CN111314113B - Internet of things node fault detection method and device, storage medium and computer equipment - Google Patents
Internet of things node fault detection method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN111314113B CN111314113B CN202010060065.0A CN202010060065A CN111314113B CN 111314113 B CN111314113 B CN 111314113B CN 202010060065 A CN202010060065 A CN 202010060065A CN 111314113 B CN111314113 B CN 111314113B
- Authority
- CN
- China
- Prior art keywords
- internet
- data
- things
- target
- nodes
- 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
Images
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
-
- 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
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- 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
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
A method, a device, a storage medium and computer equipment for detecting node faults of the Internet of things are provided, wherein the method comprises the following steps: acquiring target wireless data acquired by a plurality of target Internet of things nodes in a network; searching label data of the Internet of things nodes adjacent to each target Internet of things node in a pre-stored data diagnosis database, marking the searched label data as source domain data, and marking the target wireless data as target domain data, wherein the label data are wireless data marked with state labels; establishing a deep migration learning model, and training the deep migration learning model according to the source domain data and the target domain data to obtain an internet of things node fault diagnosis model; and carrying out fault diagnosis on the nodes of the Internet of things in the network by using the fault diagnosis model. According to the method, the label data of the adjacent nodes are fully utilized by means of the deep migration learning model, and fault diagnosis is carried out on the label-free wireless data of the nodes of the Internet of things.
Description
Technical Field
The invention relates to the technical field of cloud computing, in particular to a method and a device for detecting node faults of an internet of things, a storage medium and computer equipment.
Background
With the rapid development of the application of the intelligent internet of things, various intelligent services and strict performance requirements make a wireless network based on fog computing or edge computing become an important architecture for supporting the intelligent internet of things. Under the combination of the powerful computing capacity of the cloud data center and the local computing and storage capacity of the edge nodes, the service pressure of different qualities borne by the network can be effectively relieved. At the same time, the complex network structure and functionality also makes network maintenance more difficult. To solve this problem, data mining methods or artificial intelligence methods have been widely used to perform fault detection, diagnosis, and restoration of the network.
However, for the artificial intelligence method, both the supervised learning method and the unsupervised learning method require huge tag data for modeling, and require a lot of expert knowledge, and huge overhead is required for establishing a fault diagnosis model for each wireless node from scratch for a large-scale network. In addition, for the nodes of the internet of things, in consideration of node redeployment and energy-saving optimization strategies, the problems of insufficient data quantity, data expiration and the like exist in part of the nodes. The data cannot establish an effective model in terms of data quantity, and the data are not suitable for training due to different data distribution in terms of data effectiveness, so that the data cannot be subjected to fault detection by using a fault diagnosis model.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a method, an apparatus, a storage medium, and a computer device for detecting a fault of a node of an internet of things, in order to solve the problem in the prior art that an effective fault diagnosis model cannot be established and fault detection cannot be performed for nodes with insufficient data volume and expired data in a network.
A method for detecting a node fault of an Internet of things comprises the following steps:
acquiring target wireless data acquired by a plurality of target Internet of things nodes in a network, wherein the target wireless data is wireless data of Internet of things equipment which is acquired by the target Internet of things nodes and connected with the target Internet of things nodes;
searching label data of the Internet of things nodes adjacent to each target Internet of things node in a pre-stored data diagnosis library, marking the searched label data as source domain data, and simultaneously marking the target wireless data as target domain data, wherein the label data are wireless data marked with state labels;
establishing a deep migration learning model, and training the deep migration learning model according to the source domain data and the target domain data to obtain an internet of things node fault diagnosis model;
and carrying out fault diagnosis on the nodes of the Internet of things in the network by using the fault diagnosis model.
Further, in the method for detecting a fault of a node of the internet of things, the step of searching the label data of the node of the internet of things adjacent to each target node of the internet of things in a pre-stored data diagnosis database includes:
searching an internet of things node in the same network with the target internet of things node in a pre-stored data diagnosis database;
and performing cluster analysis on the searched label data of the nodes of the Internet of things to determine the nodes of the Internet of things similar to the wireless data distribution of the target nodes of the Internet of things, thereby determining the nodes of the Internet of things adjacent to the target nodes of the Internet of things and the label data of the nodes of the Internet of things.
