CN117150415B - Communication equipment state monitoring method and system based on artificial intelligence - Google Patents
Communication equipment state monitoring method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117150415B CN117150415B CN202311389176.6A CN202311389176A CN117150415B CN 117150415 B CN117150415 B CN 117150415B CN 202311389176 A CN202311389176 A CN 202311389176A CN 117150415 B CN117150415 B CN 117150415B
- Authority
- CN
- China
- Prior art keywords
- communication equipment
- equipment
- lstm
- communication
- state data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 385
- 238000012544 monitoring process Methods 0.000 title claims abstract description 149
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title abstract description 23
- 238000012423 maintenance Methods 0.000 claims abstract description 45
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 230000007787 long-term memory Effects 0.000 claims abstract description 12
- 238000005457 optimization Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 21
- 230000004913 activation Effects 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000032683 aging Effects 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 5
- 210000002569 neuron Anatomy 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 230000008033 biological extinction Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Signal Processing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Maintenance And Management Of Digital Transmission (AREA)
Abstract
The invention relates to the field of artificial intelligence, in particular to a communication equipment state monitoring method and system based on artificial intelligence. Establishing a state monitoring network model of the target BO-LSTM communication equipment through the LSTM long-term memory neural network; acquiring equipment real-time state data in the communication equipment, inputting the equipment real-time state data into a state monitoring network model of the target BO-LSTM communication equipment for identification, and obtaining the communication equipment real-time state data; judging real-time state data of the communication equipment, if judging that the communication equipment has serious faults and general faults, generating equipment fault maintenance measures according to the real-time state data of the communication equipment, sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server; if the communication equipment is judged to be slightly faulty, the slight fault factor of the equipment is acquired according to the real-time state data of the communication equipment. The fault inquiry and state monitoring of the communication equipment can be improved, and the communication efficiency of the communication equipment is improved.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a communication equipment state monitoring method and system based on artificial intelligence.
Background
The communication equipment is wire communication equipment and wireless communication equipment suitable for industrial control environment, the wire communication equipment mainly introduces the conversion equipment for solving serial port communication, professional bus type communication, industrial Ethernet communication and various communication protocols of industrial sites, and the wireless communication equipment mainly comprises equipment such as wireless AP, wireless network bridge, wireless network card, wireless lightning arrester, antenna and the like, however, when the communication equipment breaks down, a fault detection device of the communication equipment is needed to detect the fault position of the communication equipment during maintenance. In addition, the current fault state monitoring of the communication equipment generally adopts a manual inspection mode to perform fault inquiry, and the inspection efficiency is low, and time and labor are wasted. How to use artificial intelligence to improve the communication state monitoring efficiency of communication equipment is a technical problem to be solved in the current stage.
Disclosure of Invention
The invention aims to solve the problems and designs a communication equipment state monitoring method and system based on artificial intelligence.
The technical scheme of the invention for achieving the purpose is that in the communication equipment state monitoring method based on artificial intelligence, the communication equipment state monitoring method comprises the following steps:
acquiring equipment history state data in communication equipment, and performing data preprocessing on the equipment history state data to obtain equipment history state data to be trained;
establishing an LSTM communication equipment state monitoring network model through an LSTM long-term memory neural network, and optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm to obtain an initial BO-LSTM communication equipment state monitoring network model;
inputting the historical state data of the equipment to be trained into the initial BO-LSTM communication equipment state monitoring network model for training to obtain a target BO-LSTM communication equipment state monitoring network model;
acquiring equipment real-time state data in communication equipment, and inputting the equipment real-time state data into a state monitoring network model of target BO-LSTM communication equipment for identification to obtain the communication equipment real-time state data;
judging the real-time state data of the communication equipment, if judging that the communication equipment has serious faults and the communication equipment has general faults, generating equipment fault maintenance measures according to the real-time state data of the communication equipment, sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server;
if the communication equipment is judged to be slightly faulty, the slight fault factor of the equipment is obtained according to the real-time state data of the communication equipment, the communication equipment is monitored according to the slight fault factor of the equipment, and if the slight fault factor of the equipment continues to expand, the server is warned.
Further, in the above communication equipment state monitoring method, the acquiring equipment history state data in the communication equipment, performing data preprocessing on the equipment history state data to obtain equipment history state data to be trained, includes:
acquiring equipment history state data in communication equipment, wherein the equipment history state data at least comprises a communication equipment program state, a communication equipment connecting wire state, a communication equipment component state, a communication equipment power indicator state and a communication equipment serial port state;
deleting the missing value data in the historical state data of the equipment to obtain the historical state data of the complete equipment;
and normalizing the complete equipment historical state data to obtain the equipment historical state data to be trained.
