CN115001937A - Fault prediction method and device for smart city Internet of things - Google Patents
Fault prediction method and device for smart city Internet of things Download PDFInfo
- Publication number
- CN115001937A CN115001937A CN202210376991.8A CN202210376991A CN115001937A CN 115001937 A CN115001937 A CN 115001937A CN 202210376991 A CN202210376991 A CN 202210376991A CN 115001937 A CN115001937 A CN 115001937A
- Authority
- CN
- China
- Prior art keywords
- fault prediction
- smart city
- things
- residual error
- feature
- 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.)
- Granted
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
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/40—Maintenance of things
-
- 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
- H04L41/147—Network analysis or design for predicting network behaviour
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a fault prediction method and a fault prediction device for an Internet of things of a smart city, wherein the method comprises the following steps: acquiring network data to be predicted of smart city Internet of things equipment; inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data; the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set. The fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, so that fault prediction of the smart city Internet of things equipment can be realized through the lightweight model, and the safety and the robustness of the smart city Internet of things are effectively guaranteed.
Description
Technical Field
The invention relates to the technical field of network fault prediction, in particular to a fault prediction method and device for an internet of things of a smart city.
Background
With the development of smart devices and 5G networks, the use of edge smart devices has seen explosive growth. To provide the unlimited connectivity required for such devices, a basis for trusted systems and a smart city internet of things computing architecture are required. In order to achieve the vision of service availability in a trustworthy system, the sustainability and reliability of the internet of things in a smart city are very important. But along with the complication of smart city thing networking service and subassembly, trouble takes place occasionally in the smart city thing networking for the reliability of smart city thing networking can't be ensured.
The network fault prediction is based on the historical conditions of the network nodes, and is combined with the current nodes and the network conditions for analysis, the specific state of each type of fault is excavated, and then an association model between the state and the fault is established, the types of the faults which are likely to occur in the future of the nodes are presumed, and the sustainability and the reliability of the network are guaranteed. The traditional convolutional neural network has strong spatial feature extraction capability and learning capability, and can be applied to fault prediction. However, as the network model is deeper and deeper, the model identification precision is reduced, so that the model effect is worse and worse. The problem is solved easily due to the occurrence of a residual error network, but the feature input of a lower-layer network into a high-layer network can only be completed through one residual error connecting channel due to the existence of a shortcut of a residual error structure, so that a residual error block does not have enough weight to learn the multidimensional data features of nodes under the smart city internet of things, and the problem that the learning of the running data features of the nodes is not accurate enough is caused.
In the thing networking of wisdom city, edge equipment is miniature computational equipment usually, small-size intelligent equipment such as sensor, mobile terminal, and these equipment often computing capacity is limited, leads to common deep learning model can't be applicable to wisdom city thing networking failure prediction.
Disclosure of Invention
The invention provides a fault prediction method and device for smart city Internet of things, which are used for solving the defect that a deep learning model in the prior art cannot be suitable for fault prediction of smart city Internet of things, realizing fault prediction of smart city Internet of things equipment and effectively guaranteeing the safety and the robustness of an edge side network.
The invention provides a fault prediction method for an Internet of things of a smart city, which comprises the following steps:
acquiring network data to be predicted of smart city Internet of things equipment;
inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
According to the fault prediction method for the smart city Internet of things, the training method of the fault prediction model comprises the following steps:
acquiring characteristic data information of smart city Internet of things equipment as a training set of a model;
establishing an initial fault prediction model, inputting the characteristic data information into the initial fault prediction model to obtain a fault prediction result of a characteristic vector, and evaluating prediction accuracy based on the fault prediction result;
and iteratively updating the initial fault prediction model, and adjusting model parameters of the initial fault prediction model until the error value between the fault prediction result and the prediction label meets a preset threshold value, and the prediction accuracy reaches a target value to obtain the trained fault prediction model.
According to the fault prediction method for the smart city Internet of things, which is provided by the invention, the initial fault prediction model is established, the characteristic data information is input into the initial fault prediction model, the fault prediction result of the characteristic vector is obtained, and the prediction accuracy is evaluated based on the fault prediction result, and the fault prediction method comprises the following steps:
establishing an initial fault prediction model, wherein the initial fault prediction model comprises a convolution layer, a residual error structural layer and a result processing layer;
the convolutional layer is used for extracting spatial feature information of input feature data information based on the convolutional layer and acquiring a first spatial feature by combining an excitation function of the convolutional layer;
wherein the convolutional layer is built based on a convolutional decomposition operation;
the residual error structural layer is used for learning residual error information based on the first spatial feature output by the convolutional layer and outputting a second spatial feature of the feature data information;
the result processing layer is used for obtaining a fault prediction result of the characteristic data information based on the second spatial characteristics output by the residual error structural layer;
and evaluating the prediction accuracy of the fault prediction model based on the fault prediction result.
