CN110942401B - Intelligent communication method for electric power Internet of things - Google Patents
Intelligent communication method for electric power Internet of things Download PDFInfo
- Publication number
- CN110942401B CN110942401B CN201911150021.0A CN201911150021A CN110942401B CN 110942401 B CN110942401 B CN 110942401B CN 201911150021 A CN201911150021 A CN 201911150021A CN 110942401 B CN110942401 B CN 110942401B
- Authority
- CN
- China
- Prior art keywords
- things
- electric power
- intelligent communication
- power internet
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000013528 artificial neural network Methods 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 47
- 238000012360 testing method Methods 0.000 claims abstract description 36
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 230000003321 amplification Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 6
- 230000005611 electricity Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
Abstract
The invention discloses an intelligent communication method of an electric power Internet of things, and relates to an intelligent communication method of the electric power Internet of things. The invention aims to solve the problem of low accuracy of intelligent communication data transmission of the existing electric power Internet of things. The process is as follows: 1. collecting the intelligent communication data set of the electric power Internet of things as a data set, taking 70% of the data set as a training set and the rest 30% as a test set; 2. establishing a BP neural network; 3. obtaining trained BP neural network and parameters; 4. inputting a test sample into the trained BP neural network for testing, obtaining a final trained BP neural network, and if the test sample does not reach the test precision, repeating the third step until the test precision is met, and obtaining the final trained BP neural network; 5. and obtaining whether the intelligent communication data of the electric power Internet of things to be detected are correct or not, and giving an alarm if the intelligent communication data of the electric power Internet of things to be detected are wrong. The method is used in the field of intelligent communication of the electric power Internet of things.
Description
Technical Field
The invention relates to an intelligent communication method of an electric power Internet of things.
Background
In 2011, the national network company has proposed the electricity information of residents for each power-saving company, and the electric energy data of each station realizes the requirements of full coverage and full collection. According to the requirements of the national network companies, the provinces and the companies need to gradually strengthen the control force of various stations, and comprehensively understand the real-time data information such as the electricity generation quantity, the electricity selling quantity, the power supply reliability and the like so as to be beneficial to comprehensively grasping the operation conditions of various power companies.
The electric power internet of things is a network which is connected with various terminals through intelligent sensors to realize communication between the terminals. The power, bandwidth, energy, memory and the like of the terminal equipment of the electric power Internet of things are limited. The terminal perceives and collects data from the surrounding environment, the data are firstly transmitted to the base station and then forwarded to the Internet by the base station, and further communication between the terminal and the terminal or between the terminal and the data center is achieved. The increasing number of terminals in the internet of things and the data traffic demands of services based on the internet of things require more reliable network technologies.
Along with the rapid development of the electric power Internet of things, the requirements of the electric power industry on informatization and intellectualization are increasingly improved, the data of the electric power Internet of things system is huge in data scale and high in updating speed, intelligent communication of the electric power Internet of things is transmitted through the data, but when the electric power Internet of things system fails, errors exist in the data transmitted by the intelligent communication of the electric power Internet of things, so that fault diagnosis of the electric power Internet of things system is extremely important, namely, fault elements are timely and effectively determined by utilizing alarm information generated after the occurrence of the faults, an auxiliary decision is provided for a dispatcher to rapidly identify the faults, the faults are helped to be removed as soon as possible, normal operation of the electric power Internet of things system is recovered, and accurate transmission of the intelligent communication data of the electric power Internet of things is ensured.
Disclosure of Invention
The invention aims to solve the problem of low accuracy of data transmission of the existing intelligent communication of the electric power Internet of things, and provides an intelligent communication method of the electric power Internet of things.