Further, in the method for detecting a fault of a node of the internet of things, the step of training the deep migration learning model according to the source domain data and the target domain data to obtain a fault diagnosis model includes:
dividing the target domain data into training data and test data;
training the deep migration learning model according to the source domain data and the training data, and testing the trained deep migration learning model according to the test data;
and when the trained deep migration learning model is tested to be qualified, determining the trained deep migration learning model as a fault diagnosis model.
Further, the method for detecting faults of nodes of the internet of things further includes, after the step of performing fault diagnosis on the nodes of the internet of things in the network by using the fault diagnosis model:
and storing the fault diagnosis result into a data diagnosis database, and uploading the fault diagnosis result to a visualization platform.
Further, in the method for detecting a node fault in the internet of things, the wireless data includes a signal to interference plus noise ratio, a reference signal received power, a throughput, and a frame error rate.
The embodiment of the invention also provides a device for detecting the node fault of the internet of things, which comprises:
the acquisition module is used for acquiring target wireless data acquired by a plurality of target Internet of things nodes in a network, wherein the target wireless data is wireless data of Internet of things equipment which is acquired by the target Internet of things acquisition Internet of things nodes and is connected with the target Internet of things acquisition Internet of things nodes;
the searching module is used for searching label data of the Internet of things nodes adjacent to each target Internet of things node in a pre-stored data diagnosis database, marking the searched label data as source domain data, and meanwhile marking the target wireless data as target domain data, wherein the label data are wireless data marked with state labels;
the model establishing module is used for establishing a deep migration learning model and training the deep migration learning model according to the source domain data and the target domain data to obtain an internet of things node fault diagnosis model;
and the diagnosis module is used for diagnosing faults of the nodes of the Internet of things in the network by using the fault diagnosis model.
Further, above-mentioned thing networking node fault detection device, wherein, the search module is specifically used for:
searching an Internet of things node in the same network with the target Internet of things node in a pre-stored data diagnosis database;
and performing cluster analysis on the searched label data of the nodes of the Internet of things to determine the nodes of the Internet of things similar to the wireless data distribution of the target nodes of the Internet of things, thereby determining the nodes of the Internet of things adjacent to the target nodes of the Internet of things and the label data of the nodes of the Internet of things.
Further, the internet of things node fault detection apparatus, wherein the model building module is specifically configured to:
dividing the target domain data into training data and test data;
training the deep migration learning model according to the source domain data and the training data, and testing the trained deep migration learning model according to the test data;
and when the trained deep migration learning model is tested to be qualified, determining the trained deep migration learning model as a fault diagnosis model.
The invention also provides a storage medium having a program stored thereon, which when executed by a processor implements any of the methods described above.
An embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and when the processor executes the program, the method described in any one of the above is implemented.
The invention relates to a fault diagnosis method for nodes of the Internet of things based on deep migration learning, which is used for detecting wireless data of target nodes with state labels in a network and more importantly can also be used for detecting wireless data of the target nodes without labels. According to the method, the label data of the adjacent nodes are fully utilized by means of the deep migration learning model, fault diagnosis is carried out on the label-free wireless data of the nodes of the Internet of things, and fault classification is completed. The method can effectively solve the problem that the machine learning model cannot be established due to no historical fault data of the nodes of the Internet of things, and can reduce the time consumed by collecting enough fault data for each node to establish the model and the dependence on expert knowledge.
Drawings
Fig. 1 is a flowchart of a method for detecting a node fault in the internet of things according to a first embodiment of the present invention;
fig. 2 is a flowchart of a node fault detection method for the internet of things in a second embodiment of the present invention;
fig. 3 is a block diagram of a node fault detection apparatus of the internet of things in a third embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention and are not to be construed as limiting the present invention.