According to the fault prediction method for the smart city Internet of things, the residual error structural layer comprises a first residual error connecting channel and a second residual error connecting channel;
residual error information learning is performed based on a first spatial feature output by the convolutional layer, and the residual error information learning method comprises the following steps:
obtaining a first residual mapping result of a first spatial feature output by the convolutional layer through the first residual connecting channel, and obtaining a second residual mapping result of the first spatial feature output by the convolutional layer through the second residual connecting channel;
and performing multiplicative flow residual error information learning on the first residual error mapping result and the first spatial characteristic, and performing additive flow residual error information learning on the second residual error mapping result and the first spatial characteristic.
According to the fault prediction method for the smart city Internet of things, the method for evaluating the prediction accuracy of the fault prediction model based on the fault prediction result comprises the following steps:
acquiring the feature number of feature data information, selecting a target feature based on the feature number of the feature data information, and acquiring a data value corresponding to the target feature based on the fault prediction result;
and acquiring a state data value of the intelligent city Internet of things of the target characteristics at the target moment, and evaluating the prediction accuracy of the fault prediction model by combining the characteristic number and the data value corresponding to the target characteristics.
According to the fault prediction method for the smart city Internet of things, provided by the invention, after residual error information learning is carried out based on the first spatial feature output by the convolutional layer and the second spatial feature of the feature data information is output, the fault prediction method further comprises the following steps:
performing batch normalization processing on the second spatial features of the feature data information and inputting the second spatial features into the result processing layer;
the obtaining of the fault prediction result of the feature data information through the result processing layer based on the second spatial feature output by the residual error structural layer includes:
and obtaining a fault prediction result of the characteristic data information through the result processing layer based on the second spatial characteristics after batch normalization processing.
The invention also provides a fault prediction device for the smart city internet of things, which comprises the following components:
the acquisition module is used for acquiring network data to be predicted of the smart city Internet of things equipment;
the prediction module is used for inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the program, the fault prediction method for the smart city internet of things is realized.
The present invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method for fault prediction for smart city internet of things as described in any of the above.
The invention also provides a computer program product, which comprises a computer program, and the computer program is used for realizing the fault prediction method for the smart city internet of things when being executed by a processor.
According to the fault prediction method and device for the smart city Internet of things, network data to be predicted of smart city Internet of things equipment are obtained; the network data are input into the trained fault prediction model to obtain the fault prediction result of the network data, and the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, so that the fault prediction of the smart city Internet of things equipment can be realized through a lightweight model, and the safety and the robustness of the smart city Internet of things are effectively guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a fault prediction method for the internet of things of a smart city according to the present invention;
fig. 2 is a second schematic flow chart of the fault prediction method for the internet of things of the smart city according to the present invention;
FIG. 3 is a schematic diagram of the structure of the fault prediction model of the present invention;
FIG. 4 is a schematic structural diagram of a residual structural layer according to the present invention;
fig. 5 is a schematic structural diagram of a fault prediction device for the internet of things of a smart city according to the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The fault prediction method and device for the internet of things of the smart city according to the present invention are described with reference to fig. 1 to 6.
Referring to fig. 1, the fault prediction method for the smart city internet of things provided by the invention comprises the following steps:
and 110, acquiring network data to be predicted of the smart city Internet of things equipment.
Specifically, the smart city internet of things device in this embodiment is a computing device in the smart city internet of things, such as an intelligent computing device like a sensor or a mobile terminal. The network data is data needing fault prediction in the smart city Internet of things. The fault prediction is based on the historical conditions of the network nodes, analysis is carried out by combining the current nodes and the network conditions, the specific state of each type of fault is excavated, an association model between the state and the fault is further established, the types of the faults which are likely to occur in the future of the nodes are presumed, and the sustainability and the reliability of the network are guaranteed.
And 120, inputting the network data into the trained fault prediction model to obtain a fault prediction result of the network data.
The fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
Specifically, this step is an application process of the fault prediction model, that is, the trained model is incorporated into a specific application scenario.
And inputting the network data needing fault prediction into the trained model for prediction, thereby obtaining the fault prediction result of the network data.