The intelligent communication method of the electric power Internet of things comprises the following specific processes:
firstly, collecting an intelligent communication data set of the electric power Internet of things as a data set, taking 70% of the data set as a training set and the rest 30% as a test set, wherein the intelligent communication data of the electric power Internet of things comprises voltage, power and load;
step two, establishing a BP neural network;
step three, inputting a training sample into the BP neural network established in the step two for training to obtain a trained BP neural network and parameters;
inputting a test sample into the trained BP neural network for testing, obtaining the final trained BP neural network, and if the test sample does not reach the test precision, repeating the third step until the test precision is met, and obtaining the final trained BP neural network;
and fifthly, carrying out normalization processing on the intelligent communication data of the electric power Internet of things to be detected, inputting the intelligent communication data into the finally trained BP neural network to obtain whether the intelligent communication data of the electric power Internet of things to be detected are correct or not, and giving an alarm if the intelligent communication data of the electric power Internet of things to be detected are wrong.
Further, in the first step, an intelligent communication data set of the electric power internet of things is collected as a data set, 70% of the data set is used as a training set, the rest 30% is used as a test set, and the intelligent communication data of the electric power internet of things comprises voltage, power and load; the specific process is as follows:
the method comprises the following steps: establishing an intelligent communication data set of the electric power Internet of things;
acquiring intelligent communication data of the electric power Internet of things in a fault-free state and intelligent communication data of the electric power Internet of things in various faults, and establishing an intelligent communication data set of the electric power Internet of things;
step two: performing data amplification operation on the intelligent communication data set of the electric power internet of things, which is established in the step one by one;
step one, three: marking the amplified intelligent communication data of the electric power Internet of things:
adopting a multi-tag classification data set, wherein the multi-tag comprises intelligent communication data of the electric power Internet of things in a fault-free state and intelligent communication data of the electric power Internet of things in various faults;
step four: carrying out normalization processing on the marked intelligent communication data of the electric power Internet of things to obtain a data set;
70% of the dataset was used as training set and the remaining 30% was used as test set.
Further, establishing a BP neural network in the second step; the specific process is as follows:
the BP neural network is set to be of an 11-layer topological structure, and the network structure of the BP neural network comprises a 1-layer input layer, a 3-layer convolution layer, a 3-layer pooling layer, a 2-layer full connection layer, a 1-layer classification layer and a 1-layer output layer;
determining initial parameters of the BP neural network, namely determining initial parameters of an input layer, a convolution layer, a pooling layer, a full connection, a classification layer, an output layer, a learning rate, a connection weight and bias of the BP neural network;
the input layer size is 16, the output layer size is 8, the learning rate is 0.08, and the bias is 0;
the average value of the connection weight is 0, and the variance is 0.01;
the convolution kernel sizes of the convolution layers are 3*1, the number of the convolution kernels is 30, and the number of the convolution kernels is represented by the multiplication number.
Further, training the BP neural network in the third step to obtain a trained BP neural network and parameters; the specific process is as follows:
and inputting the training sample into the BP neural network for training, setting the iteration times and the training accuracy, wherein the iteration times are 500, the training accuracy is 95%, and stopping training when the training accuracy reaches 95% or the iteration times reach 500, so as to obtain the trained convolutional neural network and parameters.
Further, the training samples are input into the BP neural network for training, and a cross entropy loss function is adopted; the specific process is as follows:
let the true label of a sample be y t Y of the sample t Probability of =1 is y p The cross entropy loss function of the sample is then:
log(y t |y p )=-(y t ×log(y p )+(1-y t )log(1-y p ))。
in the fourth step, if the intelligent communication data of the electric power internet of things to be tested is wrong, an alarm is given; the specific process is as follows:
the alarm comprises: an alarm information receiving module and a fault area determining module;
the alarm information receiving module is used for receiving alarm information generated after the intelligent communication data error of the electric power Internet of things occurs;
and the fault area determining module is used for determining a fault area according to the alarm information.
