CN109699021B - Agricultural Internet of things fault diagnosis method based on time weighting - Google Patents

Agricultural Internet of things fault diagnosis method based on time weighting Download PDF

Info

Publication number
CN109699021B
CN109699021B CN201811654282.1A CN201811654282A CN109699021B CN 109699021 B CN109699021 B CN 109699021B CN 201811654282 A CN201811654282 A CN 201811654282A CN 109699021 B CN109699021 B CN 109699021B
Authority
CN
China
Prior art keywords
data
sensor
time
things
agricultural internet
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
Application number
CN201811654282.1A
Other languages
Chinese (zh)
Other versions
CN109699021A (en
Inventor
黄怡宁
何金保
韩玉静
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ningbo University of Technology
Original Assignee
Ningbo University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ningbo University of Technology filed Critical Ningbo University of Technology
Priority to CN201811654282.1A priority Critical patent/CN109699021B/en
Publication of CN109699021A publication Critical patent/CN109699021A/en
Application granted granted Critical
Publication of CN109699021B publication Critical patent/CN109699021B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/04—Arrangements for maintaining operational condition

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Evolutionary Biology (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)
  • Arrangements For Transmission Of Measured Signals (AREA)

Abstract

The invention provides an agricultural Internet of things fault diagnosis method based on time weighting. The upper computer weights data time, predicts future data of the sensor, and judges the fault of the sensor through errors of the measured data and the predicted data. Because the sensor data of the agricultural Internet of things change slowly, the latest data has the highest reference value, the weight of the latest data is increased through a time weighting method, the future data is predicted, and the obtained data is accurate. The invention is simple to realize and meets the requirement of practical application.

Description

Agricultural Internet of things fault diagnosis method based on time weighting
Technical Field
The invention relates to an agricultural Internet of things fault diagnosis method based on time weighting.
Background
With the rapid development of the internet of things technology, the application of the internet of things technology in an agricultural system has a wide application prospect. Through the agricultural internet of things technology, human resources can be effectively saved, the influence of people on the farmland environment is reduced, and accurate crop environment and crop information are obtained. China is a large country for agricultural production, agriculture is the root of national economy, and agriculture has the characteristics of various objects, dispersion, wide regions and the like, so that the wireless sensor network is adopted to acquire agricultural data information, and the prospect is wide. Various fault diagnosis methods are proposed for a wireless sensor network, but the methods are suitable for being used when the sensors are dense, the errors of the measured values of the nodes in a normal state are low, and the methods are not suitable for being used under the condition of complex environment. In addition, the conventional fault diagnosis is mainly studied for specific sensors, specific networks and specific environmental requirements, and has no generality. Therefore, for agricultural internet of things fault diagnosis, the development of a wireless sensor network fault diagnosis method based on actual needs has important economic significance.
Disclosure of Invention
In view of the defects of the prior art, the invention aims to provide an agricultural internet of things fault diagnosis method based on time weighting, aiming at wireless sensors in the agricultural internet of things, the method adopts data time weighting to diagnose sensor faults, and comprises the following specific steps:
collecting the atmospheric temperature, the soil temperature, the illumination time and the atmospheric humidity through a wireless sensor, and sending data to an upper computer for storage;
step two, setting a time window length T for each sensor, and taking n data [ D ] in T1,D2,D3,…,Dn]The data are arranged according to time sequence, and the data are weighted in time, namely the data are transformed according to the following formula:
Figure GDA0003133349910000011
where i is 1,2,3, … n, obtaining time-weighted data
Figure GDA0003133349910000012
Thirdly, using the time weighted data
Figure GDA0003133349910000013
Predicting future data
Figure GDA0003133349910000014
The prediction formula is as follows:
Figure GDA0003133349910000015
step four, if the measured n +1 th data D of the wireless sensorn+1And predicted data
Figure GDA0003133349910000021
With an error greater than a threshold value theta, i.e.
Figure GDA0003133349910000022
Judging that the wireless sensor is likely to have a fault;
step five, if the sensor is judged to be possibly failed in the step four, continuously collecting the data of the wireless sensor for 2 times, judging according to the method of the step two, the step three and the step four, and if the sensor is failed for 1 time or 2 times, confirming that the sensor is failed and giving an alarm; otherwise, the sensor is confirmed to be normal without alarming.
In summary, the invention provides an agricultural internet of things fault diagnosis method based on time weighting, which weights data time, predicts future data of a sensor, and judges a fault of the sensor according to an error between actual measurement data and the predicted data. Because the sensor data of the agricultural Internet of things change slowly, the latest data has the highest reference value, the weight of the latest data is increased through a time weighting method, the future data is predicted, and the obtained data is accurate. And only 2 or more than 2 faults in the 3-time data are regarded as faults, so that false alarm can be effectively avoided. The method is simple to implement and has good operability.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with specific examples, and those skilled in the art can easily implement the embodiments disclosed in the present specification.
The invention aims to provide an agricultural Internet of things fault diagnosis method based on time weighting, aiming at wireless sensors in the agricultural Internet of things, the data time weighting is adopted to diagnose the sensor faults, the flow is shown in figure 1, and the method specifically comprises the following steps:
collecting the atmospheric temperature, the soil temperature, the illumination time and the atmospheric humidity through a wireless sensor, and sending data to an upper computer for storage;
step two, setting a time window length T for each sensor, and taking n data [ D ] in T1,D2,D3,…,Dn]The data is according toThe data are arranged according to the time sequence, the latest data is arranged at the end, and the time weighting is carried out on the data, namely the data are transformed according to the following formula:
Figure GDA0003133349910000023
where i is 1,2,3, … n, obtaining time-weighted data
Figure GDA0003133349910000024
The time window length T can be selected according to actual conditions, T is taken as 3 hours, and if the sensor data n is 9 in 3 hours, 9 data are weighted to be
Figure GDA0003133349910000031
Thirdly, using the time weighted data
Figure GDA0003133349910000032
Predicting future data
Figure GDA0003133349910000033
The prediction formula is as follows:
Figure GDA0003133349910000034
the predicted next data is
Figure GDA0003133349910000035
Step four, if the measured n +1 th data D of the wireless sensorn+1And predicted data
Figure GDA0003133349910000036
With an error greater than a threshold value theta, i.e.
Figure GDA0003133349910000037
The threshold is set according to the actual situation, and then the wireless is judgedThe sensor may fail. That is to say
Figure GDA0003133349910000038
And judging that the wireless sensor is possibly in failure.
Step five, if the sensor is judged to be possibly failed in the step four, continuously collecting the data of the wireless sensor for 2 times, judging according to the method of the step two, the step three and the step four, and if the sensor is failed for 1 time or 2 times, confirming that the sensor is failed and giving an alarm; otherwise, the sensor is confirmed to be normal without alarming.
In summary, the invention provides an agricultural internet of things fault diagnosis method based on time weighting, which weights data time, predicts future data of a sensor, and judges a fault of the sensor according to an error between actual measurement data and the predicted data. Because the sensor data of the agricultural Internet of things change slowly, the latest data has the highest reference value, the weight of the latest data is increased through a time weighting method, the future data is predicted, and the obtained data is accurate. And only 2 or more than 2 faults in the 3-time data are regarded as faults, so that false alarm can be effectively avoided. The invention effectively overcomes various defects in the prior art and has high industrial utilization value.

