after executing, executing a rollback strategy, and returning the system state to the state before executing the control strategy.
The operation state, fault information and maintenance record of the power communication network are uploaded to a cloud record after a report is generated, and data support is provided for long-term optimization of the system by recording the operation condition of the system, specifically:
uploading the operation state, fault information and maintenance record data of the power communication network to a Cloud for storage, selecting storage services provided by a Cloud service provider (for example, AWS, azure, ***-Cloud and the like), ensuring the reliability and safety of the data, ensuring the format standardization of the data before uploading, so as to effectively store and analyze the data at the Cloud, adopting a unified data structure and standard fields for subsequent report generation and analysis, setting a plan for periodically uploading the data to ensure timely update of the Cloud data, selecting daily, weekly or monthly uploading once according to actual requirements, storing the uploaded data in a Cloud database or a data warehouse, performing good management, providing high expandability and flexibility for the Cloud storage, enabling the data Cloud to store for a long time and facilitating subsequent analysis, extracting information from the stored data, generating a report of the system operation state, the fault information and the maintenance record, and defining the format and content of the report, including the system operation state abstract, the fault, statistics, the maintenance record and other information, and ensuring the readability of the information;
Setting a plan for generating an automatic report, periodically generating the report and uploading the report to a cloud, uploading the generated report to the cloud through an automation script, a task scheduler or a tool of a cloud service provider, forming a report archive which can be accessed at any time, ensuring that the uploaded report is consistent with corresponding data, carrying out long-term analysis on system performance and running conditions by using the data uploaded to the cloud, identifying potential trends, problem patterns and optimization opportunities by analyzing historical data, setting a continuous monitoring mechanism to ensure the accuracy and timeliness of the report, receiving feedback of the system, continuously improving report content and generating mechanisms, and ensuring compliance and safety standards when uploading and storing the data so as to protect sensitive information and prevent data leakage.
The user-friendly interface is provided, so that operation and maintenance personnel can intuitively know the running state, fault information and maintenance record of the system, help the operation and maintenance personnel quickly know the system condition, and support the operation and maintenance personnel to make timely decisions, and the method specifically comprises the following steps:
creating an intuitive instrument panel, displaying key indexes and overall running states of a system, including information such as network bandwidth utilization rate, equipment on-line state, fault quantity, maintenance records and the like, displaying real-time data such as network flow, equipment state change, signal strength and the like in a clear manner, using a line graph, a bar graph and other visual means to help operation staff to better understand dynamic changes of the system, providing a list of fault information, displaying according to time sequence or priority, providing summary information such as fault type, influence range, occurrence time and the like for each fault, so that the operation staff can quickly know key information of the problem, creating a calendar view of maintenance records, identifying date and type of maintenance of the system, facilitating the operation staff to know past maintenance work and future planned maintenance activities, providing powerful searching and screening functions, enabling the operation staff to quickly find needed information according to conditions such as key words, time range, equipment type and the like, and being vital for large-scale system and history data management;
If the system relates to equipment with a plurality of geographic positions, the distribution and the state of the equipment are shown on a map, so that an operation and maintenance person can more intuitively know the geographic layout and possible regional problems of the system, the report generation and downloading functions are provided, the operation and maintenance person can customize report contents according to needs, the report can be saved or shared to other team members, the report can comprise detailed contents of system states, fault information and maintenance records, the notification and alarm management functions are integrated, important information such as system state change, fault occurrence and the like can be timely sent to the operation and maintenance person, the notification can be sent through an email, a short message or an instant messaging tool, user roles and authority management can be realized, users with different levels can be ensured to see and operate the information related to responsibilities of the user, the safety and privacy of the system can be guaranteed, operation and interface display contents can be customized, a user feedback mechanism is integrated, the operation and maintenance person can put forward improvement suggestions or report interface problems, and user feedback can be timely collected, and user feedback experience is continuously optimized.
According to the method and the device, whether the power communication has abnormal conditions or not is identified through the edge computing equipment, whether an alarm needs to be generated is judged, when the abnormal conditions exist in the power communication, through deep analysis of the fault diagnosis model, the specific property and the influence range of the problem are determined, so that accurate diagnosis is conducted, corresponding preventive maintenance plans are formulated according to monitoring and diagnosis results, including regular inspection, equipment maintenance, upgrading and the like, corresponding control strategies are automatically executed on the power communication network according to the fault diagnosis results, and the self-healing capacity of the power communication network is improved. The system can carry out problem diagnosis and preventive decision support on the occurrence of abnormality, effectively improves the management efficiency of the power communication network, has high decision accuracy, can enable the power communication network to recover to a normal state in time, and ensures the stable operation of the power communication network.