The beneficial effects of the invention are as follows:
the method comprises the steps of collecting an intelligent communication data set of the electric power Internet of things as a data set, taking 70% of the data set as a training set and the rest 30% as a test set, wherein the intelligent communication data of the electric power Internet of things comprises voltage, power and load; establishing a BP neural network; inputting a training sample into the BP neural network established in the second step for training to obtain a trained BP neural network and parameters; inputting a test sample into the trained BP neural network for testing, obtaining a final trained BP neural network, and if the test sample does not reach the test precision, repeating the third step until the test precision is met, and obtaining the final trained BP neural network; carrying out normalization processing on intelligent communication data of the electric power Internet of things to be detected, inputting the intelligent communication data into a final trained BP neural network to obtain whether the intelligent communication data of the electric power Internet of things to be detected is correct or not, and giving an alarm if the intelligent communication data of the electric power Internet of things to be detected is wrong; the intelligent communication data transmission accuracy of the electric power Internet of things is improved;
the method comprises the steps of amplifying data set information, constructing a multi-label neural network training set, constructing a neural network model, and training the neural network model until the model converges.
According to the invention, the multi-label data set is less in false alarm than the single-label data set, the BP neural network is higher in accuracy than the common network, and finally, the machine inspection operation is realized to replace the human inspection operation, so that the labor cost of a unit can be saved, the operation quality and the operation efficiency can be improved, the intelligent communication data transmission accuracy of the electric power Internet of things is improved, and the problem of low intelligent communication data transmission accuracy of the existing electric power Internet of things is solved.
In practical application, loading the weight of the neural network, judging whether the intelligent communication data of the electric power Internet of things to be tested is fault data or not, and alarming the fault throwing data. Compared with the traditional manual detection method, the electric power Internet of things intelligent communication method based on deep learning has high flexibility, accuracy and robustness.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The first embodiment is as follows: the specific process of the intelligent communication method of the electric power Internet of things in the embodiment is as follows:
firstly, collecting an intelligent communication data set of the electric power Internet of things as a data set, taking 70% of the data set as a training set and the rest 30% as a test set, wherein the intelligent communication data of the electric power Internet of things comprises voltage, power, load and the like;
step two, establishing a BP neural network;
step three, inputting a training sample into the BP neural network established in the step two for training to obtain a trained BP neural network and parameters;
inputting a test sample into the trained BP neural network for testing, obtaining the final trained BP neural network, and if the test sample does not reach the test precision, repeating the third step until the test precision is met, and obtaining the final trained BP neural network;
and fifthly, carrying out normalization processing on the intelligent communication data of the electric power Internet of things to be detected, inputting the intelligent communication data into the finally trained BP neural network to obtain whether the intelligent communication data of the electric power Internet of things to be detected are correct or not, and giving an alarm if the intelligent communication data of the electric power Internet of things to be detected are wrong.
The second embodiment is as follows: the first step is to collect the intelligent communication data set of the electric power internet of things as the data set, wherein 70% of the data set is used as a training set, the rest 30% is used as a test set, and the intelligent communication data of the electric power internet of things comprises voltage, power, load and the like; the specific process is as follows:
the method comprises the following steps: establishing an intelligent communication data set of the electric power Internet of things;
acquiring intelligent communication data of the electric power Internet of things in a fault-free state and intelligent communication data of the electric power Internet of things in various faults, and establishing an intelligent communication data set of the electric power Internet of things;
step two: performing data amplification operation on the intelligent communication data set of the electric power internet of things, which is established in the step one by one;
step one, three: marking the amplified intelligent communication data of the electric power Internet of things:
adopting a multi-tag classification data set, wherein the multi-tag comprises intelligent communication data of the electric power Internet of things in a fault-free state and intelligent communication data of the electric power Internet of things in various faults;
step four: carrying out normalization processing on the marked intelligent communication data of the electric power Internet of things to obtain a data set;
70% of the dataset was used as training set and the remaining 30% was used as test set.
Other steps and parameters are the same as in the first embodiment.