Claims (1)

1. A time-weighted agricultural Internet of things fault diagnosis method is used for diagnosing sensor faults by adopting data time weighting aiming at wireless sensors in the agricultural Internet of things, and is characterized in that:
collecting the atmospheric temperature, the soil temperature, the illumination time and the atmospheric humidity through a wireless sensor, and sending data to an upper computer for storage;
step two, setting a time window length T for each sensor, and taking n data [ D ] in T1,D2,D3,…,Dn]The data are arranged according to time sequence, and the data are weighted in time, namely the data are transformed according to the following formula:
Figure FDA0003133349900000011
where i is 1,2,3, …, n, obtaining time-weighted data
Figure FDA0003133349900000012
Thirdly, using the time weighted data
Figure FDA0003133349900000013
Predicting future data
Figure FDA0003133349900000014
Figure FDA0003133349900000015
The prediction formula is as follows:
Figure FDA0003133349900000016
step four, if the measured n +1 th data D of the wireless sensorn+1And predicted data
Figure FDA0003133349900000017
With an error greater than a threshold value theta, i.e.
Figure FDA0003133349900000018
Judging that the wireless sensor is likely to have a fault;
step five, if the sensor is judged to be possibly failed in the step four, continuously collecting the data of the wireless sensor for 2 times, judging according to the method of the step two, the step three and the step four, and if the sensor is failed for 1 time or 2 times, confirming that the sensor is failed and giving an alarm; otherwise, the sensor is confirmed to be normal without alarming.
CN201811654282.1A 2018-12-31 2018-12-31 Agricultural Internet of things fault diagnosis method based on time weighting Active CN109699021B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811654282.1A CN109699021B (en) 2018-12-31 2018-12-31 Agricultural Internet of things fault diagnosis method based on time weighting

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811654282.1A CN109699021B (en) 2018-12-31 2018-12-31 Agricultural Internet of things fault diagnosis method based on time weighting

Publications (2)

Publication Number Publication Date
CN109699021A CN109699021A (en) 2019-04-30
CN109699021B true CN109699021B (en) 2021-08-10