It should be noted that, in the training process of the fault prediction model, an error value is generated between the output result of the model and the prediction label, parameters of the model can be adjusted according to the error value, when the error value reaches a preset target value, the model converges, and the fault prediction model at this time is kept as the trained model to perform fault prediction.
It should be noted that the fault prediction model in this embodiment is established based on a convolutional decomposition operation and an improved residual network structure, and the convolutional layer is improved based on the idea of the inclusion module, so as to reduce the parameter amount of the convolutional layer and thus reduce the network computation amount. And according to the improved residual error network structure, under the same parameter quantity, compared with the residual error network structure before improvement, the learning capability of the network can be improved, and the spatial feature extraction capability of the network on fault information is improved.
According to the fault prediction method for the smart city Internet of things, network data to be predicted of smart city Internet of things equipment are obtained; the network data are input into the trained fault prediction model to obtain the fault prediction result of the network data, and the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, so that fault prediction of smart city Internet of things equipment can be realized through a lightweight model, and the safety and the robustness of the smart city Internet of things are effectively guaranteed.
Referring to fig. 2, based on the above embodiment, the training method of the fault prediction model includes the following steps:
and step 210, acquiring characteristic data information of the smart city Internet of things equipment as a training set of the model.
Step 220, establishing an initial fault prediction model, inputting the characteristic data information into the initial fault prediction model to obtain a fault prediction result of the characteristic vector, and evaluating the prediction accuracy based on the fault prediction result.
And 230, iteratively updating the initial fault prediction model, and adjusting model parameters of the initial fault prediction model until the error value between the fault prediction result and the prediction label meets a preset threshold value, and the prediction accuracy reaches a target value to obtain a trained fault prediction model.
Specifically, the present embodiment is a training process of the fault prediction model, that is, an obtaining process of the model.
Firstly, a large amount of new feature data information of smart city internet of things equipment is obtained to serve as a training set of a model, namely a sample. The fault status sequence of the characteristic new data information may be represented as: h f ＝(X 1 ,X 2 ,…,X t )。
Wherein, X t The data sequence represented is X t ＝(x t-l ,x t-l+1 ,..,x t-1 )，x t-1 Showing the state of the Internet of things of the smart city at the moment of t-1A feature vector.
Then, an initial fault prediction model needing to be trained is established, new feature data information of the smart city Internet of things equipment is input into the model to obtain a prediction result of the model, and then accuracy evaluation is carried out on the prediction result.
The training process of the model is an iterative updating process, namely, the error between the output result of the current model and the expected result is utilized to adjust the model parameters, and the model training is represented to be completed under the condition that the error between the current output result and the expected result meets a preset threshold value and the accuracy corresponding to the expected result meets a target value.
Based on the above embodiments, the establishing an initial fault prediction model, inputting the feature data information into the initial fault prediction model, obtaining a fault prediction result of a feature vector, and evaluating prediction accuracy based on the fault prediction result includes:
establishing an initial fault prediction model, wherein the initial fault prediction model comprises a convolution layer, a residual error structural layer and a result processing layer;
the convolutional layer is used for extracting spatial feature information of input feature data information based on the convolutional layer and acquiring a first spatial feature by combining an excitation function of the convolutional layer;
wherein the convolutional layer is built based on a convolutional decomposition operation;
the residual error structural layer is used for learning residual error information based on the first spatial feature output by the convolutional layer and outputting a second spatial feature of the feature data information;
the result processing layer is used for obtaining a fault prediction result of the characteristic data information based on the second spatial characteristics output by the residual error structural layer;
and evaluating the prediction accuracy of the fault prediction model based on the fault prediction result.
Specifically, the embodiment is a specific building process of the fault prediction model, which includes a building process of a plurality of layer structures of the model.
Referring to fig. 3, the failure prediction model in the present embodiment includes a convolution layer 310, a residual structural layer 320(Two-way residual structure), and a result processing layer 330 (softmax).
Firstly, building a convolutional layer, extracting spatial feature information from Input feature data information (Input), and acquiring a first spatial feature by combining an excitation function of the convolutional layer. The convolution decomposition operation in this embodiment is specifically embodied as: the idea of the inclusion module is improved, and the convolution layers select two convolution layers of 1 × 1(Conv1 × 1) and 3 × 3(Conv3 × 3) to replace a convolution kernel of 7 × 7, namely only three convolution layers in the model, so that the parameter quantity of the convolution layers is reduced, and the network calculation quantity is reduced.