Further, in the above method for monitoring a status of a communication device, the step of establishing a LSTM communication device status monitoring network model through an LSTM long-term memory neural network, and optimizing the LSTM communication device status monitoring network model by using a bayesian optimization algorithm to obtain an initial BO-LSTM communication device status monitoring network model includes:
establishing an LSTM communication equipment state monitoring network model through an LSTM long-term memory neural network, wherein the LSTM communication equipment state monitoring network model at least comprises an input layer, an LSTM hidden layer, a Dropout layer and an output layer;
optimizing a Bayesian algorithm by using a Bayesian optimization library to obtain a Bayesian optimization algorithm;
optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm;
the input layer is used for acquiring equipment state data and transmitting the equipment state data to the LSTM hidden layer;
adding a Dropout layer between LSTM hidden layers of the LSTM communication equipment state monitoring network model;
and the LSTM hidden layer is used for carrying out data analysis and learning on the equipment state data to obtain an initial BO-LSTM communication equipment state monitoring network model.
Further, in the above method for monitoring a status of a communication device, the step of inputting the historical status data of the device to be trained into the initial BO-LSTM communication device status monitoring network model to perform training, to obtain a target BO-LSTM communication device status monitoring network model, includes:
inputting the historical state data of the equipment to be trained into the initial BO-LSTM communication equipment state monitoring network model for training;
setting the LSTM hidden layer number in the initial BO-LSTM communication equipment state monitoring network model to be 2;
setting an optimizer for the state monitoring network model of the initial BO-LSTM communication equipment by using an Adam algorithm;
setting the learning rate and the neuron number of the initial BO-LSTM communication equipment state monitoring network model based on a Bayesian optimization algorithm;
setting a tanh hyperbolic tangent activation function as an activation function of the initial BO-LSTM communication equipment state monitoring network model;
and setting the MSE loss function as the loss function of the initial BO-LSTM communication equipment state monitoring network model, and setting the iteration times to 100 times to obtain the target BO-LSTM communication equipment state monitoring network model.
Further, in the above method for monitoring a status of a communication device, the acquiring real-time status data of the device in the communication device, inputting the real-time status data of the device into a status monitoring network model of a target BO-LSTM communication device for identification, and obtaining the real-time status data of the communication device includes:
the real-time state data of the communication equipment at least comprises severe faults of the communication equipment, general faults of the communication equipment and slight faults of the communication equipment;
the serious faults of the communication equipment at least comprise breakage of connecting wires of the communication equipment, faults of components of the communication equipment, extinction of power supply indication lamps of the communication equipment and disconnection of serial ports of the communication equipment;
the general faults of the communication equipment at least comprise program faults of the communication equipment system and power faults of the communication equipment;
the slight fault of the communication equipment at least comprises ageing of components of the communication equipment, signal shielding of the communication equipment and fault of connecting wires of the communication equipment.
Further, in the above method for monitoring a status of a communication device, the determining the real-time status data of the communication device, if determining that the communication device has a serious fault and the communication device has a general fault, generating a device fault maintenance measure according to the real-time status data of the communication device, and sending the device fault maintenance measure to a server, and meanwhile, performing early warning on the server, including:
judging the real-time state data of the communication equipment, and if the real-time state data is judged to be serious faults of the communication equipment and general faults of the communication equipment;
acquiring equipment historical maintenance data of severe faults of communication equipment and general faults of the communication equipment, and clustering the equipment historical maintenance data by using a mean shift clustering algorithm to obtain an equipment maintenance measure database;
generating equipment fault maintenance measures according to severe faults of the communication equipment and general faults of the communication equipment based on the equipment maintenance measure database;
and sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server.
Further, in the above method for monitoring a status of a communication device, if the communication device is determined to be slightly faulty, a device slight fault factor is obtained according to the real-time status data of the communication device, the communication device is monitored according to the device slight fault factor, and if the device slight fault factor continues to expand, a server is pre-warned, including:
if the communication equipment is judged to be slightly faulty, acquiring a slight fault factor of the equipment according to the real-time state data of the communication equipment;
the slight fault factors of the equipment at least comprise temperature and humidity for accelerating the aging of components of the communication equipment, objects for increasing the signal shielding of the communication equipment and objects for increasing the fault of connecting wires of the communication equipment;
monitoring communication equipment components, communication equipment signal shields and communication equipment connecting wires according to the slight fault factors of the equipment;
if the communication equipment component reaches the set use duration, the server is pre-warned; if the signal shielding object of the communication equipment has an increasing trend, the server is pre-warned; if the connecting wire of the communication equipment is broken, the server is pre-warned.