And a third specific embodiment: the difference between the present embodiment and the first or second embodiment is that in the second step, a BP neural network is established; the specific process is as follows:
the BP neural network is set to be of an 11-layer topological structure, and the network structure of the BP neural network comprises a 1-layer input layer, a 3-layer convolution layer, a 3-layer pooling layer, a 2-layer full connection layer, a 1-layer classification layer and a 1-layer output layer;
determining initial parameters of the BP neural network, namely determining initial parameters of an input layer, a convolution layer, a pooling layer, a full connection, a classification layer, an output layer, a learning rate, a connection weight and bias of the BP neural network;
the input layer size is 16, the output layer size is 8, the learning rate is 0.08, and the bias is 0;
the average value of the connection weight is 0, and the variance is 0.01;
the convolution kernel sizes of the convolution layers are 3*1, the number of the convolution kernels is 30, and the number of the convolution kernels is represented by the multiplication number.
Other steps and parameters are the same as in the first or second embodiment.
The specific embodiment IV is as follows: the difference between the embodiment and the first to third embodiments is that the BP neural network is trained in the third step to obtain a trained BP neural network and parameters; the specific process is as follows:
and inputting the training sample into the BP neural network for training, setting the iteration times and the training accuracy, wherein the iteration times are 500, the training accuracy is 95%, and stopping training when the training accuracy reaches 95% or the iteration times reach 500, so as to obtain the trained convolutional neural network and parameters.
Other steps and parameters are the same as in one to three embodiments.
Fifth embodiment: the difference between the embodiment and the specific embodiment is that the training samples are input into the BP neural network for training, and a cross entropy loss function is adopted; the specific process is as follows:
let the true label of a sample be y t Y of the sample t Probability of =1 is y p The cross entropy loss function of the sample is then:
log(y t |y p )=-(y t ×log(y p )+(1-y t )log(1-y p ))。
other steps and parameters are the same as in one to four embodiments.
Specific embodiment six: the difference between the embodiment and the first to fifth embodiments is that in the fourth step, if the intelligent communication data of the electric power internet of things to be tested is wrong, an alarm is given; the specific process is as follows:
the alarm comprises: an alarm information receiving module and a fault area determining module;
the alarm information receiving module is used for receiving alarm information generated after the intelligent communication data error of the electric power Internet of things occurs;
and the fault area determining module is used for determining a fault area according to the alarm information.
Other steps and parameters are the same as in one of the first to fifth embodiments.
The present invention is capable of other and further embodiments and its several details are capable of modification and variation in light of the present invention, as will be apparent to those skilled in the art, without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (4)
1. An intelligent communication method of an electric power internet of things is characterized by comprising the following steps: the method comprises the following specific processes:
firstly, collecting an intelligent communication data set of the electric power Internet of things as a data set, taking 70% of the data set as a training set and the rest 30% as a test set, wherein the intelligent communication data of the electric power Internet of things comprises voltage, power and load;
step two, establishing a BP neural network;
step three, inputting a training sample into the BP neural network established in the step two for training to obtain a trained BP neural network and parameters;
inputting a test sample into the trained BP neural network for testing, obtaining the final trained BP neural network, and if the test sample does not reach the test precision, repeating the third step until the test precision is met, and obtaining the final trained BP neural network;
fifthly, carrying out normalization processing on the intelligent communication data of the electric power internet of things to be tested, inputting the intelligent communication data into a finally trained BP neural network to obtain whether the intelligent communication data of the electric power internet of things to be tested are correct or not, and alarming if the intelligent communication data of the electric power internet of things to be tested are wrong;
collecting an intelligent communication data set of the electric power Internet of things as a data set, taking 70% of the data set as a training set and the rest 30% as a test set, wherein the intelligent communication data of the electric power Internet of things comprises voltage, power and load; the specific process is as follows:
the method comprises the following steps: establishing an intelligent communication data set of the electric power Internet of things;
acquiring intelligent communication data of the electric power Internet of things in a fault-free state and intelligent communication data of the electric power Internet of things in various faults, and establishing an intelligent communication data set of the electric power Internet of things;
step two: performing data amplification operation on the intelligent communication data set of the electric power internet of things, which is established in the step one by one;
step one, three: marking the amplified intelligent communication data of the electric power Internet of things:
adopting a multi-tag classification data set, wherein the multi-tag comprises intelligent communication data of the electric power Internet of things in a fault-free state and intelligent communication data of the electric power Internet of things in various faults;
step four: carrying out normalization processing on the marked intelligent communication data of the electric power Internet of things to obtain a data set;
taking 70% of the data set as a training set and the remaining 30% as a test set;
establishing a BP neural network in the second step; the specific process is as follows:
the BP neural network is set to be of an 11-layer topological structure, and the network structure of the BP neural network comprises a 1-layer input layer, a 3-layer convolution layer, a 3-layer pooling layer, a 2-layer full connection layer, a 1-layer classification layer and a 1-layer output layer;
determining initial parameters of the BP neural network, namely determining initial parameters of an input layer, a convolution layer, a pooling layer, a full connection, a classification layer, an output layer, a learning rate, a connection weight and bias of the BP neural network;
the input layer size is 16, the output layer size is 8, the learning rate is 0.08, and the bias is 0;
the average value of the connection weight is 0, and the variance is 0.01;
the convolution kernel sizes of the convolution layers are 3*1, the number of the convolution kernels is 30, and the number of the convolution kernels is represented by the multiplication number.
2. The intelligent communication method of the electric power internet of things according to claim 1, wherein the intelligent communication method comprises the following steps: training the BP neural network to obtain a trained BP neural network and parameters; the specific process is as follows:
and inputting the training sample into the BP neural network for training, setting the iteration times and the training accuracy, wherein the iteration times are 500, the training accuracy is 95%, and stopping training when the training accuracy reaches 95% or the iteration times reach 500, so as to obtain the trained convolutional neural network and parameters.
3. The intelligent communication method of the electric power internet of things according to claim 2, wherein the intelligent communication method is characterized by comprising the following steps of: inputting the training sample into a BP neural network for training, and adopting a cross entropy loss function; the specific process is as follows:
let the true label of a sample be y t Y of the sample t Probability of =1 is y p The cross entropy loss function of the sample is then:
log(y t |y p )=-(y t ×log(y p )+(1-y t )log(1-y p ))。
4. the intelligent communication method of the electric power internet of things according to claim 3, wherein the intelligent communication method comprises the following steps: in the fourth step, if the intelligent communication data of the electric power Internet of things to be tested is wrong, an alarm is given; the specific process is as follows:
