CN110266527B - Sensor node fault classification alarm method and device based on spatial correlation - Google Patents
Sensor node fault classification alarm method and device based on spatial correlation Download PDFInfo
- Publication number
- CN110266527B CN110266527B CN201910501493.XA CN201910501493A CN110266527B CN 110266527 B CN110266527 B CN 110266527B CN 201910501493 A CN201910501493 A CN 201910501493A CN 110266527 B CN110266527 B CN 110266527B
- Authority
- CN
- China
- Prior art keywords
- sensor
- data
- value
- sensors
- judging whether
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0681—Configuration of triggering conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- 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
Abstract
The invention relates to a sensor node fault classification alarm method and device based on spatial correlation, wherein the method comprises the following steps: step S1: acquiring data of each sensor to obtain a sensor data column; step S2: estimating the true value of each sensor in a circulating calculation mode based on the data of the adjacent sensor of each sensor to be detected; step S3: obtaining respective deviation values; step S4: judging whether a measured value of the sensor data to be detected exists, if so, executing a step S5, otherwise, outputting a first alarm signal; step S5: judging whether the deviation value is greater than a first set threshold value, if so, outputting a second alarm signal, otherwise, listing the sensor in a first set; step S6: and judging whether the deviation value of a single sensor is obviously different from that of other sensors for the sensors in the first set, and if so, outputting a third alarm signal for representing the data error of the sensor. Compared with the prior art, the invention has the advantages of improving the alarm accuracy and the like.
Description
Technical Field
The invention relates to a node fault classification alarm method, in particular to a sensor node fault classification alarm method and device based on spatial correlation.
Background
The wireless sensor network is composed of wireless sensor nodes with sensing, processing, storing and communicating capabilities, and the wireless sensor network is formed in a self-organizing mode through node cooperation. The wireless sensor network can be used for deploying various sensor nodes in various monitoring areas, sensing a series of information in the monitoring areas such as temperature, humidity, acceleration, structural state and other environmental information in real time by using the sensors, transmitting data to a monitoring center through the self-organizing network, and being widely applied to the fields of military detection, environmental monitoring, structural monitoring and the like. In most wireless sensor network applications, various sensor node faults often occur easily due to the large number and low cost of wireless sensor nodes.
In order to ensure the application effect of the wireless sensor network, it is important to detect and alarm the wireless sensor node failure. The wireless sensor node fault detection method mainly comprises a centralized fault detection method and a distributed fault detection method. In the centralized fault detection method, data of all sensor nodes are transmitted to a base station, the data are analyzed uniformly, and abnormal conditions of the sensor nodes are judged. The method usually needs to transmit a large amount of original data, consumes a large amount of transmission energy consumption, and reduces the life cycle of the network. In the distributed fault detection method, local sensor data is utilized to perform distributed processing analysis on the data, and abnormal conditions of sensor nodes are judged. The method has the advantages of low energy consumption, low complexity and the like.
However, the existing wireless sensor node fault detection method is difficult to subdivide fault types, and mainly the fault characteristics are not sufficiently distinguished, so that the basis for subsequent manual repair is not sufficient. To overcome the foregoing and other drawbacks, there is a need for a sensor node fault classification alarm method suitable for use in a wireless sensor network.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a sensor node fault classification alarm method and device based on spatial correlation.
The purpose of the invention can be realized by the following technical scheme:
a sensor node fault classification alarm method based on spatial correlation comprises the following steps:
step S1: acquiring data of each sensor to obtain a sensor data column;
step S2: estimating the true value of each sensor by using the spatial correlation of the sensor node data and considering the characteristics of randomness and structure based on the data of the adjacent sensors of each sensor to be detected in a circular calculation mode;
step S3: obtaining respective deviation values based on the measured values of the data of the sensors to be detected and the estimated true values:
Δivk=|ivk-ivk *|,k=1,...,m
wherein: Δ ivkDeviation value for sensor k, ivkIs the acquired value of the sensor k data ivk *The actual value obtained by estimating the data of the sensor k is obtained, and m is the number of the sensors;
step S4: judging whether a measured value of the data of the sensor to be detected exists, if so, executing a step S5, otherwise, outputting a first alarm signal for representing the loss of connection of the sensor;
step S5: judging whether the deviation value corresponding to the sensor to be detected is larger than a first set threshold value, if so, outputting a second alarm signal for representing the data abnormity of the sensor, otherwise, listing the sensor in a first set;
step S6: and judging whether the deviation value of a single sensor is obviously different from that of other sensors or not for each sensor in the first set based on the respective deviation value, and if so, outputting a third alarm signal for representing the data error of the sensor.