It should be noted that, an excitation function follows each convolution layer to strengthen the learning ability of the network, in this embodiment, an improved Relu function is used as the excitation function, and when the input of the conventional Relu function is negative, the output is 0, so that the output of the negative input is eliminated, and the fault information extraction effect is affected. Therefore, from the new definition of the N-Relu function, the formula is as follows:
it should be further noted that the number of active channels of N-Relu in this embodiment is twice that of the Relu before improvement, i.e. N/2 channels are only needed for N-Relu to obtain the same N feature maps, so that the number of parameters participating in calculation can be reduced by half.
And then establishing a residual error structural layer, inputting the spatial characteristics output by the convolution layer into the residual error structural layer for residual error information learning, and outputting the learned spatial characteristics.
And further establishing a result processing layer, and inputting the learned spatial features output by the residual error structural layer into the result processing layer to obtain a final fault prediction result. And finally, evaluating the accuracy of the fault prediction result.
It should be noted that, the result processing layer in this embodiment uses softmax to perform fault prediction, and unlike the SVM commonly used for multi-classification problems, the final output of softmax is probability, which is convenient for directly obtaining a fault prediction result under the smart city internet of things, and the final output of SVM is score, which cannot visually reflect the prediction condition.
Failure prediction under the smart city Internet of things in the embodiment can be abstracted to multi-classification problems, and softmax regression belongs to a multi-classification model and can be suitable for intentional prediction problems under the smart city Internet of things scene.
Based on the above embodiment, the residual error structure layer includes a first residual error connection channel and a second residual error connection channel;
residual error information learning is performed based on a first spatial feature output by the convolutional layer, and the residual error information learning method comprises the following steps:
obtaining a first residual mapping result of a first spatial feature output by the convolutional layer through the first residual connecting channel, and obtaining a second residual mapping result of the first spatial feature output by the convolutional layer through the second residual connecting channel;
and performing multiplicative flow residual error information learning on the first residual error mapping result and the first spatial characteristic, and performing additive flow residual error information learning on the second residual error mapping result and the first spatial characteristic.
Specifically, the residual error structure layer in this embodiment is a two-way residual error block structure, and is used to solve the problem that the learning of the fault information spatial feature by the conventional residual error structure is insufficient.
Referring to fig. 4, the residual structure layer of the present embodiment includes two residual connection channels, so that the entire residual block contains both multiplication information streams and addition information streams.
Specifically, the two residual connecting channels perform additive flow residual information learning according to the spatial characteristics output by the convolutional layer, and the first residual connecting channel can also perform multiplicative flow residual information learning according to the spatial characteristics output by the convolutional layer.
It should be noted that the parameter amount of the 1 × 3 convolution kernel in the present embodiment is only 1/3 of the conventional 3 × 3 convolution kernel. The parameter number of the one-dimensional residual block is also 2/3 of only one conventional residual block. Therefore, although the residual structure layer introduces multiplication information flow, compared with the traditional residual structure layer, the residual structure layer does not increase excessive parameter quantity.
In addition, under the smart city internet of things fault prediction scene, the traditional residual error structural layer can only learn the residual error information of the main information flow, and the improved residual error structural layer in the embodiment can well learn the multiplication factor while learning the residual error information.
The two paths of residual block structures enable each layer of network to obtain richer spatial characteristics of fault information data under the smart city Internet of things.
The two-way residual block proposed by this embodiment can be defined as:
y i ＝x i ×F 1 ([x i ,K i ])+(F 2 ([x i ,W i ])+x i )
(2)
wherein x is i Input vector, y, representing a residual structure layer i Representing the output vector, function F 1 ([x i ,K i ]) And F 2 ([x i ,W i ]) Representing a residual mapping.
Based on the above embodiment, the evaluating the prediction accuracy of the fault prediction model based on the fault prediction result includes:
acquiring the feature number of feature data information, selecting a target feature based on the feature number of the feature data information, and acquiring a data value corresponding to the target feature based on the fault prediction result;
and acquiring a state data value of the intelligent city Internet of things of the target characteristic at the target moment, and evaluating the prediction accuracy of the fault prediction model by combining the characteristic number and the data value corresponding to the target characteristic.
Specifically, the present embodiment provides a specific process for evaluating the accuracy of the failure prediction result. After the fault prediction result of the model is obtained, the accuracy of the model is measured by using Root Mean Square Error (RMSE). As shown in the following equation:
wherein n represents the feature number of data acquisition, namely the feature number of feature data information;
the data value of the ith characteristic representing the predicted output of the model, namely the data value corresponding to the target characteristic,
and representing a real data value of the ith characteristic at the moment t, namely the state data value of the internet of things of the smart city of the target characteristic at the target moment. As can be seen from the definition of the above equation, a smaller RMSE indicates a higher model accuracy.