These and other aspects of embodiments of the invention will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the invention have been disclosed in detail as being indicative of some of the ways in which the principles of the embodiments of the invention may be practiced, but it is understood that the scope of the embodiments of the invention is not limited correspondingly. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Referring to fig. 1, a method for detecting a node fault of an internet of things in a first embodiment of the present invention includes steps S11 to S14.
The network fault node detection method in the embodiment of the invention detects the network node based on the fault diagnosis model established by deep migration learning.
Step S11, target wireless data collected by a plurality of target Internet of things nodes in a network are obtained, and the target wireless data are wireless data of Internet of things equipment which is collected by the target Internet of things nodes and connected with the target Internet of things nodes.
The embodiment of the invention is applied to a cloud computing center which is used for analyzing and processing data and is a computer device. And each Internet of things node in the network performs information interaction with the cloud computing center in a wireless communication mode. The internet of things node is provided with a communication module, collects wireless data of internet of things equipment connected with the internet of things node, and uploads the collected wireless data to the cloud computing center. The wireless data includes but is not limited to signal to interference plus noise ratio, reference signal received power, throughput, frame error rate.
During specific implementation, the internet of things node sends acquired wireless data to the cloud computing center after preprocessing the acquired wireless data. The preprocessing of the wireless data comprises noise data removal, missing data filling and feature normalization operation, and the processed data are sent to a cloud computing center. The node of the Internet of things is provided with a computing module, and the computing module is used for data preprocessing operation. The denoising data, taking the throughput index as an example, counts outlier data points in the throughput data, and deletes the data. Filling missing data, taking the throughput index as an example, if the throughput index at a certain time is empty, selecting the values of the previous time and the next time to calculate an average value, and filling the average value on the missing value. The data normalization operation may be performed using data normalization algorithms known in the art, including but not limited to max-min normalization and zero-mean normalization.
And S12, searching label data of the Internet of things nodes adjacent to each target Internet of things node in a pre-stored data diagnosis library, marking the searched label data as source domain data, and marking the target wireless data as target domain data, wherein the label data are wireless data marked with state labels.
The cloud computing center prestores a data diagnosis database, the data diagnosis database stores information of each Internet of things node in the network, the information comprises geographic position coordinate parameters and/or serial numbers of the Internet of things nodes in the network, key performance indexes such as signal-to-noise ratio, reference signal receiving power, throughput and the like, and state labels corresponding to each group of key performance indexes such as normal, weak coverage, over coverage and the like are included.
The cloud computing center searches the database for label data of the internet of things nodes adjacent to each target internet of things node. The adjacent internet of things node is an internet of things node similar to the wireless data distribution of the target node in the data diagnosis database. The cloud computing center marks the searched label data of the adjacent Internet of things nodes as source domain data, and marks the target domain data of the wireless data marks of the target Internet of things nodes.
As can be appreciated, the network includes a large number of nodes of the internet of things, and there are nodes of the internet of things with insufficient data volume and outdated data. The data diagnosis library can selectively set information of partial internet of things nodes with complete data in the network, so that data label information can be reduced, and the cost and difficulty of a fault diagnosis model can be reduced.
In the above step, the step of searching the pre-stored data diagnosis database for the label data of the internet of things node adjacent to each target internet of things node specifically includes:
step S121, searching an Internet of things node in the same network with the current target Internet of things node in a pre-stored data diagnosis database;
step S122, performing cluster analysis on the searched label data of the Internet of things nodes, and determining the Internet of things nodes similar to the wireless data distribution of the current target Internet of things node according to a clustering result, thereby determining the Internet of things nodes adjacent to the current target Internet of things node and label data thereof.
The searching method can search according to the geographic position and the number of the target node, and after the nodes of the same network are determined, clustering is carried out according to the wireless data to find the nodes similar to the data distribution of the target node, wherein the clustering method comprises but is not limited to a K average clustering method and a density clustering method. The K-means clustering method is taken as an example for explanation:
selecting key performance index data which are the same as the current target Internet of things node from a data diagnosis base, and assigning K categories;
calculating the distance between the data and the clustering center and classifying the data into the nearest class;
calculating the average value of the class and using the average value to update the value of the cluster center;
the above steps are repeated until the value of the cluster center is not changed.