In step S2, the actual value iv obtained by estimating the sensor data specifically is:
wherein α*For near initial sensor values, λkAs a weighting factor, αkIs the initial sensor value of sensor k.
The second alarm signal output in step S5 carries an abnormal indicator for reflecting the severity of the abnormality, and the updating mode of the abnormal indicator is as follows:
ξ‘=(ξ+Δivk)/2
wherein: xi' is the abnormal severity index after updating, and xi is the abnormal severity index before updating.
The step S6 specifically includes:
step S61: setting a second set threshold;
step S62: circularly judging whether the deviation value of each sensor exceeds a second set threshold value or not;
step S63: and judging whether the number of the sensors with the deviation values exceeding a second set threshold value is 1, if so, determining that the sensors have sensor errors, and outputting a third alarm signal for representing the data errors of the sensors.
A sensor node fault classification alarm device based on spatial correlation comprises a memory, a processor and a program stored in the memory and executed by the processor, wherein the processor executes the program to realize the following steps:
step S1: acquiring data of each sensor to obtain a sensor data column;
step S2: estimating the true value of each sensor by using the spatial correlation of the sensor node data and considering the characteristics of randomness and structure based on the data of the adjacent sensors of each sensor to be detected in a circular calculation mode;
step S3: obtaining respective deviation values based on the measured values of the data of the sensors to be detected and the estimated true values:
Δivk=|ivk-ivk *|,k=1,...,m
wherein: Δ ivkDeviation value for sensor k, ivkIs the acquired value of the sensor k data ivk *The actual value obtained by estimating the data of the sensor k is obtained, and m is the number of the sensors;
step S4: judging whether a measured value of the data of the sensor to be detected exists, if so, executing a step S5, otherwise, outputting a first alarm signal for representing the loss of connection of the sensor;
step S5: judging whether the deviation value corresponding to the sensor to be detected is larger than a first set threshold value, if so, outputting a second alarm signal for representing the data abnormity of the sensor, otherwise, listing the sensor in a first set;
step S6: and judging whether the deviation value of a single sensor is obviously different from that of other sensors or not for each sensor in the first set based on the respective deviation value, and if so, outputting a third alarm signal for representing the data error of the sensor.
Compared with the prior art, the invention has the following beneficial effects: and detecting the wireless sensor node fault by using the data spatial correlation of the neighbor nodes and carrying out classified alarm. The method considers the randomness and the structurality of spatial data distribution, designs a spatial interpolation method, circularly calculates the estimation value of each sensor node data, and then preliminarily classifies the sensor node faults according to the deviation value characteristics, namely three types of 'node disconnection', 'abnormal data' and 'rest', and further utilizes corresponding error judgment rules to continuously classify the 'rest' into two types of 'sensor error' and 'normal' aiming at the 'rest' type sensor nodes. The invention not only realizes the fault detection of the sensor node, but also subdivides the fault types through two stages, and the fault types are divided into three categories of node disconnection, abnormal data and sensor error, thereby providing a basis for node repair. The wireless sensor node fault detection and classification alarm method can timely and accurately detect the wireless sensor node fault and perform classification alarm, and effectively improves the node repair accuracy and timeliness.
Drawings
FIG. 1 is a schematic diagram of a fault classification alarm process of a sensor node according to the present invention;
FIG. 2 is a diagram illustrating bias value estimation based on spatial correlation according to the present invention;
FIG. 3 is a schematic diagram of a sensor node fault classification alarm method according to the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
The scheme of the application utilizes the spatial interpolation estimation, the fault classification mechanism and the error judgment method. And (3) performing spatial interpolation estimation to obtain data of adjacent sensor nodes, designing a spatial interpolation method by utilizing the spatial correlation of the sensor data and considering the randomness and structural characteristics, estimating the true value of each sensor in a cyclic calculation mode, and calculating to obtain the deviation value between the read value and the estimated value. And the fault classification mechanism judges the fault type of the sensor node by comparing the deviation value with a set threshold value, wherein the fault type comprises three types of 'node disconnection', 'abnormal data' and 'rest'. The error judgment method selects the sensor nodes of the 'other' types as objects, judges whether the sensor nodes are the 'sensor error' or not by using corresponding error judgment rules, and continuously divides the 'other' into the 'sensor error' and the 'normal'. The fault classification alarm method carries out classification alarm on the three types of sensor node faults of 'node loss of connection', 'abnormal data' and 'sensor error' through the judgment result, and triggers manual repair.