Based on the above embodiment, after performing residual error information learning based on the first spatial feature output by the convolutional layer and outputting the second spatial feature of the feature data information, the method further includes:
performing batch normalization processing on the second spatial features of the feature data information and inputting the second spatial features into the result processing layer;
the obtaining, by the result processing layer, a fault prediction result of feature data information based on the second spatial feature output by the residual error structural layer includes:
and obtaining a fault prediction result of the characteristic data information through the result processing layer based on the second spatial characteristics after batch normalization processing.
In particular, the model is difficult to train if the neural network trains for too long or the network is too deep during the training process. Therefore, in the embodiment, batch normalization processing is performed on the second spatial features of the feature data information, and the spatial features after normalization processing are input to the result processing layer, so that the fault prediction result is obtained, and the model training efficiency is improved.
The fault prediction device for the internet of things of the smart city provided by the invention is described below, and the fault prediction device for the internet of things of the smart city described below and the fault prediction method for the internet of things of the smart city described above can be referred to correspondingly.
Referring to fig. 5, the invention further provides a fault prediction device for the internet of things of the smart city, which includes:
the obtaining module 510 is configured to obtain network data to be predicted of the smart city internet of things device;
the prediction module 520 is configured to input the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
Based on the above embodiment, the training process of the fault prediction model includes the following modules:
the training set acquisition module is used for acquiring characteristic data information of the smart city Internet of things equipment as a training set of the model;
the model establishing module is used for establishing an initial fault prediction model, inputting the characteristic data information into the initial fault prediction model to obtain a fault prediction result of a characteristic vector and evaluating the prediction accuracy based on the fault prediction result;
and the training module is used for carrying out iterative update on the initial fault prediction model, adjusting model parameters of the initial fault prediction model until the error value between the fault prediction result and the prediction label meets a preset threshold value, and obtaining the trained fault prediction model when the prediction accuracy reaches a target value.
Based on the above embodiments, the model building module is specifically configured to:
establishing an initial fault prediction model, wherein the initial fault prediction model comprises a convolution layer, a residual error structural layer and a result processing layer;
the convolutional layer is used for extracting spatial feature information of input feature data information based on the convolutional layer and acquiring a first spatial feature by combining an excitation function of the convolutional layer;
wherein the convolutional layer is built based on a convolutional decomposition operation;
the residual error structural layer is used for learning residual error information based on the first spatial feature output by the convolutional layer and outputting a second spatial feature of the feature data information;
the result processing layer is used for obtaining a fault prediction result of the characteristic data information based on the second spatial characteristics output by the residual error structural layer;
and evaluating the prediction accuracy of the fault prediction model based on the fault prediction result.
Based on the above embodiment, the residual structural layer includes a first residual connecting channel and a second residual connecting channel;
the residual structural layer is specifically used for:
obtaining a first residual mapping result of a first spatial feature output by the convolutional layer through the first residual connecting channel, and obtaining a second residual mapping result of the first spatial feature output by the convolutional layer through the second residual connecting channel;
and performing multiplicative flow residual error information learning on the first residual error mapping result and the first spatial characteristic, and performing additive flow residual error information learning on the second residual error mapping result and the first spatial characteristic.
Based on the above embodiments, the training module is specifically configured to:
acquiring the feature number of feature data information, selecting a target feature based on the feature number of the feature data information, and acquiring a data value corresponding to the target feature based on the fault prediction result;
and acquiring a state data value of the intelligent city Internet of things of the target characteristic at the target moment, and evaluating the prediction accuracy of the fault prediction model by combining the characteristic number and the data value corresponding to the target characteristic.