And S13, establishing a deep migration learning model, and training the deep migration learning model according to the source domain data and the target domain data to obtain an Internet of things node fault diagnosis model.
The cloud computing center firstly establishes an initial deep learning migration model, trains the deep learning migration model according to source domain data and target domain data, and the trained deep learning migration model is the fault diagnosis model. The deep migration learning model includes, but is not limited to, a deep domain confrontation network, a deep adaptive neural network and the like.
The source domain data comprises wireless data of the network and a state label corresponding to the current data, and the target domain data only comprises the wireless data of the network and does not comprise the state label corresponding to the current data. Wherein the wireless data type of the source domain data and the target domain data is the same. The deep migration learning model utilizes the two parts of data for model training.
Specifically, the training of the deep migration learning model includes two links of training and testing, wherein the target source data is divided into two parts, one part is used as training data, the other part is used as testing data, and the division ratio can be set according to requirements, for example, the training data and the testing data are 7.
The step of training the deep learning migration model comprises the following steps:
step S131, training the deep migration learning model according to the source domain data and the training data, and testing the trained deep migration learning model according to the test data;
step S132, when the trained deep migration learning model is tested to be qualified, determining that the trained deep migration learning model is a fault diagnosis model.
And after the deep migration learning model is trained according to the source domain data and the training data, testing the deep migration learning model by adopting the test data. And testing, wherein the output of the deep migration learning model is a state label. Comparing the state label output by the deep migration learning model with the actual network state of the test data, and if the accuracy reaches a preset threshold value, determining that the model training is successful; and if the threshold value is not reached, returning to the step of continuously executing the model training. The threshold value is set according to actual needs, for example, 95%.
And S14, performing fault diagnosis on the nodes of the Internet of things in the network by using the fault diagnosis model.
The established fault diagnosis model can be used for fault diagnosis of each node of the internet of things in the network. In this step, the detected internet of things node may be the target internet of things node or other internet of things nodes in the network. When the fault diagnosis model detects the nodes of the Internet of things, the wireless data of the nodes are input and then the result is directly output, if the detected nodes of the Internet of things are in fault, the state label is directly output, and if the detected nodes of the Internet of things are in fault, the information which represents the normal state is output, or no information or output is output.
It can be understood that, in this embodiment, wireless data of a stateless tag can be detected, and the data cannot judge the current state of the network from the currently collected key performance indicators. And classifying the collected label-free data by using the trained deep migration learning model aiming at the data. For example, wireless data is collected every fifteen minutes, the wireless data is a one-dimensional vector including key performance indicators such as signal-to-noise ratio, throughput, and reference signal received power, and the state of the network is the label of the vector, such as normal, weak coverage, and over coverage labels. Generally, the real-time network state (namely, data label) cannot be known, and label data information of similar nodes can be migrated by using deep migration learning to perform fault diagnosis on the node.
In the embodiment, by using the fault information of other nodes in the same network, the high-dimensional characteristics of the fault information are extracted by using a deep migration learning method, and the fault reason of the target node is diagnosed by using the existing node fault information, so that the problems that label data is lacked, and the fault diagnosis model cannot be established and the fault diagnosis cannot be performed due to different data distributions can be solved.
Further, as another embodiment of the present invention, as shown in fig. 2, in a second embodiment of the present invention, the method for diagnosing a node fault of an internet of things further includes:
and S15, storing the fault diagnosis result into a data diagnosis database, and uploading the fault diagnosis result to a visualization platform.
Specifically, a communication module of the cloud computing center uploads the network state of the wireless data of the target node in the previous step to a visualization platform, and the visualization platform can display the current network state and provide network state information for maintenance personnel. Meanwhile, a storage module of the cloud computing center stores the wireless data of the target node and the network state in the last step in a data diagnosis library, so that more available data are provided for subsequent fault diagnosis.