A sensor node fault classification alarm method based on spatial correlation is realized by a computer system in the form of a computer program, a corresponding alarm device comprises a memory, a processor and a program stored in the memory and executed by the processor, as shown in FIG. 1, the processor executes the program to realize the following steps:
step S1: acquiring data of each sensor through a wireless sensing network to obtain a sensor data column IV ═ IV1,iv2,…,ivm];
Step S2: by utilizing the spatial correlation of the sensor node data, as shown in fig. 2, the real values of the sensors are estimated in a circular calculation mode based on the data of the adjacent sensors of the sensors to be detected by considering the randomness and the structural characteristics, wherein the real values iv obtained by estimating the sensor data*The method specifically comprises the following steps:
wherein α*For near initial sensor values, λkAs a weighting factor, αkIs the initial sensor value of sensor k.
Step S3: obtaining respective deviation values based on the measured values of the data of the sensors to be detected and the estimated true values:
Δivk=|ivk-ivk *|,k=1,...,m
wherein: Δ ivkDeviation value for sensor k, ivkIs the acquired value of the sensor k data ivk *The actual value obtained by estimating the data of the sensor k is obtained, and m is the number of the sensors;
then, as shown in fig. 3, the failure classification mechanism determines the failure type of the sensor node by comparing the deviation value with the threshold value η of each sensor, if the routing node does not receive the data of a certain node, the node is determined as a "node disconnection" failure, if the deviation data of a certain node is greater than the threshold value η, the node is determined as an "abnormal data" failure, and an abnormal index ξ reflecting the abnormal severity is set, wherein the updating mode is ξ ═ ξ + Δ ivk) And 2, judging that the node is in a 'rest' state if the node is in a 'rest' state, wherein the sensor node faults are divided into three types of 'node disconnection', 'abnormal data' and 'rest', further selecting the 'rest' type sensor nodes as objects, operating an error judgment method, judging whether the sensor error is 'sensor error' by using corresponding error judgment rules, and continuously dividing the 'rest' into two types of 'sensor error' and 'normal', wherein the judgment basis of the error judgment rules is that the sensors slowly drift, the errors of different sensors cannot obviously appear at the same time, and when the data change of a single sensor obviously different from the rest sensors appears, the error is considered to be generated, and setting a threshold value βkAnd circularly judging m sensor nodes delta ivkWhether greater than threshold β is satisfiedkWhen the number of the sensor nodes meeting the condition is 1, judging that the sensor node has a sensorError "fault", otherwise "normal". And (4) classifying and alarming the node faults of the sensors, namely 'node loss connection', 'abnormal data' and 'sensor error', and triggering manual repair according to the judgment result.
The specific program is realized by the following steps:
step S4: judging whether a measured value of the data of the sensor to be detected exists, if so, executing a step S5, otherwise, outputting a first alarm signal for representing the loss of connection of the sensor;
step S5: judging whether a deviation value corresponding to a sensor to be detected is larger than a first set threshold value, if so, outputting a second alarm signal for representing data abnormity of the sensor, otherwise, listing the sensor in a first set, wherein the output second alarm signal carries an abnormal index for reflecting the abnormal severity degree, and the updating mode of the abnormal index is as follows:
ξ‘=(ξ+Δivk)/2
wherein: xi' is the abnormal severity index after updating, and xi is the abnormal severity index before updating.
Step S6: for each sensor in the first set, judging whether the deviation value of a single sensor is obviously different from that of other sensors or not based on the respective deviation value, and if so, outputting a third alarm signal for representing the data error of the sensor, specifically, the method comprises the following steps:
step S61: setting a second set threshold;
step S62: circularly judging whether the deviation value of each sensor exceeds a second set threshold value or not;
step S63: and judging whether the number of the sensors with the deviation values exceeding a second set threshold value is 1, if so, determining that the sensors have sensor errors, and outputting a third alarm signal for representing the data errors of the sensors.