Based on the above embodiment, the model building module is further configured to:
performing batch normalization processing on second spatial features of the feature data information and inputting the second spatial features into the result processing layer;
and obtaining a fault prediction result of the characteristic data information through the result processing layer based on the second spatial characteristics after batch normalization processing.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform a smart city internet of things oriented fault prediction method comprising:
acquiring network data to be predicted of smart city Internet of things equipment;
inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
In addition, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present invention further provides a computer program product, where the computer program product includes a computer program, the computer program may be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, a computer is capable of executing the method for predicting the fault of the smart city internet of things provided by the foregoing methods, and the method includes:
acquiring network data to be predicted of smart city Internet of things equipment;
inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the method for predicting the smart city internet of things-oriented fault provided by the above methods, the method including:
acquiring network data to be predicted of smart city Internet of things equipment;
inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A fault prediction method for the Internet of things of a smart city is characterized by comprising the following steps:
acquiring network data to be predicted of smart city Internet of things equipment;
inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
2. The smart city internet of things-oriented fault prediction method according to claim 1, wherein the training method of the fault prediction model comprises the following steps:
acquiring characteristic data information of smart city Internet of things equipment as a training set of a model;
establishing an initial fault prediction model, inputting the characteristic data information into the initial fault prediction model to obtain a fault prediction result of a characteristic vector, and evaluating prediction accuracy based on the fault prediction result;
and iteratively updating the initial fault prediction model, and adjusting model parameters of the initial fault prediction model until the error value between the fault prediction result and the prediction label meets a preset threshold value, and the prediction accuracy reaches a target value to obtain the trained fault prediction model.
3. The smart city internet of things-oriented fault prediction method according to claim 2, wherein the establishing of an initial fault prediction model, inputting the feature data information into the initial fault prediction model, obtaining a fault prediction result of a feature vector and evaluating prediction accuracy based on the fault prediction result comprises:
establishing an initial fault prediction model, wherein the initial fault prediction model comprises a convolution layer, a residual error structural layer and a result processing layer;
the convolutional layer is used for extracting spatial feature information of input feature data information based on the convolutional layer and acquiring a first spatial feature by combining an excitation function of the convolutional layer;
wherein the convolutional layer is built based on a convolutional decomposition operation;
the residual error structural layer is used for learning residual error information based on the first spatial feature output by the convolutional layer and outputting a second spatial feature of the feature data information;
the result processing layer is used for obtaining a fault prediction result of the characteristic data information based on the second spatial characteristics output by the residual error structural layer;
and evaluating the prediction accuracy of the fault prediction model based on the fault prediction result.
4. The smart city internet of things-oriented fault prediction method according to claim 3, wherein the residual error structural layer comprises a first residual error connection channel and a second residual error connection channel;
residual error information learning is performed based on a first spatial feature output by the convolutional layer, and the residual error information learning method comprises the following steps:
obtaining a first residual mapping result of a first spatial feature output by the convolutional layer through the first residual connecting channel, and obtaining a second residual mapping result of the first spatial feature output by the convolutional layer through the second residual connecting channel;
and performing multiplicative flow residual error information learning on the first residual error mapping result and the first spatial characteristic, and performing additive flow residual error information learning on the second residual error mapping result and the first spatial characteristic.
5. The smart city internet of things-oriented fault prediction method according to claim 3, wherein the evaluating the prediction accuracy of the fault prediction model based on the fault prediction result comprises:
acquiring the feature number of feature data information, selecting a target feature based on the feature number of the feature data information, and acquiring a data value corresponding to the target feature based on the fault prediction result;
and acquiring a state data value of the intelligent city Internet of things of the target characteristics at the target moment, and evaluating the prediction accuracy of the fault prediction model by combining the characteristic number and the data value corresponding to the target characteristics.
6. The smart city internet of things-oriented fault prediction method according to claim 3, wherein after residual error information learning is performed based on the first spatial feature output by the convolutional layer and the second spatial feature of the feature data information is output, the method further comprises:
performing batch normalization processing on the second spatial features of the feature data information and inputting the second spatial features into the result processing layer;
the obtaining, by the result processing layer, a fault prediction result of feature data information based on the second spatial feature output by the residual error structural layer includes:
and obtaining a fault prediction result of the characteristic data information through the result processing layer based on the second spatial characteristics after batch normalization processing.
7. The utility model provides a fault prediction device towards wisdom city thing networking which characterized in that includes:
the acquisition module is used for acquiring network data to be predicted of the smart city Internet of things equipment;
the prediction module is used for inputting the network data into a trained fault prediction model to obtain a fault prediction result of the network data;
the fault prediction model is established based on convolution decomposition operation and an improved residual error network structure, and is obtained by training by taking characteristic data information of the smart city Internet of things equipment as a training set and a prediction label corresponding to the training set.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the smart city internet of things oriented fault prediction method according to any one of claims 1 to 6.