The technical scheme of the invention for achieving the purpose is that in the communication equipment state monitoring system based on deep learning, the communication equipment state monitoring system comprises:
the data acquisition module is used for acquiring equipment history state data in the communication equipment, and carrying out data preprocessing on the equipment history state data to obtain the equipment history state data to be trained;
the model building module is used for building an LSTM communication equipment state monitoring network model through an LSTM long-term memory neural network, and optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm to obtain an initial BO-LSTM communication equipment state monitoring network model;
the model training module is used for inputting the historical state data of the equipment to be trained into the initial BO-LSTM communication equipment state monitoring network model for training to obtain a target BO-LSTM communication equipment state monitoring network model;
the state identification module is used for acquiring equipment real-time state data in the communication equipment, inputting the equipment real-time state data into a state monitoring network model of the target BO-LSTM communication equipment for identification, and obtaining the communication equipment real-time state data;
the state judging module is used for judging the real-time state data of the communication equipment, generating equipment fault maintenance measures according to the real-time state data of the communication equipment if the real-time state data of the communication equipment is judged to be serious faults and general faults, sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server;
and the state monitoring module is used for acquiring the equipment slight fault factor according to the real-time state data of the communication equipment if the communication equipment is judged to be slightly faulty, monitoring the communication equipment according to the equipment slight fault factor, and carrying out early warning on the server if the equipment slight fault factor is continuously expanded.
Further, in the communication equipment state monitoring system based on deep learning, the data acquisition module includes the following submodules:
the device comprises an acquisition submodule, a communication device management submodule and a communication device management submodule, wherein the acquisition submodule is used for acquiring device history state data in communication devices, and the device history state data at least comprise a program state of the communication devices, a connecting line state of the communication devices, a component state of the communication devices, a power indicator state of the communication devices and a serial port state of the communication devices;
the deleting sub-module is used for deleting the missing value data in the equipment history state data to obtain complete equipment history state data;
and the normalization sub-module is used for carrying out normalization processing on the complete equipment historical state data to obtain the equipment historical state data to be trained.
Further, in the communication equipment state monitoring system based on deep learning, the model training module includes the following submodules:
the training sub-module is used for inputting the historical state data of the equipment to be trained into the initial BO-LSTM communication equipment state monitoring network model for training;
the hidden layer sub-module is used for setting the LSTM hidden layer number in the initial BO-LSTM communication equipment state monitoring network model to be 2;
the optimizer submodule is used for setting an optimizer of the initial BO-LSTM communication equipment state monitoring network model by utilizing an Adam algorithm;
the optimization algorithm sub-module is used for setting the learning rate and the neuron number of the initial BO-LSTM communication equipment state monitoring network model based on a Bayesian optimization algorithm;
an activation function sub-module, configured to set a tanh hyperbolic tangent activation function as an activation function of the initial BO-LSTM communications device state monitoring network model;
and the obtaining submodule is used for setting the MSE loss function as the loss function of the initial BO-LSTM communication equipment state monitoring network model, and setting the iteration times to 100 times to obtain the target BO-LSTM communication equipment state monitoring network model.
The method has the advantages that the historical state data of the equipment in the communication equipment is obtained, and the historical state data of the equipment is subjected to data preprocessing to obtain the historical state data of the equipment to be trained; establishing an LSTM communication equipment state monitoring network model through an LSTM long-term memory neural network, and optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm to obtain an initial BO-LSTM communication equipment state monitoring network model; inputting the historical state data of the equipment to be trained into the initial BO-LSTM communication equipment state monitoring network model for training to obtain a target BO-LSTM communication equipment state monitoring network model; acquiring equipment real-time state data in communication equipment, and inputting the equipment real-time state data into a state monitoring network model of target BO-LSTM communication equipment for identification to obtain the communication equipment real-time state data; judging the real-time state data of the communication equipment, if judging that the communication equipment has serious faults and the communication equipment has general faults, generating equipment fault maintenance measures according to the real-time state data of the communication equipment, sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server; if the communication equipment is judged to be slightly faulty, the slight fault factor of the equipment is obtained according to the real-time state data of the communication equipment, the communication equipment is monitored according to the slight fault factor of the equipment, and if the slight fault factor of the equipment continues to expand, the server is warned. The state of the communication equipment can be monitored anytime and anywhere, the fault state of the communication equipment is automatically identified, monitoring measures are made according to the fault severity of the communication equipment in a grading manner, a large amount of manpower and material resources are saved, the fault inquiry and state monitoring of the communication equipment are facilitated, and the communication efficiency of the communication equipment is improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.