Claims (6)
1. A sensor node fault classification alarm method based on spatial correlation is characterized by comprising the following steps:
step S1: acquiring data of each sensor to obtain a sensor data column,
step S2: by utilizing the spatial correlation of the sensor node data and considering the characteristics of randomness and structure, the true value of each sensor is estimated in a circular calculation mode based on the data of the adjacent sensors of each sensor to be detected,
step S3: obtaining respective deviation values based on the measured values of the data of the sensors to be detected and the estimated true values:
Δivk=|ivk-ivk *|,k=1,...,m
wherein: Δ ivkDeviation value for sensor k, ivkIs the acquired value of the sensor k data ivk *Is the estimated true value of the sensor k data, m is the number of sensors,
step S4: judging whether the measured value of the sensor data to be detected exists, if so, executing a step S5, otherwise, outputting a first alarm signal for representing the loss of connection of the sensor,
step S5: judging whether the deviation value corresponding to the sensor to be detected is larger than a first set threshold value, if so, outputting a second alarm signal for representing the data abnormity of the sensor, otherwise, listing the sensor in a first set,
step S6: judging whether the deviation value of a single sensor is obviously different from that of other sensors or not for each sensor in the first set based on the respective deviation value, and if so, outputting a third alarm signal for representing the data error of the sensor;
in said step S2, the estimated true value iv of the sensor data*The method specifically comprises the following steps:
wherein α*For near initial sensor values, λkAs a weighting factor, αkIs the initial sensor value of sensor k.
2. The sensor node fault classification alarm method based on spatial correlation according to claim 1, wherein the second alarm signal output in step S5 carries an abnormal indicator for reflecting the severity of the abnormality, and the abnormal indicator is updated in a manner that:
ξ‘=(ξ+Δivk)/2
wherein: xi' is the abnormal severity index after updating, and xi is the abnormal severity index before updating.
3. The spatial correlation-based sensor node fault classification alarm method according to claim 1, wherein the step S6 specifically includes:
step S61: setting a second set threshold;
step S62: circularly judging whether the deviation value of each sensor exceeds a second set threshold value or not;
step S63: and judging whether the number of the sensors with the deviation values exceeding a second set threshold value is 1, if so, determining that the sensors have sensor errors, and outputting a third alarm signal for representing the data errors of the sensors.
4. A sensor node fault classification alarm device based on spatial correlation is characterized by comprising a memory, a processor and a program stored in the memory and executed by the processor, wherein the processor executes the program to realize the following steps:
step S1: acquiring data of each sensor to obtain a sensor data column,
step S2: by utilizing the spatial correlation of the sensor node data and considering the characteristics of randomness and structure, the true value of each sensor is estimated in a circular calculation mode based on the data of the adjacent sensors of each sensor to be detected,
step S3: obtaining respective deviation values based on the measured values of the data of the sensors to be detected and the estimated true values:
Δivk=|ivk-ivk *|,k=1,...,m
wherein:Δivkdeviation value for sensor k, ivkIs the acquired value of the sensor k data ivk *Is the estimated true value of the sensor k data, m is the number of sensors,
step S4: judging whether the measured value of the sensor data to be detected exists, if so, executing a step S5, otherwise, outputting a first alarm signal for representing the loss of connection of the sensor,
step S5: judging whether the deviation value corresponding to the sensor to be detected is larger than a first set threshold value, if so, outputting a second alarm signal for representing the data abnormity of the sensor, otherwise, listing the sensor in a first set,
step S6: judging whether the deviation value of a single sensor is obviously different from that of other sensors or not for each sensor in the first set based on the respective deviation value, and if so, outputting a third alarm signal for representing the data error of the sensor;
in said step S2, the estimated true value iv of the sensor data*The method specifically comprises the following steps:
wherein α*For near initial sensor values, λkAs a weighting factor, αkIs the initial sensor value of sensor k.
5. The sensor node fault classification warning device based on the spatial correlation as claimed in claim 4, wherein the second warning signal output in step S5 carries an abnormal indicator for reflecting the severity of the abnormality, and the abnormal indicator is updated in a manner that:
ξ‘=(ξ+Δivk)/2
wherein: xi' is the abnormal severity index after updating, and xi is the abnormal severity index before updating.