Referring to fig. 3, a node fault detection apparatus for internet of things according to a third embodiment of the present invention includes:
the system comprises an acquisition module 10, a processing module and a processing module, wherein the acquisition module is used for acquiring target wireless data acquired by a plurality of target internet of things nodes in a network, and the target wireless data is wireless data of internet of things equipment which is acquired by the target internet of things nodes and is connected with the target internet of things nodes;
the searching module 20 is configured to search a pre-stored data diagnosis library for tag data of an internet of things node adjacent to each target internet of things node, mark the searched tag data as source domain data, and mark the target wireless data as target domain data, where the tag data is wireless data marked with a status tag;
the model establishing module 30 is configured to establish a deep migration learning model, and train the deep migration learning model according to the source domain data and the target domain data to obtain an internet of things node fault diagnosis model;
and the diagnosis module 40 is used for performing fault diagnosis on the nodes of the internet of things in the network by using the fault diagnosis model.
Further, in the device for detecting a node fault in the internet of things, the search module 20 is specifically configured to:
searching an internet of things node in the same network with the target internet of things node in a pre-stored data diagnosis database;
and performing cluster analysis on the searched label data of the nodes of the Internet of things to determine the nodes of the Internet of things similar to the wireless data distribution of the target nodes of the Internet of things, thereby determining the nodes of the Internet of things adjacent to the target nodes of the Internet of things and label data thereof.
Further, in the device for detecting a node fault in the internet of things, the model building module 30 is specifically configured to:
dividing the target domain data into training data and testing data;
training the deep migration learning model according to the source domain data and the training data, and testing the trained deep migration learning model according to the test data;
and when the trained deep migration learning model is tested to be qualified, determining the trained deep migration learning model as a fault diagnosis model.
The implementation principle and the generated technical effects of the internet of things node fault detection device provided by the embodiment of the invention are the same as those of the method embodiment, and for brief description, corresponding contents in the method embodiment can be referred to where the device embodiment is not mentioned.
An embodiment of the present invention further provides a storage medium, on which a program is stored, where the program is executed by a processor to implement any one of the methods described above.
An embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and when the processor executes the program, the method described in any one of the above is implemented.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following technologies, which are well known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., 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 invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. 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 above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method for detecting a node fault of an Internet of things is characterized by comprising the following steps:
acquiring target wireless data acquired by a plurality of target Internet of things nodes in a network, wherein the target wireless data is wireless data of Internet of things equipment which is acquired by the target Internet of things nodes and is connected with the target Internet of things nodes;
searching label data of an internet of things node adjacent to each target internet of things node in a pre-stored data diagnosis library, marking the searched label data as source domain data, and simultaneously marking the target wireless data as target domain data, wherein the label data are wireless data marked with a state label, and the steps comprise:
searching an internet of things node in the same network with the target internet of things node in a pre-stored data diagnosis database;
performing cluster analysis on the searched label data of the nodes of the Internet of things to determine the nodes of the Internet of things similar to the wireless data distribution of the target nodes of the Internet of things, thereby determining the nodes of the Internet of things adjacent to the target nodes of the Internet of things and the label data of the nodes of the Internet of things;
marking the searched tag data as source domain data, and marking the target wireless data as target domain data, wherein the tag data is wireless data marked with a state tag;
establishing a deep migration learning model, and training the deep migration learning model according to the source domain data and the target domain data to obtain an internet of things node fault diagnosis model;
and carrying out fault diagnosis on the nodes of the Internet of things in the network by using the fault diagnosis model.
2. The method for detecting the node fault in the internet of things according to claim 1, wherein the step of training the deep migration learning model according to the source domain data and the target domain data to obtain the fault diagnosis model comprises:
dividing the target domain data into training data and test data;
training the deep migration learning model according to the source domain data and the training data, and testing the trained deep migration learning model according to the test data;
and when the trained deep migration learning model is tested to be qualified, determining the trained deep migration learning model as a fault diagnosis model.
3. The method for detecting the fault of the node of the internet of things according to claim 1, wherein the step of diagnosing the fault of the node of the internet of things in the network by using the fault diagnosis model further comprises the following steps:
and storing the fault diagnosis result into a data diagnosis database, and uploading the fault diagnosis result to a visualization platform.