FIG. 1 is a schematic diagram of a first embodiment of a communication device status monitoring method based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a second embodiment of a communication device status monitoring method based on artificial intelligence according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a third embodiment of a communication device status monitoring method based on artificial intelligence according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a first embodiment of a state monitoring system for a communication device based on deep learning according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The invention is specifically described below with reference to the accompanying drawings, as shown in fig. 1, a communication device state monitoring method based on artificial intelligence, the communication device state monitoring method includes the following steps:
step 101, acquiring equipment history state data in communication equipment, and performing data preprocessing on the equipment history state data to obtain the equipment history state data to be trained;
specifically, in this embodiment, device history state data in the communication device is obtained, where the device history state data includes at least a program state of the communication device, a connection line state of the communication device, a component state of the communication device, a power indicator state of the communication device, and a serial port state of the communication device; deleting the missing value data in the historical state data of the equipment to obtain the historical state data of the complete equipment; and normalizing the complete equipment historical state data to obtain the equipment historical state data to be trained.
Step 102, establishing an LSTM communication equipment state monitoring network model through an LSTM long-term memory neural network, and optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm to obtain an initial BO-LSTM communication equipment state monitoring network model;
specifically, in this embodiment, an LSTM long-term memory neural network is used to establish an LSTM communication device state monitoring network model, where the LSTM communication device state monitoring network model at least includes an input layer, an LSTM hidden layer, a Dropout layer, and an output layer; optimizing a Bayesian algorithm by using a Bayesian optimization library to obtain a Bayesian optimization algorithm; optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm; the input layer is used for acquiring equipment state data and transmitting the equipment state data to the LSTM hidden layer; adding a Dropout layer between LSTM hidden layers of the LSTM communication equipment state monitoring network model; the LSTM hidden layer is used for carrying out data analysis and learning on the equipment state data to obtain an initial BO-LSTM communication equipment state monitoring network model.
Step 103, inputting historical state data of the equipment to be trained into an initial BO-LSTM communication equipment state monitoring network model for training to obtain a target BO-LSTM communication equipment state monitoring network model;
specifically, in this embodiment, historical state data of the equipment to be trained is input into an initial BO-LSTM communication equipment state monitoring network model to perform training; setting the LSTM hidden layer number in the initial BO-LSTM communication equipment state monitoring network model to be 2; setting an optimizer of an initial BO-LSTM communication equipment state monitoring network model by using an Adam algorithm; setting the learning rate and the neuron number of an initial BO-LSTM communication equipment state monitoring network model based on a Bayesian optimization algorithm; setting a tanh hyperbolic tangent activation function as an activation function of an initial BO-LSTM communication equipment state monitoring network model; and setting the MSE loss function as the loss function of the initial BO-LSTM communication equipment state monitoring network model, and setting the iteration number to 100 times to obtain the target BO-LSTM communication equipment state monitoring network model.
104, acquiring equipment real-time state data in the communication equipment, and inputting the equipment real-time state data into a state monitoring network model of the target BO-LSTM communication equipment for identification to obtain the communication equipment real-time state data;
specifically, the real-time status data of the communication device in this embodiment at least includes a serious fault of the communication device, a general fault of the communication device, and a slight fault of the communication device; the serious fault of the communication equipment at least comprises the breakage of a connecting wire of the communication equipment, the fault of components of the communication equipment, the extinction of a power indicator lamp of the communication equipment and the disconnection of a serial port of the communication equipment; the general faults of the communication equipment at least comprise program faults of the communication equipment system and power faults of the communication equipment; the slight fault of the communication equipment at least comprises ageing of components of the communication equipment, signal shielding of the communication equipment and fault of connecting wires of the communication equipment.