9. A non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the method for smart city internet of things oriented fault prediction according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program when executed by a processor implements the method for smart city internet of things oriented fault prediction according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210376991.8A CN115001937B (en) | 2022-04-11 | 2022-04-11 | Smart city Internet of things-oriented fault prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210376991.8A CN115001937B (en) | 2022-04-11 | 2022-04-11 | Smart city Internet of things-oriented fault prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115001937A true CN115001937A (en) | 2022-09-02 |
| CN115001937B CN115001937B (en) | 2023-06-16 |
Family
ID=83023890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210376991.8A Active CN115001937B (en) | 2022-04-11 | 2022-04-11 | Smart city Internet of things-oriented fault prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115001937B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115580635A (en) * | 2022-09-26 | 2023-01-06 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for terminal of Internet of things |
| CN118229036A (en) * | 2024-05-23 | 2024-06-21 | 中建八局第一建设有限公司 | Operation and maintenance management system and method for smart city |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3276539A1 (en) * | 2016-07-27 | 2018-01-31 | Samsung Electronics Co., Ltd. | Accelerator in convolutional neural network and method for operating the same |
| WO2018026995A1 (en) * | 2016-08-03 | 2018-02-08 | Schlumberger Technology Corporation | Multi-scale deep network for fault detection |
| JP2018112852A (en) * | 2017-01-11 | 2018-07-19 | 安川情報システム株式会社 | Fault prediction method, fault prediction device and fault prediction program |
| CN110390275A (en) * | 2019-07-04 | 2019-10-29 | 淮阴工学院 | A kind of gesture classification method based on transfer learning |
| WO2019233244A1 (en) * | 2018-06-08 | 2019-12-12 | 腾讯科技（深圳）有限公司 | Image processing method and apparatus, and computer readable medium, and electronic device |
| CN110798417A (en) * | 2019-10-24 | 2020-02-14 | 北京邮电大学 | Signal modulation identification method and device based on cyclic residual error network |
| WO2020215676A1 (en) * | 2019-04-26 | 2020-10-29 | 平安科技（深圳）有限公司 | Residual network-based image identification method, device, apparatus, and storage medium |
| CN112381775A (en) * | 2020-11-06 | 2021-02-19 | 厦门市美亚柏科信息股份有限公司 | Image tampering detection method, terminal device and storage medium |
| CN112910695A (en) * | 2021-01-22 | 2021-06-04 | 湖北工业大学 | Network fault prediction method based on global attention time domain convolutional network |
| CN112953629A (en) * | 2021-03-16 | 2021-06-11 | 北京邮电大学 | Method and system for analyzing uncertainty of optical network fault prediction |
| CN113783717A (en) * | 2021-08-12 | 2021-12-10 | 北京邮电大学 | Smart city network flow prediction method and system |
| CN113923123A (en) * | 2021-09-24 | 2022-01-11 | 天津大学 | Underwater wireless sensor network topology control method based on deep reinforcement learning |
| CN114186500A (en) * | 2022-02-16 | 2022-03-15 | 华中科技大学 | Marine bearing residual life prediction method based on transfer learning and multiple time windows |
-
2022
- 2022-04-11 CN CN202210376991.8A patent/CN115001937B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3276539A1 (en) * | 2016-07-27 | 2018-01-31 | Samsung Electronics Co., Ltd. | Accelerator in convolutional neural network and method for operating the same |
| WO2018026995A1 (en) * | 2016-08-03 | 2018-02-08 | Schlumberger Technology Corporation | Multi-scale deep network for fault detection |
| JP2018112852A (en) * | 2017-01-11 | 2018-07-19 | 安川情報システム株式会社 | Fault prediction method, fault prediction device and fault prediction program |
| WO2019233244A1 (en) * | 2018-06-08 | 2019-12-12 | 腾讯科技（深圳）有限公司 | Image processing method and apparatus, and computer readable medium, and electronic device |
| WO2020215676A1 (en) * | 2019-04-26 | 2020-10-29 | 平安科技（深圳）有限公司 | Residual network-based image identification method, device, apparatus, and storage medium |
| CN110390275A (en) * | 2019-07-04 | 2019-10-29 | 淮阴工学院 | A kind of gesture classification method based on transfer learning |
| CN110798417A (en) * | 2019-10-24 | 2020-02-14 | 北京邮电大学 | Signal modulation identification method and device based on cyclic residual error network |
| CN112381775A (en) * | 2020-11-06 | 2021-02-19 | 厦门市美亚柏科信息股份有限公司 | Image tampering detection method, terminal device and storage medium |
| CN112910695A (en) * | 2021-01-22 | 2021-06-04 | 湖北工业大学 | Network fault prediction method based on global attention time domain convolutional network |