Example 2: the establishment of the fault diagnosis model comprises the following steps:
inputting a fault state matrix representing faults and fault labels corresponding to the fault state matrix representing faults into a CNN network in the form of vector pairs, extracting fault characteristics, outputting results through forward propagation, comparing the outputted results with real label vectors corresponding to the faults, calculating errors between the results and the real label vectors, and then adjusting and modifying model parameters by using a BP algorithm until the model meets the requirements, and storing the output of the model for later fault diagnosis, wherein the method comprises the following specific steps of:
firstly, inputting a fault state matrix obtained in a data processing stage into a CNN network, extracting feature graphs of different fault categories by convolution operation, extracting a plurality of features from different layers by a plurality of convolution kernels, and facilitating feature association between mining faults and alarms;
after the convolution layer obtains the fault feature map, in order to reduce the dimension of the feature map, the feature map is input to the pooling layer, and the pooling layer performs the maximum pooling operation, while only sampling part of the data of the feature map, the important feature of the fault is still reserved, the feature of the local relevance of the image is utilized, so that the pooling operation simplifies the representation of the feature;
After the convolution and pooling operations, the CNN network extracts feature graphs of different fault categories, namely, all fault state matrixes are converted into gray level pictures, but the feature graphs are obtained from local pixels of the fault state matrixes and cannot fully reflect fault category features, two neural networks are used for respectively training two types of labels of input samples, a 6-layer network model is constructed according to the number and classification requirements of the samples, the 6-layer network model comprises 2 convolution layers and 2 pooling layers which are alternately connected, then a full connection layer and a Softmax classification output layer, network parameters of all layers are set to be 0.01 by adopting a truncated normal distribution initialization method, the maximum iteration number n_epoch is set to be 35, the batch size of data is set to be 64, the loss is defined by adopting an integrated cross function provided by tensorf low, and the training is optimized by adopting an Adam algorithm optimizer;
the full-connection layer combines fault class feature graphs output by the pooling layer, then sends the fault class feature graphs into a softmax classifier to classify different fault classes, the convolution pooling layer extracts fault features, the obtained feature graphs are local information with class differentiation, and the full-connection layer is equivalent to weighting the features to obtain more comprehensive fault feature output of each fault;
And comparing the fault characteristic output with the true value, calculating an error between the fault characteristic output and the true value, if the CNN network is not converged, returning the error between the fault characteristic output and the true value to each layer of the network, correcting the weight of each layer of nodes by using a BP algorithm, and recalculating the error between the fault characteristic output and the true value until the CNN network is converged and then outputting the CNN network, thereby completing the establishment of a fault diagnosis model.
Comparing the fault characteristic output with a true value, calculating an error between the fault characteristic output and the true value, and judging whether the CNN network converges or not, wherein the method comprises the following steps of:
the test set is used to calculate the model's predicted value for the fault feature and compare the predicted value to the true value, a common measure of the calculated error includes mean square error (Mean Squared Error, MSE) or other error indicator suitable for the task, visualizing the predicted value to the true value, such as by making a scatter plot or error plot, which helps to intuitively understand the model's behavior on different samples, considering that the model has converged when the model's performance on the validation set is no longer significantly improved, which can be determined by observing the plateau of the loss function curve or fluctuations around a certain value.
The error between the fault characteristic output and the true value is returned to each layer of the network, the weight of each layer of nodes is corrected by using the BP algorithm, the error between the fault characteristic output and the true value is recalculated, and the CNN network is output after the CNN network is converged, wherein the method comprises the following steps:
The gradient of the loss function to the network parameters is calculated by an error back propagation algorithm, which involves calculating the partial derivative of each parameter to the loss, updating the weights and biases of the network to reduce the value of the loss function using the gradient descent or a variation thereof, by controlling the step size of the parameter update using a learning rate, and stopping the correction when a fixed number of iterations or the loss function converges to a sufficiently small value.
Referring to fig. 3, the fault state matrix acquisition includes the following steps:
all alarm information in the power communication network is collected to obtain an original alarm information database, the alarm information fields are subjected to standardized processing aiming at the characteristics of the original alarm information data and the purpose of fault diagnosis, and redundant alarm information is removed to obtain a target alarm information database. And synchronizing time and sites of the data of the target alarm information database in a time window mode, and extracting alarm transactions. And carrying out alarm transaction coding on the alarm information of the whole network according to the site as a unit to obtain a topological connection and a fault state matrix representing the whole network, and marking a label for the root fault for the fault state matrix.
The alarm data is collected from the power communication network, the alarm is an external representation of the fault on one hand, and on the other hand, some secondary and low-level alarms only reflect the running state of the network and do not represent that the network really has the fault;
Therefore, the alarm data has uncertainty, the original data is collected in the history alarm table of each professional network manager, and one piece of alarm information generally has a plurality of fields, such as fault type, fault level, alarm name, alarm source, positioning information, occurrence time, detection board, clearing state and confirmation state, and the like, and each field has multiple values, wherein the alarm level has urgent, important and minor scores to indicate the emergency degree of the alarm;
when a plurality of alarms occur, the alarms with high level are generally processed first, and the alarms with lower level are classified into safety, equipment, communication and environment, and under normal conditions, the safety and equipment alarms belong to important alarms, the alarm source designates the name of the network element generating the alarms, which is important information of fault location, the alarm name is the unique identification of the alarms, different alarm names correspond to different types of alarms, and are important information of fault type diagnosis.
In summary, the method for carrying out standardized processing on the alarm information field comprises the following steps:
selecting an alarm information field related to fault diagnosis, and performing deduplication on an original alarm information database;
And (3) carrying out standardized processing on alarm data of all manufacturer network management by taking defined field names and attribute values as alarm information standard formats, wherein the defined field names and the defined attribute values are shown in a table 1:
TABLE 1
Selecting a proper time window size, and synchronously processing the alarm information of each site at the moment of failure to form an alarm transaction;
according to analysis of original alarm data, incomplete synchronization between faults and alarms can be found, which is mainly caused by association relation of alarms and an alarm reporting mechanism, and generation time of some alarm information is very close, and the alarm information is very likely to be alarms caused by the same faults, so that the alarm information of each site needs to be synchronized to form alarm transactions, the alarm data is synchronously processed by using a method of a fixed-size time window, the size of the time window is represented by W, the size of the W can be regarded as the maximum time interval related to two alarm transactions, and the alarm information of the same time window belongs to one alarm transaction;
based on the fault and the alarm history data, it can be known that different alarms have different importance degrees on different fault decisions, such as emergency, the alarms with high level are more likely to be directly caused by the root fault, the influence degree of the alarm types on the fault diagnosis is different, the root cause alarm types of the root fault are generally safety alarms, communication alarms and equipment alarms, the environment alarms are generally derivative alarm types, based on the different alarm types, the different alarm types are weighted to represent the influence degree of the different alarm types on the fault diagnosis, but NOT all faults are such characteristics, such as the equipment board dislocation Shi Gen is a secondary alarm due to the bd_NOT_ INSTALLED level, but the faults without board dislocation are likely to be undetected, the difference of weights between the different alarms after quantization is small enough to indicate the importance of each alarm on the fault diagnosis, the application uses the history data to set the importance of each alarm for each fault decision with a normalized weight value, and calculate each alarm weight for final all fault diagnosis is expressed as:
Wherein qz A Represents the alarm weight, qz x The weight of the alarm on the x-th fault effect is represented, and x=1, 2, 3, y represents the type of fault, and y is a positive integer, s A Representing qz x And the number of the alarms is not equal to 0, and the alarms are ranked from large to small according to the alarm weight, and the higher the alarm weight is, the higher the priority of the alarms is.