Step 105, judging real-time state data of the communication equipment, if judging that the communication equipment has serious faults and general faults, generating equipment fault maintenance measures according to the real-time state data of the communication equipment, sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server;
specifically, in this embodiment, the real-time status data of the communication device is determined, and if it is determined that the communication device has serious faults and the communication device has general faults; acquiring equipment historical maintenance data of severe faults of communication equipment and general faults of the communication equipment, and clustering the equipment historical maintenance data by using a mean shift clustering algorithm to obtain an equipment maintenance measure database; generating equipment fault maintenance measures according to severe faults of the communication equipment and general faults of the communication equipment based on an equipment maintenance measure database; and sending the equipment fault maintenance measures to the server, and simultaneously carrying out early warning on the server.
And 106, if the communication equipment is judged to be slightly faulty, acquiring a slight fault factor of the equipment according to the real-time state data of the communication equipment, monitoring the communication equipment according to the slight fault factor of the equipment, and if the slight fault factor of the equipment continues to expand, early warning the server.
Specifically, in this embodiment, if it is determined that the communication device is slightly faulty, a slight fault factor of the device is obtained according to the real-time status data of the communication device; the slight fault factors of the equipment at least comprise temperature and humidity for accelerating the ageing of components of the communication equipment, objects for increasing the signal shielding of the communication equipment and objects for increasing the fault of connecting lines of the communication equipment; monitoring communication equipment components, communication equipment signal shields and communication equipment connecting wires according to equipment slight fault factors; if the communication equipment component reaches the set use duration, the server is pre-warned; if the signal shielding object of the communication equipment has an increasing trend, the server is pre-warned; if the connecting wire of the communication equipment is broken, the server is pre-warned.
The communication equipment state monitoring also comprises the step of identifying the indicator lights and components in the communication equipment by utilizing the image acquisition and processing identification device; the device also comprises a temperature sensor, a humidity sensor and a gas sensor for collecting components and connecting wire states in the communication equipment.
The method has the advantages that the historical state data of the equipment to be trained is obtained by acquiring the historical state data of the equipment in the communication equipment and carrying out data preprocessing on the historical state data of the equipment; establishing an LSTM communication equipment state monitoring network model through an LSTM long-term memory neural network, and optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm to obtain an initial BO-LSTM communication equipment state monitoring network model; inputting historical state data of equipment to be trained into an initial BO-LSTM communication equipment state monitoring network model for training to obtain a target BO-LSTM communication equipment state monitoring network model; acquiring equipment real-time state data in the communication equipment, inputting the equipment real-time state data into a state monitoring network model of the target BO-LSTM communication equipment for identification, and obtaining the communication equipment real-time state data; judging real-time state data of the communication equipment, if judging that the communication equipment has serious faults and general faults, generating equipment fault maintenance measures according to the real-time state data of the communication equipment, sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server; if the communication equipment is judged to be slightly faulty, the slight fault factor of the equipment is obtained according to the real-time state data of the communication equipment, the communication equipment is monitored according to the slight fault factor of the equipment, and if the slight fault factor of the equipment is continuously expanded, the server is warned. The state of the communication equipment can be monitored anytime and anywhere, the fault state of the communication equipment is automatically identified, monitoring measures are made according to the fault severity of the communication equipment in a grading manner, a large amount of manpower and material resources are saved, the fault inquiry and state monitoring of the communication equipment are facilitated, and the communication efficiency of the communication equipment is improved.
In this embodiment, referring to fig. 2, in a second embodiment of a communication device status monitoring method based on artificial intelligence in the present invention, the step of inputting historical status data of a device to be trained into an initial BO-LSTM communication device status monitoring network model for training to obtain a target BO-LSTM communication device status monitoring network model includes the following steps:
step 201, inputting historical state data of equipment to be trained into an initial BO-LSTM communication equipment state monitoring network model for training;
step 202, setting the LSTM hidden layer number in the initial BO-LSTM communication equipment state monitoring network model to be 2;
step 203, setting an optimizer of an initial BO-LSTM communication equipment state monitoring network model by using an Adam algorithm;
step 204, setting the learning rate and the neuron number of an initial BO-LSTM communication equipment state monitoring network model based on a Bayesian optimization algorithm;
step 205, setting a tanh hyperbolic tangent activation function as an activation function of an initial BO-LSTM communication equipment state monitoring network model;
and 206, setting the MSE loss function as the loss function of the initial BO-LSTM communication equipment state monitoring network model, and setting the iteration times to 100 times to obtain the target BO-LSTM communication equipment state monitoring network model.