4. The method of claim 1, wherein the wireless data comprises signal-to-interference-and-noise ratio (SINR), reference Signal Received Power (RSRP), throughput, and frame error rate (FRA).
5. The utility model provides a thing networking node fault detection device which characterized in that includes:
the acquisition module is used for acquiring target wireless data acquired by a plurality of target Internet of things nodes in a network, wherein the target wireless data is wireless data of Internet of things equipment which is acquired by the target Internet of things acquisition Internet of things nodes and is connected with the target Internet of things acquisition Internet of things nodes;
the searching module is used for searching label data of the Internet of things nodes adjacent to each target Internet of things node in a pre-stored data diagnosis database, marking the searched label data as source domain data, and meanwhile marking the target wireless data as target domain data, wherein the label data are wireless data marked with state labels;
the search module is specifically configured to:
searching an Internet of things node in the same network with the target Internet of things node in a pre-stored data diagnosis database;
performing cluster analysis on the searched label data of the nodes of the Internet of things to determine the nodes of the Internet of things similar to the wireless data distribution of the target nodes of the Internet of things, thereby determining the nodes of the Internet of things adjacent to the target nodes of the Internet of things and the label data of the nodes of the Internet of things;
the model establishing module is used for establishing a deep migration learning model and training the deep migration learning model according to the source domain data and the target domain data to obtain an internet of things node fault diagnosis model;
and the diagnosis module is used for diagnosing the fault of the nodes of the Internet of things in the network by utilizing the fault diagnosis model.
6. The internet-of-things node fault detection device of claim 5, wherein the model building module is specifically configured to:
dividing the target domain data into training data and testing data;
training the deep migration learning model according to the source domain data and the training data, and testing the trained deep migration learning model according to the test data;
and when the trained deep migration learning model is tested to be qualified, determining the trained deep migration learning model as a fault diagnosis model.
7. A storage medium having a program stored thereon, wherein the program, when executed by a processor, implements the method of any of claims 1-5.
8. A computer device comprising a memory, a processor and a program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1-5 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010060065.0A CN111314113B (en) | 2020-01-19 | 2020-01-19 | Internet of things node fault detection method and device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010060065.0A CN111314113B (en) | 2020-01-19 | 2020-01-19 | Internet of things node fault detection method and device, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111314113A CN111314113A (en) | 2020-06-19 |
| CN111314113B true CN111314113B (en) | 2023-04-07 |
Family
ID=71160104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010060065.0A Active CN111314113B (en) | 2020-01-19 | 2020-01-19 | Internet of things node fault detection method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111314113B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114095336A (en) * | 2020-08-07 | 2022-02-25 | 中国移动通信集团海南有限公司 | End-to-end problem diagnosis method and system |
| CN112804336B (en) * | 2020-10-29 | 2022-11-01 | 浙江工商大学 | Fault detection method, device, system and computer readable storage medium |
| TWI793604B (en) * | 2021-05-12 | 2023-02-21 | 國立陽明交通大學 | Method for fault diagnosis in communication network |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948648A (en) * | 2019-01-31 | 2019-06-28 | 中山大学 | A kind of multiple target domain adaptive migration method and system based on member confrontation study |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160078359A1 (en) * | 2014-09-12 | 2016-03-17 | Xerox Corporation | System for domain adaptation with a domain-specific class means classifier |
| CN106483449B (en) * | 2016-09-09 | 2019-01-25 | 电子科技大学 | Analog-circuit fault diagnosis method based on deep learning and Complex eigenvalues |