the alarm comprises: an alarm information receiving module and a fault area determining module;
the alarm information receiving module is used for receiving alarm information generated after the intelligent communication data error of the electric power Internet of things occurs;
and the fault area determining module is used for determining a fault area according to the alarm information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911150021.0A CN110942401B (en) | 2019-11-21 | 2019-11-21 | Intelligent communication method for electric power Internet of things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911150021.0A CN110942401B (en) | 2019-11-21 | 2019-11-21 | Intelligent communication method for electric power Internet of things |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110942401A CN110942401A (en) | 2020-03-31 |
CN110942401B true CN110942401B (en) | 2023-12-19 |
Family
ID=69907219
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911150021.0A Active CN110942401B (en) | 2019-11-21 | 2019-11-21 | Intelligent communication method for electric power Internet of things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110942401B (en) |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2090734A1 (en) * | 1992-02-24 | 1993-08-25 | Kiyoshi Alyfuku | Networked health care and monitoring system |
CN102063563A (en) * | 2010-12-14 | 2011-05-18 | 中国电力科学研究院 | Network-province-local integrative bus load predicting method |
WO2012018388A1 (en) * | 2010-08-03 | 2012-02-09 | Alibaba Group Holding Limited | Product recommendation system |
CN102510059A (en) * | 2011-11-28 | 2012-06-20 | 山东电力集团公司潍坊供电公司 | Super short-term wind power forecasting method based on back propagation (BP) neural network |
CN102722759A (en) * | 2012-05-17 | 2012-10-10 | 河海大学 | Method for predicting power supply reliability of power grid based on BP neural network |
CN103425743A (en) * | 2013-07-17 | 2013-12-04 | 上海金自天正信息技术有限公司 | Steam pipe network prediction system based on Bayesian neural network algorithm |
CN104978612A (en) * | 2015-01-27 | 2015-10-14 | 厦门大学 | Distributed big data system risk predicating method based on AHP-RBF |
CN106250812A (en) * | 2016-07-15 | 2016-12-21 | 汤平 | A kind of model recognizing method based on quick R CNN deep neural network |
CN107679525A (en) * | 2017-11-01 | 2018-02-09 | 腾讯科技(深圳)有限公司 | Image classification method, device and computer-readable recording medium |
CN108073917A (en) * | 2018-01-24 | 2018-05-25 | 燕山大学 | A kind of face identification method based on convolutional neural networks |
CN109255441A (en) * | 2018-10-18 | 2019-01-22 | 西安电子科技大学 | Spacecraft fault diagnosis method based on artificial intelligence |
CN109376933A (en) * | 2018-10-30 | 2019-02-22 | 成都云材智慧数据科技有限公司 | Lithium ion battery negative material energy density prediction technique neural network based |
CN109558787A (en) * | 2018-09-28 | 2019-04-02 | 浙江农林大学 | A kind of Bamboo insect pests recognition methods based on convolutional neural networks model |
CN110110426A (en) * | 2019-04-29 | 2019-08-09 | 淮阴工学院 | A kind of Switching Power Supply filter capacitor abatement detecting method |
CN110427022A (en) * | 2019-07-08 | 2019-11-08 | 武汉科技大学 | A kind of hidden fire-fighting danger detection robot and detection method based on deep learning |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9230219B2 (en) * | 2010-08-23 | 2016-01-05 | Institute Of Nuclear Energy Research Atomic Energy Council, Executive Yuan | Wind energy forecasting method with extreme wind speed prediction function |
US10902302B2 (en) * | 2018-04-23 | 2021-01-26 | International Business Machines Corporation | Stacked neural network framework in the internet of things |
-
2019
- 2019-11-21 CN CN201911150021.0A patent/CN110942401B/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2090734A1 (en) * | 1992-02-24 | 1993-08-25 | Kiyoshi Alyfuku | Networked health care and monitoring system |
WO2012018388A1 (en) * | 2010-08-03 | 2012-02-09 | Alibaba Group Holding Limited | Product recommendation system |
CN102063563A (en) * | 2010-12-14 | 2011-05-18 | 中国电力科学研究院 | Network-province-local integrative bus load predicting method |
CN102510059A (en) * | 2011-11-28 | 2012-06-20 | 山东电力集团公司潍坊供电公司 | Super short-term wind power forecasting method based on back propagation (BP) neural network |
CN102722759A (en) * | 2012-05-17 | 2012-10-10 | 河海大学 | Method for predicting power supply reliability of power grid based on BP neural network |
CN103425743A (en) * | 2013-07-17 | 2013-12-04 | 上海金自天正信息技术有限公司 | Steam pipe network prediction system based on Bayesian neural network algorithm |