In this embodiment, referring to fig. 3, in a third embodiment of a communication device status monitoring method based on artificial intelligence in the present invention, real-time status data of a communication device is determined, if it is determined that the communication device has serious faults and general faults, device fault maintenance measures are generated according to the real-time status data of the communication device, and the device fault maintenance measures are sent to a server, and at the same time, early warning is performed on the server, including the following steps:
step 301, judging real-time status data of the communication equipment, if judging that the communication equipment has serious faults and general faults;
step 302, acquiring equipment historical maintenance data of severe faults of the communication equipment and general faults of the communication equipment, and clustering the equipment historical maintenance data by using a mean shift clustering algorithm to obtain an equipment maintenance measure database;
step 303, generating equipment fault maintenance measures according to severe faults of the communication equipment and general faults of the communication equipment based on an equipment maintenance measure database;
and 304, sending the equipment fault maintenance measures to the server, and simultaneously carrying out early warning on the server.
The foregoing describes a communication device state monitoring method based on artificial intelligence according to an embodiment of the present invention, and the following describes a communication device state monitoring system based on deep learning according to an embodiment of the present invention, referring to fig. 4, where an embodiment of the communication device state monitoring system in the embodiment of the present invention includes:
the data acquisition module is used for acquiring equipment history state data in the communication equipment, and carrying out data preprocessing on the equipment history state data to obtain the equipment history state data to be trained;
the model building module is used for building an LSTM communication equipment state monitoring network model through the LSTM long-term memory neural network, and optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm to obtain an initial BO-LSTM communication equipment state monitoring network model;
the model training module is used for inputting historical state data of the equipment to be trained into an initial BO-LSTM communication equipment state monitoring network model for training to obtain a target BO-LSTM communication equipment state monitoring network model;
the state identification module is used for acquiring equipment real-time state data in the communication equipment, inputting the equipment real-time state data into a state monitoring network model of the target BO-LSTM communication equipment for identification, and obtaining the communication equipment real-time state data;
the state judging module is used for judging the real-time state data of the communication equipment, generating equipment fault maintenance measures according to the real-time state data of the communication equipment if the real-time state data of the communication equipment is judged to be serious faults and general faults, sending the equipment fault maintenance measures to the server, and simultaneously carrying out early warning on the server;
and the state monitoring module is used for acquiring the equipment slight fault factor according to the real-time state data of the communication equipment if the communication equipment is judged to be slightly faulty, monitoring the communication equipment according to the equipment slight fault factor, and carrying out early warning on the server if the equipment slight fault factor is continuously expanded.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (1)
1. Communication equipment state monitoring system based on artificial intelligence, characterized by, communication equipment state monitoring system includes following module:
the data acquisition module is used for acquiring equipment history state data in the communication equipment, and carrying out data preprocessing on the equipment history state data to obtain the equipment history state data to be trained;
the model building module is used for building an LSTM communication equipment state monitoring network model through an LSTM long-term memory neural network, optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm to obtain an initial BO-LSTM communication equipment state monitoring network model, wherein the LSTM communication equipment state monitoring network model is built through the LSTM long-term memory neural network and at least comprises an input layer, an LSTM hidden layer, a Dropout layer and an output layer; optimizing a Bayesian algorithm by using a Bayesian optimization library to obtain a Bayesian optimization algorithm; optimizing the LSTM communication equipment state monitoring network model by using a Bayesian optimization algorithm; the input layer is used for acquiring equipment state data and transmitting the equipment state data to the LSTM hidden layer; adding a Dropout layer between LSTM hidden layers of the LSTM communication equipment state monitoring network model; the LSTM hidden layer is used for carrying out data analysis and learning on the equipment state data to obtain an initial BO-LSTM communication equipment state monitoring network model;
the model training module is used for inputting the historical state data of the equipment to be trained into the initial BO-LSTM communication equipment state monitoring network model for training to obtain a target BO-LSTM communication equipment state monitoring network model;