| CN112953629A (en) * | 2021-03-16 | 2021-06-11 | 北京邮电大学 | Method and system for analyzing uncertainty of optical network fault prediction |
| CN113783717A (en) * | 2021-08-12 | 2021-12-10 | 北京邮电大学 | Smart city network flow prediction method and system |
| CN113923123A (en) * | 2021-09-24 | 2022-01-11 | 天津大学 | Underwater wireless sensor network topology control method based on deep reinforcement learning |
| CN114186500A (en) * | 2022-02-16 | 2022-03-15 | 华中科技大学 | Marine bearing residual life prediction method based on transfer learning and multiple time windows |
Non-Patent Citations (5)
| Title |
|---|
| LANLAN RUI等: "Data clustering-based fault detection in WSNs", 2015 SEVENTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE (ICACI), pages 334 - 336 * |
| LEI WANG等: "Human Action Recognition by Learning Spatio-Temporal Features With DNNs", DIGITAL OBJECT IDENTIFIER 10.1109/ACCESS., pages 17913 - 17917 * |
| 孟洛明: "支持向量机回归预测在网络故障检测中的应用", 北京邮电大学学报, vol. 37, no. 4, pages 24 - 27 * |
| 王有元;李后英;梁玄鸿;李昀琪;蔚超;陆云才;: "基于红外图像的变电设备热缺陷自调整残差网络诊断模型", 高电压技术, vol. 46, no. 09, pages 1 - 2 * |
| 芮兰兰等: "基于组合模型的短时交通流量预测算法", 《电 子 与 信 息 学 报》, vol. 38, no. 5, pages 1228 - 1232 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115580635A (en) * | 2022-09-26 | 2023-01-06 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for terminal of Internet of things |
| CN115580635B (en) * | 2022-09-26 | 2023-06-13 | 广州健新科技有限责任公司 | Intelligent fault diagnosis method and system for Internet of things terminal |
| CN118229036A (en) * | 2024-05-23 | 2024-06-21 | 中建八局第一建设有限公司 | Operation and maintenance management system and method for smart city |
| CN118229036B (en) * | 2024-05-23 | 2024-08-16 | 中建八局第一建设有限公司 | Operation and maintenance management system and method for smart city |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115001937B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11270190B2 (en) | Method and apparatus for generating target neural network structure, electronic device, and storage medium | |
| CN111242282B (en) | Deep learning model training acceleration method based on end edge cloud cooperation | |
| CN109990790B (en) | Unmanned aerial vehicle path planning method and device | |
| CN112181666A (en) | Method, system, equipment and readable storage medium for equipment evaluation and federal learning importance aggregation based on edge intelligence | |
| CN115001937A (en) | Fault prediction method and device for smart city Internet of things | |
| CN112069903B (en) | Method and device for realizing face recognition end edge unloading calculation based on deep reinforcement learning | |
| CN110138595A (en) | Time link prediction technique, device, equipment and the medium of dynamic weighting network | |
| CN113194493B (en) | Wireless network data missing attribute recovery method and device based on graph neural network | |
| CN113536081B (en) | Data center data management method and system based on artificial intelligence | |
| CN111191918A (en) | Service route planning method and device for smart power grid communication network | |
| CN111079780A (en) | Training method of space map convolution network, electronic device and storage medium | |
| CN111695696A (en) | Method and device for model training based on federal learning | |
| CN115186821A (en) | Core particle-oriented neural network inference overhead estimation method and device and electronic equipment | |
| CN114511042A (en) | Model training method and device, storage medium and electronic device | |
| CN111224905A (en) | Multi-user detection method based on convolution residual error network in large-scale Internet of things | |
| CN115758643A (en) | Network flow prediction method and device based on temporal-spatial feature fusion and storage medium | |
| CN115359334A (en) | Training method of multi-task learning deep network and target detection method and device | |
| CN117914690A (en) | Edge node network fault prediction method based on deep learning GCN-LSTM | |
| CN113850669A (en) | User grouping method and device, computer equipment and computer readable storage medium | |
| CN113825165B (en) | 5G slice network congestion early warning method and device based on time diagram network | |
| CN117853596A (en) | Unmanned aerial vehicle remote sensing mapping method and system | |
| CN111464327A (en) | Spatial information network survivability evaluation method based on graph convolution network | |
| CN114445692B (en) | Image recognition model construction method and device, computer equipment and storage medium | |
| CN116827685A (en) | Dynamic defense strategy method of micro-service system based on deep reinforcement learning | |
| CN116362894A (en) | Multi-objective learning method, multi-objective learning device, electronic equipment and computer readable storage medium |
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 |