Example 3: referring to fig. 2, in the system for diagnosing and preventing a power communication fault, real-time data including equipment status, signal intensity, data transmission conditions and the like are collected from a power communication network through an acquisition module, the collected data are sent to an edge calculation module, the edge calculation module performs rapid diagnosis and analysis, identifies whether the power communication has abnormal conditions and judges whether an alarm needs to be generated or not, the identification result is sent to a fault diagnosis module, when the power communication is identified as abnormal conditions, the fault diagnosis module performs deep analysis through a fault diagnosis model, determines specific properties and influence ranges of problems to perform accurate diagnosis, the fault diagnosis result is sent to a preventive maintenance module, an automatic control module and a report recording module, the preventive maintenance module formulates a corresponding preventive maintenance plan according to the fault diagnosis result, the preventive maintenance module comprises periodic inspection, equipment maintenance, cloud end upgrading and the like, the maintenance record is sent to a report recording module, the automatic control module automatically performs a corresponding control strategy on the power communication network according to the fault diagnosis result, improves self-capability of the power communication network, the power communication network operation state is sent to the report recording module, and the report recording module enables operation state of the power communication network, fault information and fault information to be generated by the fault diagnosis module, the fault maintenance module is sent to a preventive maintenance module, and the fault maintenance module is friendly to a cloud end, and the user can provide a user interface to a user to perform a visual operation system, and a user interface to perform a visual operation and a user to know and a user interface.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. A power communication fault diagnosis and prevention method is characterized in that: the prevention method comprises the following steps:
s1: the acquisition end collects real-time data from the power communication network and sends the collected real-time data to the edge computing equipment;
s2: the edge computing equipment analyzes the real-time data, identifies whether an abnormal condition exists in the power communication network and judges whether an alarm needs to be generated or not;
s3: when the abnormal condition of the power communication is identified, diagnosing the abnormality through a fault diagnosis model, and determining the nature and the influence range of the abnormality;
s4: the management end makes a corresponding preventive maintenance plan according to the diagnosis result, and automatically executes a corresponding control strategy on the power communication network according to the fault diagnosis result;
s5: uploading the operation state, fault information and maintenance record of the power communication network to a cloud record after generating a report;
s6: and providing a user interface to enable operation and maintenance personnel to know the operation state, fault information and maintenance record of the power communication network.
2. The power communication fault diagnosis and prevention method according to claim 1, characterized in that: in step S2, the edge computing device analyzes the real-time data, and identifies whether an abnormal condition exists in the power communication network and determines whether an alarm needs to be generated, including the following steps:
S201: acquiring network data, equipment data and safety data of an electric power communication network, wherein the network data comprises a network signal floating coefficient, the equipment data comprises an equipment performance floating coefficient, and the safety data comprises a communication state floating coefficient;
s202: the edge computing device establishes an abnormal coefficient yc after normalizing the network signal floating coefficient, the device performance floating coefficient and the communication state floating coefficient x ;
S203: if the anomaly coefficient yc x The method comprises the steps of identifying that an abnormal condition does not exist in the power communication network and generating no alarm when the power communication network is larger than or equal to an abnormal threshold value;
s204: if the anomaly coefficient yc x If the power communication network is smaller than the abnormality threshold, an abnormality is identified, and an alarm needs to be generated.
3. The power communication fault diagnosis and prevention method according to claim 2, characterized in that: the calculation expression of the network signal floating coefficient is as follows: wherein W) t) is the real-time change of the bandwidth of the network signal, [ t ] a ,t b ]Time period of signal intensity over-frequency, [ t ] c ,t d ]A time period for network delay early warning;
the calculation expression of the device performance floating coefficient is as follows:wherein S (t) is the real-time variation of the load of the equipment, [ t ] e ,t f ]For the time period of early warning of the energy consumption of the equipment, [ t ] g ,t h ]A time period for device temperature pre-warning;
The calculation expression of the communication state floating coefficient is as follows:wherein T (T) is the real-time variation of communication flow, [ T ] i ,t j ]For the period of abnormal attack early warning, [ t ] k ,t l ]For communication purposesAnd verifying the early warning time period.
4. A power communication failure diagnosis and prevention method according to claim 3, characterized in that: in step S3, the establishment of the fault diagnosis model includes the steps of:
s301: inputting the fault state matrix obtained in the data processing stage into a CNN network, and extracting different fault class feature diagrams by convolution operation;
s302: after the convolution layer obtains the fault feature map, the feature map is input to a pooling layer, and the pooling layer samples partial data of the feature map through the maximum pooling operation;
s303: after the rolling and pooling operation, the CNN network extracts feature graphs of different fault categories;
s304: the full-connection layer combines the fault class feature graphs output by the pooling layer, and then sends the fault class feature graphs into a softmax classifier to classify different fault class feature graphs to obtain fault feature output;
s305: comparing the fault characteristic output with a true value, calculating an error between the fault characteristic output and the true value, and if the CNN network has no convergence, returning the error between the fault characteristic output and the true value to each layer of the network;
S306: and correcting the weight of each layer of nodes by using a BP algorithm, and recalculating the error between the fault characteristic output and the true value until the CNN network is converged and then outputting the CNN network, thereby completing the establishment of a fault diagnosis model.