the state identification module is used for acquiring equipment real-time state data in the communication equipment, inputting the equipment real-time state data into a target BO-LSTM communication equipment state monitoring network model for identification, and obtaining the communication equipment real-time state data, wherein the communication equipment real-time state data comprises serious faults of the communication equipment, general faults of the communication equipment and slight faults of the communication equipment; the serious faults of the communication equipment comprise breakage of a connecting wire of the communication equipment, faults of components of the communication equipment, extinction of a power indicator lamp of the communication equipment and disconnection of a serial port of the communication equipment; the general faults of the communication equipment comprise communication equipment system program faults and communication equipment power supply faults; the slight faults of the communication equipment comprise ageing of components of the communication equipment, signal shielding of the communication equipment and faults of connecting wires of the communication equipment;
the state judging module is used for judging the real-time state data of the communication equipment, generating equipment fault maintenance measures according to the real-time state data of the communication equipment if the real-time state data of the communication equipment is judged to be serious faults and general faults, sending the equipment fault maintenance measures to a server, and simultaneously carrying out early warning on the server, wherein the real-time state data of the communication equipment is judged, and if the real-time state data of the communication equipment is judged to be serious faults and general faults of the communication equipment; acquiring equipment historical maintenance data of severe faults of communication equipment and general faults of the communication equipment, and clustering the equipment historical maintenance data by using a mean shift clustering algorithm to obtain an equipment maintenance measure database; generating equipment fault maintenance measures according to severe faults of the communication equipment and general faults of the communication equipment based on the equipment maintenance measure database; the equipment fault maintenance measures are sent to a server, and meanwhile, early warning is carried out on the server;
the state monitoring module is used for acquiring equipment slight fault factors according to the real-time state data of the communication equipment if the communication equipment is judged to be slightly faulty, monitoring the communication equipment according to the equipment slight fault factors, and early warning a server if the equipment slight fault factors continue to expand, wherein if the communication equipment is judged to be slightly faulty, acquiring the equipment slight fault factors according to the real-time state data of the communication equipment; the slight fault factors of the equipment comprise temperature and humidity for accelerating the aging of components of the communication equipment, objects for increasing the signal shielding of the communication equipment and objects for increasing the fault of connecting wires of the communication equipment; monitoring communication equipment components, communication equipment signal shields and communication equipment connecting wires according to the equipment slight fault factors; if the communication equipment component reaches the set use duration, the server is pre-warned; if the signal shielding object of the communication equipment has an increasing trend, the server is pre-warned; if the connecting line of the communication equipment is broken, the server is pre-warned;
the data acquisition module comprises the following submodules:
the device comprises an acquisition submodule, a communication device management submodule and a communication device management submodule, wherein the acquisition submodule is used for acquiring device history state data in communication devices, and the device history state data at least comprise a program state of the communication devices, a connecting line state of the communication devices, a component state of the communication devices, a power indicator state of the communication devices and a serial port state of the communication devices;
the deleting sub-module is used for deleting the missing value data in the equipment history state data to obtain complete equipment history state data;
the normalization sub-module is used for carrying out normalization processing on the complete equipment historical state data to obtain the equipment historical state data to be trained;
the model training module comprises the following submodules:
the training sub-module is used for inputting the historical state data of the equipment to be trained into the initial BO-LSTM communication equipment state monitoring network model for training;
the hidden layer sub-module is used for setting the LSTM hidden layer number in the initial BO-LSTM communication equipment state monitoring network model to be 2;
the optimizer submodule is used for setting an optimizer of the initial BO-LSTM communication equipment state monitoring network model by utilizing an Adam algorithm;
the optimization algorithm sub-module is used for setting the learning rate and the neuron number of the initial BO-LSTM communication equipment state monitoring network model based on a Bayesian optimization algorithm;
an activation function sub-module, configured to set a tanh hyperbolic tangent activation function as an activation function of the initial BO-LSTM communications device state monitoring network model;