CN104978612A (en) * | 2015-01-27 | 2015-10-14 | 厦门大学 | Distributed big data system risk predicating method based on AHP-RBF |
CN106250812A (en) * | 2016-07-15 | 2016-12-21 | 汤平 | A kind of model recognizing method based on quick R CNN deep neural network |
CN107679525A (en) * | 2017-11-01 | 2018-02-09 | 腾讯科技(深圳)有限公司 | Image classification method, device and computer-readable recording medium |
CN108073917A (en) * | 2018-01-24 | 2018-05-25 | 燕山大学 | A kind of face identification method based on convolutional neural networks |
CN109558787A (en) * | 2018-09-28 | 2019-04-02 | 浙江农林大学 | A kind of Bamboo insect pests recognition methods based on convolutional neural networks model |
CN109255441A (en) * | 2018-10-18 | 2019-01-22 | 西安电子科技大学 | Spacecraft fault diagnosis method based on artificial intelligence |
CN109376933A (en) * | 2018-10-30 | 2019-02-22 | 成都云材智慧数据科技有限公司 | Lithium ion battery negative material energy density prediction technique neural network based |
CN110110426A (en) * | 2019-04-29 | 2019-08-09 | 淮阴工学院 | A kind of Switching Power Supply filter capacitor abatement detecting method |
CN110427022A (en) * | 2019-07-08 | 2019-11-08 | 武汉科技大学 | A kind of hidden fire-fighting danger detection robot and detection method based on deep learning |
Non-Patent Citations (5)
Title |
---|
基于数据相关性分析的燃气-蒸汽联合循环机组传感器在线故障监测系统;李磊;司风琪;于海泉;黄郑;;工业控制计算机(12);全文 * |
机械产品智能化故障诊断技术研究现状与展望;王翔, 李伯全;机械(02);全文 * |
王坚 ; 蒋绍华 ; 陈雄 ; 程素霞 ; 姜杏辉 ; .基于油气试验车和神经网络的变压器故障诊断方法.科技创新导报.2018,(20),全文. * |
王学渊 ; 陈志刚 ; 钟新荣 ; 卢宁 ; .基于粒子群优化的SVM供水管道泄漏诊断方法.现代电子技术.2018,(07),全文. * |
陈寿宏 ; 柳馨雨 ; 马峻 ; 康怀强 ; .深度卷积神经网络胸片肺结节分类识别研究.计算机工程与应用.2018,(24),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN110942401A (en) | 2020-03-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108062571B (en) | Photovoltaic array fault diagnosis method based on differential evolution random forest classifier | |
CN110703057B (en) | Power equipment partial discharge diagnosis method based on data enhancement and neural network | |
CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
Gilanifar et al. | Multi-task logistic low-ranked dirty model for fault detection in power distribution system | |
Zaki et al. | Deep‐learning–based method for faults classification of PV system | |
CN111008641B (en) | Power transmission line tower external force damage detection method based on convolutional neural network | |
CN113505655A (en) | Bearing fault intelligent diagnosis method for digital twin system | |
CN110119397B (en) | Deep learning method for simultaneously realizing data anomaly detection and data compression | |
CN111595541A (en) | Multi-dimensional structure damage identification method based on mass vibration transmissibility data convolutional neural network processing | |
CN114048787B (en) | Method and system for intelligently diagnosing bearing fault in real time based on Attention CNN model | |
CN115980560A (en) | CNN-GRU-based high-voltage circuit breaker mechanical fault diagnosis system, method and equipment | |
CN117041029A (en) | Network equipment fault processing method and device, electronic equipment and storage medium | |
CN116956215A (en) | Fault diagnosis method and system for transmission system | |
CN113112039B (en) | Active power distribution system initial fault identification method based on time-frequency memory recurrent neural network | |
CN112763215B (en) | Multi-working-condition online fault diagnosis method based on modular federal deep learning | |
CN110942401B (en) | Intelligent communication method for electric power Internet of things | |
CN113093695A (en) | Data-driven SDN controller fault diagnosis system | |
CN116578922A (en) | Valve cooling system fault diagnosis method and device based on multichannel convolutional neural network | |
CN113092044B (en) | Rotary machine fault diagnosis method based on weighted level visible graph | |
CN113063595A (en) | Full convolution neural network rolling bearing fault identification method based on one-dimensional convolution | |
CN111539478A (en) | Intelligent diagnosis method, system and diagnosis equipment for elevator faults | |
CN111723851A (en) | Production line fault detection method | |
CN112634216B (en) | Insulator self-explosion detection method based on deep learning model | |
CN117407824B (en) | Health detection method, equipment and medium of power time synchronization device | |
CN112712106B (en) | Mechanical equipment health state identification method based on multi-view confrontation self-encoder |
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 |