5. The power communication fault diagnosis and prevention method according to claim 4, wherein: in step S301, the failure state matrix acquisition includes the steps of:
s3011: collecting all alarm information in the power communication network to obtain an original alarm information database;
s3012: based on the characteristics of the original alarm information data and the fault diagnosis purpose, carrying out standardized processing on the alarm information fields to obtain a target alarm information database;
s3013: the method comprises the steps of synchronously extracting alarm transactions from time and sites by adopting a time window mode for data of a target alarm information database;
s3014: and carrying out alarm transaction coding on alarm information of the power communication network according to the site unit to obtain a topological connection and a fault state matrix representing the whole network, and finally marking a label for the fault state matrix with a root fault.
6. The power communication fault diagnosis and prevention method according to claim 5, characterized in that: in step S3012, the normalization processing of the alert information field includes the following steps:
S30121: selecting an alarm information field related to fault diagnosis, and performing deduplication on an original alarm information database;
s30122: the defined field name and attribute value are used as the standard format of the alarm information to carry out standardized processing on the alarm data of the webmaster of all manufacturers
S30123: the alarm information of each site at the moment of failure is synchronously processed by a time window size method to form an alarm transaction;
s30124: the importance of each alarm for each fault judgment is set by using the historical data, the alarm weight of each alarm for final fault diagnosis is calculated, all alarm types are ordered according to the alarm weight from large to small, and the higher the alarm weight is, the higher the alarm priority is.
7. The power communication fault diagnosis and prevention method according to claim 6, characterized in that: the calculation expression of the alarm weight is as follows:wherein qz A Represents the alarm weight, qz x The weight of the alarm on the x-th fault effect is represented, and x=1, 2, 3, y represents the type of fault, and y is a positive integer, s A Representing qz x A number not equal to 0.
8. The power communication fault diagnosis and prevention method according to claim 7, characterized in that: in step S3, when it is recognized that the power communication has an abnormal condition, diagnosis is performed by the fault diagnosis model, and determining the abnormal property and the influence range includes the steps of:
S307: collecting detailed information related to the abnormality, and extracting related features from the abnormality information;
s308: when an abnormal situation occurs, inputting abnormal information into a fault diagnosis model, and outputting the nature and the influence range of the abnormality by the fault diagnosis model;
s309: based on the output of the fault diagnosis model, a diagnosis report is generated, the report including the cause of the abnormality, the solution, the maintenance operation.
9. The power communication fault diagnosis and prevention method according to claim 8, characterized in that: in step S4, the management end makes a corresponding preventive maintenance plan according to the diagnosis result, and automatically executes a corresponding control strategy for the power communication network according to the fault diagnosis result, including the following steps:
s401: analyzing the output of the fault diagnosis model, and knowing the nature and influence range of the abnormality;
s402: classifying the abnormality, and determining priority according to the severity of the abnormality and the urgency;
s403: making a periodic equipment inspection and maintenance plan, including inspection of equipment states, power supplies, communication modules and heat dissipation systems;
s404: making an upgrade plan for firmware and software running on the equipment, installing updated firmware and software versions in time and repairing known vulnerabilities;
S405: selecting a control strategy according to the fault diagnosis result, wherein the control strategy comprises equipment restarting, network topology adjustment, signal strength optimization and fault equipment isolation;
s406: generating a control signal for automatically executing the control strategy, and automatically executing the selected control strategy, wherein the control strategy comprises restarting equipment, adjusting network configuration and sending out a signal optimization instruction.