Family

ID=66232502

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811654282.1A Active CN109699021B (en) 2018-12-31 2018-12-31 Agricultural Internet of things fault diagnosis method based on time weighting

Country Status (1)

Country Link
CN (1) CN109699021B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113554224B (en) * 2021-07-20 2022-11-25 上海航天测控通信研究所 Fault diagnosis method and system combining multipoint statistics with health trend prediction

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101799367A (en) * 2010-01-27 2010-08-11 北京信息科技大学 Electromechanical device neural network failure trend prediction method
CN102324034A (en) * 2011-05-25 2012-01-18 北京理工大学 Sensor-fault diagnosing method based on online prediction of least-squares support-vector machine
CN104202765A (en) * 2014-08-26 2014-12-10 北京邮电大学 Method and device for detecting sensor faults based on distributed network
CN106709250A (en) * 2016-12-22 2017-05-24 河海大学 Data flow abnormality detection method based on parallel Kalman algorithm
CN107628036A (en) * 2016-07-19 2018-01-26 通用汽车环球科技运作有限责任公司 The detection and reconstruction of sensor fault

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4023228B2 (en) * 2002-06-19 2007-12-19 日産自動車株式会社 In-vehicle obstacle detection device
US9599531B1 (en) * 2015-12-21 2017-03-21 International Business Machines Corporation Topological connectivity and relative distances from temporal sensor measurements of physical delivery system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101799367A (en) * 2010-01-27 2010-08-11 北京信息科技大学 Electromechanical device neural network failure trend prediction method
CN102324034A (en) * 2011-05-25 2012-01-18 北京理工大学 Sensor-fault diagnosing method based on online prediction of least-squares support-vector machine
CN104202765A (en) * 2014-08-26 2014-12-10 北京邮电大学 Method and device for detecting sensor faults based on distributed network
CN107628036A (en) * 2016-07-19 2018-01-26 通用汽车环球科技运作有限责任公司 The detection and reconstruction of sensor fault
CN106709250A (en) * 2016-12-22 2017-05-24 河海大学 Data flow abnormality detection method based on parallel Kalman algorithm

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Sensor Fault Detection for Linear Continuous-Time Systems;Heng Wang;《2009 Chinese Control and Decision Conference》;20090807;1606-1610 *
基于时间加权K近邻法的无线传感网***故障诊断;赵锡恒;《计算机应用研究》;20151031;第32卷(第10期);3096-3100 *

Also Published As

Publication number Publication date
CN109699021A (en) 2019-04-30

Similar Documents

Publication Publication Date Title
CN110087207B (en) Method for reconstructing missing data of wireless sensor network
CN106231609B (en) A kind of underwater sensor network Optimization deployment method based on highest priority region
CN105792110A (en) Data fusion and intelligent searching processing method for multiple data sources
CN109699021B (en) Agricultural Internet of things fault diagnosis method based on time weighting
CN110266527B (en) Sensor node fault classification alarm method and device based on spatial correlation
CN108682140A (en) A kind of enhanced method for detecting abnormality based on compressed sensing and autoregression model
Karthik et al. Data trust model for event detection in wireless sensor networks using data correlation techniques
Ou et al. Design and implementation of anomaly condition detection in agricultural IoT platform system
CN114866975A (en) Non-blind area layout method of safety monitoring sensor
CN107371175B (en) Self-organizing network fault detection method using cooperative prediction
CN116839656A (en) Industrial field monitoring system and detection method for industrial Internet
CN107977730A (en) A kind of wind measurement method of multisensor Data Fusion technology
CN116256026B (en) Health monitoring system of multidimensional splice welding structure under dynamic service working condition
CN111738996B (en) Bridge health monitoring and early warning system based on machine learning
CN117277558A (en) Fault monitoring system and method for operation equipment of power system
CN204461495U (en) A kind of farm environment monitoring system
CN112215281A (en) Fan blade icing fault detection method
CN111475966A (en) Power electronic circuit fault diagnosis method based on digital twinning
Vacariu et al. Water parameters monitoring on a cyberwater platform
CN113077628B (en) Algorithm of composite geomagnetic vehicle detector
CN109587652B (en) Agricultural Internet of things fault diagnosis method
Dong et al. Study of RSSI accuracy for outdoor sensor localization
CN111542011B (en) Layered wireless sensor network clustering routing method based on particle swarm optimization
CN113654974A (en) Evaluation method and monitoring system for corrosion state of offshore wind power single-pile foundation
Rajasegarar et al. Sensor network implementation challenges in the great barrier reef marine environment

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
CB03 Change of inventor or designer information

Inventor after: Huang Yining

Inventor after: He Jinbao

Inventor after: Han Yujing

Inventor before: He Jinbao

CB03 Change of inventor or designer information
GR01 Patent grant
GR01 Patent grant