| JP6956028B2 (en) * | 2018-02-22 | 2021-10-27 | ファナック株式会社 | Failure diagnosis device and machine learning device |
| CN110619342B (en) * | 2018-06-20 | 2023-02-03 | 鲁东大学 | Rotary machine fault diagnosis method based on deep migration learning |
| CN109766921B (en) * | 2018-12-19 | 2021-08-03 | 合肥工业大学 | Vibration data fault classification method based on depth field self-adaption |
| CN110084148A (en) * | 2019-04-09 | 2019-08-02 | 东南大学 | A kind of Mechanical Failure of HV Circuit Breaker diagnostic method |
| CN109947086B (en) * | 2019-04-11 | 2020-07-28 | 清华大学 | Mechanical fault migration diagnosis method and system based on counterstudy |
| CN110533070A (en) * | 2019-07-26 | 2019-12-03 | 西安交通大学 | A kind of mechanical breakdown intelligent diagnosing method based on migration original shape network under small sample |
-
2020
- 2020-01-19 CN CN202010060065.0A patent/CN111314113B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109948648A (en) * | 2019-01-31 | 2019-06-28 | 中山大学 | A kind of multiple target domain adaptive migration method and system based on member confrontation study |
Non-Patent Citations (2)
| Title |
|---|
| Fuzzy Clustering of Seismic Sequences: Segmentation of Time-Frequency Representations;HoseiHosein;《 IEEE Signal Processing Magazine》;20120531;第29卷(第3期);全文 * |
| 基于深度学习的滚动轴承故障诊断方法研究;金余丰;《中国优秀硕士学位论文数据库》;20200116;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111314113A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111314113B (en) | Internet of things node fault detection method and device, storage medium and computer equipment | |
| CN109936582A (en) | Construct the method and device based on the PU malicious traffic stream detection model learnt | |
| CN109120435B (en) | Network link quality prediction method, device and readable storage medium | |
| CN112543465B (en) | Abnormity detection method, abnormity detection device, terminal and storage medium | |
| CN106874187A (en) | code coverage collection method and device | |
| CN107809766B (en) | Method and device for generating machine learning sample for network optimization | |
| US20090043536A1 (en) | Use of Sequential Clustering for Instance Selection in Machine Condition Monitoring | |
| CN111130890A (en) | Network flow dynamic prediction system | |
| CN109615015A (en) | A kind of data preprocessing method based on block chain intelligence contract and machine learning | |
| CN112837799B (en) | Remote internet big data intelligent medical system based on block chain | |
| CN108809734A (en) | Network alarm root-cause analysis method, system, storage medium and computer equipment | |
| CN111586728B (en) | Small sample characteristic-oriented heterogeneous wireless network fault detection and diagnosis method | |
| CN114118219A (en) | Data-driven real-time abnormal detection method for health state of long-term power-on equipment | |
| CN108470194A (en) | A kind of Feature Selection method and device | |
| CN117034143B (en) | Distributed system fault diagnosis method and device based on machine learning | |
| Carrillo et al. | Design of efficient deep learning models for determining road surface condition from roadside camera images and weather data | |
| De Vita et al. | A semi-supervised bayesian anomaly detection technique for diagnosing faults in industrial iot systems | |
| CN113807462B (en) | Network equipment fault cause positioning method and system based on AI | |
| CN112732773B (en) | Method and system for checking uniqueness of relay protection defect data | |
| CN114579659A (en) | System and method for estimating and sorting utilization potential of power battery by gradient utilization | |
| Hairuman et al. | Evaluation of machine learning techniques for anomaly detection on hourly basis kpi | |
| Sikka et al. | An investigation on the metric threshold for fault-proneness | |
| CN113947129B (en) | Method, equipment and medium for training and using AI model for intelligently identifying wheel out-of-roundness state | |
| CN117499817B (en) | Distributed ammeter acquisition system and acquisition method | |
| Valera et al. | On the application of unsupervised clustering to sound pressure data from an acoustic sensors network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 330000, 2nd Floor, Phase 2, No. 669 Huangtang East Street, Ganjiang New District, Nanchang City, Jiangxi Province Patentee after: Jiangxi smart IOT Research Institute Co.,Ltd. Address before: 330000, 2nd Floor, Phase 2, No. 669 Huangtang East Street, Ganjiang New District, Nanchang City, Jiangxi Province Patentee before: Ganjiang New Area Intelligent Material Union Research Institute Co.,Ltd. |