and the obtaining submodule is used for setting the MSE loss function as the loss function of the initial BO-LSTM communication equipment state monitoring network model, and setting the iteration times to 100 times to obtain the target BO-LSTM communication equipment state monitoring network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311389176.6A CN117150415B (en) | 2023-10-25 | 2023-10-25 | Communication equipment state monitoring method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311389176.6A CN117150415B (en) | 2023-10-25 | 2023-10-25 | Communication equipment state monitoring method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117150415A CN117150415A (en) | 2023-12-01 |
| CN117150415B true CN117150415B (en) | 2024-02-06 |
Family
ID=88902957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311389176.6A Active CN117150415B (en) | 2023-10-25 | 2023-10-25 | Communication equipment state monitoring method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117150415B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368890A (en) * | 2020-02-26 | 2020-07-03 | 珠海格力电器股份有限公司 | Fault detection method and device and information physical fusion system |
| CN111442489A (en) * | 2020-03-27 | 2020-07-24 | 广东美的暖通设备有限公司 | Control method and system of air conditioner, air conditioner and readable storage medium |
| CN114707401A (en) * | 2022-03-08 | 2022-07-05 | 通号城市轨道交通技术有限公司 | Fault early warning method and device for signal system equipment |
| CN115018178A (en) * | 2022-06-23 | 2022-09-06 | 北京华能新锐控制技术有限公司 | Power station fan fault early warning method based on deep learning |
| CN115563475A (en) * | 2022-10-25 | 2023-01-03 | 南京工业大学 | Pressure soft sensor of excavator hydraulic system |
| CN116541774A (en) * | 2023-05-09 | 2023-08-04 | 中交路桥华南工程有限公司 | Method for monitoring and early warning environmental factors in long tunnel asphalt pavement hole |
-
2023
- 2023-10-25 CN CN202311389176.6A patent/CN117150415B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368890A (en) * | 2020-02-26 | 2020-07-03 | 珠海格力电器股份有限公司 | Fault detection method and device and information physical fusion system |
| CN111442489A (en) * | 2020-03-27 | 2020-07-24 | 广东美的暖通设备有限公司 | Control method and system of air conditioner, air conditioner and readable storage medium |
| CN114707401A (en) * | 2022-03-08 | 2022-07-05 | 通号城市轨道交通技术有限公司 | Fault early warning method and device for signal system equipment |
| CN115018178A (en) * | 2022-06-23 | 2022-09-06 | 北京华能新锐控制技术有限公司 | Power station fan fault early warning method based on deep learning |
| CN115563475A (en) * | 2022-10-25 | 2023-01-03 | 南京工业大学 | Pressure soft sensor of excavator hydraulic system |
| CN116541774A (en) * | 2023-05-09 | 2023-08-04 | 中交路桥华南工程有限公司 | Method for monitoring and early warning environmental factors in long tunnel asphalt pavement hole |
Non-Patent Citations (2)
| Title |
|---|
| Bayesian Optimized Long-Short Term Memory Recurrent Neural Network for Prognostics of Thermally Aged Power Mosfets;Muhammad Haris等;《2020 International Symposium on Recent Advances in Electrical Engineering & Computer Sciences (RAEE & CS)》;第1-5页 * |
| 重大装备形性一体化数字孪生关键技术;宋学官等;《机械工程学报》;第58卷(第10期);第298-325页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117150415A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109102189B (en) | Electrical equipment health management system and method | |
| CN114819415B (en) | Power equipment fault prediction system based on data analysis | |
| CN110220602B (en) | Switch cabinet overheating fault identification method | |
| CN110084158B (en) | Electric equipment identification method based on intelligent algorithm | |
| KR102648377B1 (en) | Intelligent integrated wiring board with network cable quality monitoring | |
| CN117176560B (en) | Monitoring equipment supervision system and method based on Internet of things | |
| CN111628570B (en) | Hydropower station safety monitoring fault diagnosis method and system | |
| CN114137916A (en) | Supervision and control system for circuit board production based on data analysis | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN116308304B (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| CN116823227A (en) | Intelligent equipment management system and method based on Internet of things | |
| CN114640177B (en) | Electric energy efficiency monitoring method based on electric energy efficiency monitoring device | |
| CN117346743A (en) | Water regime remote measuring station intelligent monitoring inspection system based on machine learning model | |
| CN112988843B (en) | SMT chip mounter fault management and diagnosis system based on SQL Server database | |
| CN117150415B (en) | Communication equipment state monitoring method and system based on artificial intelligence | |
| CN110782431B (en) | High-voltage wire icing area detection method based on deep learning | |
| CN112381130A (en) | Cluster analysis-based power distribution room multivariate data anomaly detection method | |
| CN113468823B (en) | Optical module damage detection method and system based on machine learning | |
| CN115452031A (en) | Detecting system is used in rotary encoder switch production | |
| CN113627885A (en) | Power grid power supply abnormity monitoring system and monitoring method thereof | |
| CN111103487A (en) | Non-invasive PST anomaly monitoring method based on power consumption analysis | |
| CN118367682B (en) | Intelligent state identification regulation method and system for electrical equipment | |
| CN117495357B (en) | Electric power data supervision system and method based on big data | |
| CN118376265B (en) | Flow measurement equipment operation intelligent evaluation system suitable for hydrologic station flow measurement | |
| CN115988104B (en) | Sensor compatible processing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |