CN108184242A - A kind of wireless sensor network abnormal deviation data examination method - Google Patents
A kind of wireless sensor network abnormal deviation data examination method Download PDFInfo
- Publication number
- CN108184242A CN108184242A CN201711439910.XA CN201711439910A CN108184242A CN 108184242 A CN108184242 A CN 108184242A CN 201711439910 A CN201711439910 A CN 201711439910A CN 108184242 A CN108184242 A CN 108184242A
- Authority
- CN
- China
- Prior art keywords
- network
- layer
- data
- node
- output
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- 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
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a kind of wireless sensor network abnormal deviation data examination methods, are first directed to sensor data stream, then it are normalized and the solution of confidence interval；Then by treated, sample data divides as required, generates training set and test set；After BP neural network is established, network training is carried out to ready-portioned sample data and utilizes emulation tool graphing；Finally, judge whether data flow is fallen into confidence interval, if falling into the section, for normal value；Otherwise, it is exceptional value.Method proposed by the present invention utilizes nearest historical data window training neural network, forecasts the measurement value sensor of subsequent time, and provide a prediction interval.Judge whether data are abnormal according to whether actual measured value falls into prediction interval.The advantage of this method is data-driven, without establishing the mechanism model of process in advance；Meanwhile this method, using nearest local data, operand is smaller, available for on-line checking.
Description
Technical field
The present invention relates to network signal transmission field, a kind of wireless sensor network abnormal deviation data examination method.
Background technology
With the progress of the communication technology, embedding assembly technology and sensor technology, there is sensing capability, calculate energy
The sensor network of power and communication capacity increasingly shows wide application prospect.Wireless sensor network comprehensively utilizes sensor
Technology, embedding assembly technology, distributed information processing and the communication technology, can monitor, perceive and acquire network in real time
Various environmental informations in distributed areas, and these information are handled, and send it to the user for needing these information,
To make scientific and reasonable decision；When wireless network sensor exception, real-time and efficiently detect in sensor network
Abnormal data, no matter the health monitoring for the pre-alarm and prevention of external accident or for sensor network in itself,
All have a very important significance.
Invention content
It is an object of the present invention to provide a kind of wireless sensor network abnormal deviation data examination methods, convenient, fast, convenient for behaviour
Make, on-line checking.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention is：
A kind of wireless sensor network abnormal deviation data examination method, this method sequence are：It is first directed to sensor data stream,
Then it is normalized and the solution of confidence interval；Then by treated, sample data divides as required,
Generate training set and test set；After BP neural network is established, network training is carried out to ready-portioned sample data and is utilized imitative
True tool graphing；Finally, judge whether data flow is fallen into confidence interval, if falling into the section, for normal value；It is no
Then, it is exceptional value.
Preferably, the BP neural network is established：BP neural network is a kind of multilayer feedforward network, by inputting
Layer, hidden layer and output layer composition；Between layers using totally interconnected mode, with there is no any coupling in node layer.Input letter
It number is transmitted through each hidden layer node successively from input layer, output node is then passed to, under the influence of the output only of each node layer
The output of one node layer；The element characteristics of node is linear, the temperature of the input layer respective sensor node acquisition of network sometimes
Value, network output layer output node number are 11, are corresponding with, state without exception；According to designed network requirement, then determine hidden
Number containing neuron in layer and hidden layer.
Preferably, the BP neural network establishment step is：
Step 1：The foundation of network is realized using newff functions；
Step 2：The initialization of network is realized using init functions；
Step 3：Network training is realized by train functions；
Step 4：Network simulation is realized by sim functions.
The beneficial effects of the invention are as follows：
Method proposed by the present invention utilizes nearest historical data window training neural network, forecasts the sensing of subsequent time
Device measured value, and provide a prediction interval.Judge whether data are abnormal according to whether actual measured value falls into prediction interval.
The advantage of this method is data-driven, without establishing the mechanism model of process in advance；Meanwhile this method utilizes nearest office
Portion's data, operand is smaller, available for on-line checking.
Description of the drawings
The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
Fig. 1 is wireless sensor network abnormal deviation data examination method overhaul flow chart of the present invention.
Fig. 2 is BP neural network structure chart of the present invention.
Specific embodiment
The embodiment of the present invention is described in detail below in conjunction with attached drawing, but the present invention can be defined by the claims
It is applied with the multitude of different ways of covering.
As shown in Figure 1, the invention discloses a kind of wireless sensor network abnormal deviation data examination method, this method sequence
For：Sensor data stream is first directed to, then it is normalized and the solution of confidence interval；Then by treated
Sample data is divided as required, generates training set and test set；After BP neural network is established, to ready-portioned sample number
According to progress network training and utilize emulation tool graphing；Finally, judge whether data flow is fallen into confidence interval, if falling into
Then it is normal value in the section；Otherwise, it is exceptional value.
Preferably, the BP neural network is established：BP neural network is a kind of multilayer feedforward network, by inputting
Layer, hidden layer and output layer composition；Between layers using totally interconnected mode, with there is no any coupling in node layer.Input letter
It number is transmitted through each hidden layer node successively from input layer, output node is then passed to, under the influence of the output only of each node layer
The output of one node layer；The element characteristics of node is linear, the temperature of the input layer respective sensor node acquisition of network sometimes
Value, network output layer output node number are 11, are corresponding with, state without exception；According to designed network requirement, then determine hidden
Number containing neuron in layer and hidden layer.
Preferably, the BP neural network establishment step is：
Step 1：The foundation of network is realized using newff functions；
Step 2：The initialization of network is realized using init functions；
Step 3：Network training is realized by train functions；
Step 4：Network simulation is realized by sim functions.
The embodiments of the present invention described above are not intended to limit the scope of the present invention.It is any in the present invention
Spirit and principle within the modifications, equivalent substitutions and improvements made etc., should be included in the claim protection model of the present invention
Within enclosing.
Claims (3)
1. a kind of wireless sensor network abnormal deviation data examination method, which is characterized in that this method sequence be：It is first directed to sensing
Device data flow, is then normalized it and the solution of confidence interval；Then will treated sample data as required
It is divided, generates training set and test set；After BP neural network is established, network training is carried out to ready-portioned sample data
And utilize emulation tool graphing；Finally, judge whether data flow is fallen into confidence interval, if falling into the section, for
Normal value；Otherwise, it is exceptional value.
2. wireless sensor network abnormal deviation data examination method according to claim 1, which is characterized in that the BP nerve nets
Network is established：BP neural network is a kind of multilayer feedforward network, is made of input layer, hidden layer and output layer；Layer and layer
Between using totally interconnected mode, with there is no any coupling in node layer.Input signal is transmitted through each implicit successively from input layer
Node layer is then passed to output node, the output of a node layer under the influence of the output only of each node layer；The element characteristics of node
Sometimes it is linear, the temperature value of the input layer respective sensor node acquisition of network, network output layer output node number is 11,
It is corresponding with, state without exception；According to designed network requirement, then determine the number of neuron in hidden layer and hidden layer.
3. wireless sensor network abnormal deviation data examination method according to claim 2, which is characterized in that the BP nerve nets
Network establishment step is：
Step 1：The foundation of network is realized using newff functions；
Step 2：The initialization of network is realized using init functions；
Step 3：Network training is realized by train functions；
Step 4：Network simulation is realized by sim functions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711439910.XA CN108184242A (en) | 2017-12-27 | 2017-12-27 | A kind of wireless sensor network abnormal deviation data examination method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711439910.XA CN108184242A (en) | 2017-12-27 | 2017-12-27 | A kind of wireless sensor network abnormal deviation data examination method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108184242A true CN108184242A (en) | 2018-06-19 |
Family
ID=62547416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711439910.XA Pending CN108184242A (en) | 2017-12-27 | 2017-12-27 | A kind of wireless sensor network abnormal deviation data examination method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108184242A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109743103A (en) * | 2019-02-01 | 2019-05-10 | 福州大学 | FBG sensing network node fault repairing method based on ELM |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103840988A (en) * | 2014-03-17 | 2014-06-04 | 湖州师范学院 | Network traffic measurement method based on RBF neural network |
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
-
2017
- 2017-12-27 CN CN201711439910.XA patent/CN108184242A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103840988A (en) * | 2014-03-17 | 2014-06-04 | 湖州师范学院 | Network traffic measurement method based on RBF neural network |
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109743103A (en) * | 2019-02-01 | 2019-05-10 | 福州大学 | FBG sensing network node fault repairing method based on ELM |
| CN109743103B (en) * | 2019-02-01 | 2021-07-27 | 福州大学 | FBG sensing network node fault repairing method based on ELM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101799367B (en) | Electromechanical device neural network failure trend prediction method | |
| CN103268519B (en) | Based on the power-system short-term load forecasting method and the device that improve Lyapunov index | |
| CN109635483A (en) | A kind of motor and failure of pump hypothesis analysis system based on electromagnetic detection | |
| CN101477340B (en) | Progressive health monitoring method for cable system in cable structure based on cable force monitoring | |
| CN109213121A (en) | A kind of fan braking system card cylinder method for diagnosing faults | |
| Abraham et al. | Real time conversion of sign language to speech and prediction of gestures using Artificial Neural Network | |
| CN110469561A (en) | A kind of device of Hydraulic State Monitoring System, method and system | |
| CN117517907B (en) | Insulation state monitoring method and system for transformer substation capacitive equipment | |
| CN105182141A (en) | Transformer fault detection method and system | |
| CN105242231B (en) | Digitalized electric energy metering performance detects and source tracing method and closed-loop system | |
| Rosso et al. | Review on deep learning in structural health monitoring | |
| CN103994334A (en) | Oil transportation pipeline leakage flow estimating device and method based on KPCA-RBF curve fitting | |
| CN110266784A (en) | A kind of intelligent plant data acquisition management system interacted | |
| CN105488335A (en) | Lyapunov exponent based power system load prediction method and apparatus | |
| Li et al. | Tailings pond risk prediction using long short-term memory networks | |
| CN117892921A (en) | Intelligent water affair comprehensive management system and method based on big data | |
| CN108184242A (en) | A kind of wireless sensor network abnormal deviation data examination method | |
| CN104578412B (en) | A kind of detection method of the condition detecting system based on big data technology | |
| CN109215821A (en) | Nuclear power plant evaporator main feedwater flow redundant measurement channel comparative approach and system | |
| CN108535033A (en) | Virtual-sensor and its health monitoring intelligent decision system | |
| CN115758561A (en) | Method for generating flight simulation parameter data of airplane | |
| CN109213119A (en) | Complex industrial critical component failure prediction method and system based on on-line study | |
| CN109029711A (en) | A kind of multistage frequency discrimination methods of dynamic bridge structure | |
| Łęczycki et al. | Extended sensor reliability evaluation method in multi-sensor control systems | |
| CN206115231U (en) | Synthesize reliability test safety monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180619 |
|
| RJ01 | Rejection of invention patent application after publication |