10. A power communication failure diagnosis and prevention system for implementing the prevention method according to any one of claims 1 to 9, characterized in that: the system comprises an acquisition module, an edge calculation module, a fault diagnosis module, a preventive maintenance module, an automatic control module, a report recording module and a user interface module;
and the acquisition module is used for: collecting real-time data from the power communication network;
and an edge calculation module: analyzing the real-time data, identifying whether the power communication has abnormal conditions and judging whether an alarm needs to be generated;
and a fault diagnosis module: when the abnormal condition of the power communication is identified, diagnosing through a fault diagnosis model, and determining the abnormal property and the influence range;
and a preventive maintenance module: according to the fault diagnosis result, a corresponding preventive maintenance plan is formulated;
And the automatic control module is used for: automatically executing a corresponding control strategy on the power communication network according to the fault diagnosis result;
report recording module: uploading the operation state, fault information and maintenance record of the power communication network to a cloud record after generating a report;
a user interface module: and providing a user interface to enable operation and maintenance personnel to know the operation state, fault information and maintenance record of the power communication network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311795325.9A CN117675522A (en) | 2023-12-25 | 2023-12-25 | Power communication fault diagnosis and prevention method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311795325.9A CN117675522A (en) | 2023-12-25 | 2023-12-25 | Power communication fault diagnosis and prevention method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117675522A true CN117675522A (en) | 2024-03-08 |
Family
ID=90068153
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311795325.9A Pending CN117675522A (en) | 2023-12-25 | 2023-12-25 | Power communication fault diagnosis and prevention method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117675522A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118054845A (en) * | 2024-04-16 | 2024-05-17 | 微网优联科技(成都)有限公司 | Distributed optical network terminal fault monitoring method and system |
CN118091406A (en) * | 2024-04-19 | 2024-05-28 | 楷维工业服务(上海)有限公司 | Motor detection and repair method and device, electronic equipment and storage medium |
CN118096131A (en) * | 2024-04-23 | 2024-05-28 | 青岛华林电力有限公司 | Operation and maintenance inspection method based on electric power scene model |
-
2023
- 2023-12-25 CN CN202311795325.9A patent/CN117675522A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118054845A (en) * | 2024-04-16 | 2024-05-17 | 微网优联科技(成都)有限公司 | Distributed optical network terminal fault monitoring method and system |
CN118091406A (en) * | 2024-04-19 | 2024-05-28 | 楷维工业服务(上海)有限公司 | Motor detection and repair method and device, electronic equipment and storage medium |
CN118096131A (en) * | 2024-04-23 | 2024-05-28 | 青岛华林电力有限公司 | Operation and maintenance inspection method based on electric power scene model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111555716B (en) | Method, device, equipment and storage medium for determining working state of photovoltaic array | |
CN109146093B (en) | Power equipment field investigation method based on learning | |
CN117675522A (en) | Power communication fault diagnosis and prevention method and system | |
WO2020143327A1 (en) | Big data-based computer room inspection method and related device | |
US10996160B2 (en) | Mitigating asset damage via asset data analysis and processing | |
RU2626780C1 (en) | Method and system of remote monitoring energy installations | |
WO2021027728A1 (en) | Rail transit operation and maintenance method, device, system and apparatus, and medium | |
RU2649542C1 (en) | Method and system of remote monitoring of objects | |
CN108170566A (en) | Product failure information processing method, system, equipment and collaboration platform | |
US20210232104A1 (en) | Method and system for identifying and forecasting the development of faults in equipment | |
CN116308304B (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
US20180366979A1 (en) | Defect detection in power distribution system | |
CN115329812A (en) | Road infrastructure abnormity monitoring method based on artificial intelligence | |
CN110879151B (en) | Gas turbine remote monitoring and diagnosis system and method based on operation big data | |
CN113468022B (en) | Automatic operation and maintenance method for centralized monitoring of products | |
CN117423201A (en) | Intelligent fire-fighting state monitoring method and system for restaurant | |
US11665193B2 (en) | Method for managing plant, plant design device, and plant management device | |
JP7499168B2 (en) | Cause estimation system and cause estimation method | |
CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
KR102504121B1 (en) | Apparatus and method for solar power system operation and maintenance based on location using qr code | |
Li et al. | Health Monitoring Framework for Weather Radar Based on Long Short‐Term Memory Network with a Real Case Study | |
CN117955245B (en) | Method and device for determining running state of power grid, storage medium and electronic equipment | |
Black et al. | Operational Technology Behavioral Analytics (OTBA)(Final Technical Report DE-FE0031640) | |
CN116934302A (en) | Management method and system for shared operation and maintenance of distributed photovoltaic power station | |
Black et al. | OPERATIONAL TECHNOLOGY BEHAVIORAL ANALYTICS (OTBA)–A DATA-CENTRIC APPROACH FOR REDUCING CYBERSECURITY RISK |
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 |