6. The sensor node fault classification alarm device based on the spatial correlation as claimed in claim 4, wherein the step S6 specifically includes:
step S61: setting a second set threshold;
step S62: circularly judging whether the deviation value of each sensor exceeds a second set threshold value or not;
step S63: and judging whether the number of the sensors with the deviation values exceeding a second set threshold value is 1, if so, determining that the sensors have sensor errors, and outputting a third alarm signal for representing the data errors of the sensors.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910501493.XA CN110266527B (en) | 2019-06-11 | 2019-06-11 | Sensor node fault classification alarm method and device based on spatial correlation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910501493.XA CN110266527B (en) | 2019-06-11 | 2019-06-11 | Sensor node fault classification alarm method and device based on spatial correlation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110266527A CN110266527A (en) | 2019-09-20 |
CN110266527B true CN110266527B (en) | 2020-10-02 |
Family
ID=67917566
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910501493.XA Active CN110266527B (en) | 2019-06-11 | 2019-06-11 | Sensor node fault classification alarm method and device based on spatial correlation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110266527B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111189488B (en) * | 2019-12-13 | 2020-12-04 | 精英数智科技股份有限公司 | Sensor value abnormity identification method, device, equipment and storage medium |
CN116631136B (en) * | 2023-07-26 | 2023-10-03 | 邹城市美安电子科技有限公司 | Intelligent fire alarm system of building floor |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101957997A (en) * | 2009-12-22 | 2011-01-26 | 北京航空航天大学 | Regional average value kernel density estimation-based moving target detecting method in dynamic scene |
CN102752784A (en) * | 2012-06-19 | 2012-10-24 | 电子科技大学 | Detection method of distribution type event domain based on graph theory in wireless sensor network |
CN103514366A (en) * | 2013-09-13 | 2014-01-15 | 中南大学 | Urban air quality concentration monitoring missing data recovering method |
CN105867360A (en) * | 2016-06-14 | 2016-08-17 | 江南大学 | Initial value prediction iterative learning fault diagnosis algorithm of electromechanical control system |
CN107332691A (en) * | 2017-06-08 | 2017-11-07 | 西安电子科技大学 | A kind of method for detecting failure nodes of wireless sensor network |
CN109388856A (en) * | 2018-09-13 | 2019-02-26 | 北京大学 | A kind of temperature field prediction method based on sensing data fusion |
CN109729536A (en) * | 2019-03-06 | 2019-05-07 | 哈尔滨理工大学 | A kind of mobile wireless sensor network method for diagnosing faults |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101257355A (en) * | 2008-04-08 | 2008-09-03 | 杭州电子科技大学 | Method for detecting wireless sensor network node malfunction |
CN101969655B (en) * | 2010-09-21 | 2013-01-23 | 浙江农林大学 | Single-layer linear network prediction based authentication method of network data of wireless sensor |
CN105873111A (en) * | 2016-06-08 | 2016-08-17 | 南京信息工程大学 | Soft and hard fault diagnosis and self restoration method suitable for health monitoring |
CN109688602A (en) * | 2019-02-28 | 2019-04-26 | 福建师范大学 | Wireless sensor fault detection algorithm based on node pre-state |
-
2019
- 2019-06-11 CN CN201910501493.XA patent/CN110266527B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101957997A (en) * | 2009-12-22 | 2011-01-26 | 北京航空航天大学 | Regional average value kernel density estimation-based moving target detecting method in dynamic scene |
CN102752784A (en) * | 2012-06-19 | 2012-10-24 | 电子科技大学 | Detection method of distribution type event domain based on graph theory in wireless sensor network |
CN103514366A (en) * | 2013-09-13 | 2014-01-15 | 中南大学 | Urban air quality concentration monitoring missing data recovering method |
CN105867360A (en) * | 2016-06-14 | 2016-08-17 | 江南大学 | Initial value prediction iterative learning fault diagnosis algorithm of electromechanical control system |
CN107332691A (en) * | 2017-06-08 | 2017-11-07 | 西安电子科技大学 | A kind of method for detecting failure nodes of wireless sensor network |
CN109388856A (en) * | 2018-09-13 | 2019-02-26 | 北京大学 | A kind of temperature field prediction method based on sensing data fusion |
CN109729536A (en) * | 2019-03-06 | 2019-05-07 | 哈尔滨理工大学 | A kind of mobile wireless sensor network method for diagnosing faults |
Also Published As
Publication number | Publication date |
---|---|
CN110266527A (en) | 2019-09-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112284440B (en) | Sensor data deviation self-adaptive correction method | |
KR101872342B1 (en) | Method and device for intelligent fault diagnosis using improved rtc(real-time contrasts) method | |
EP1960853A1 (en) | Evaluating anomaly for one-class classifiers in machine condition monitoring | |
CN110266527B (en) | Sensor node fault classification alarm method and device based on spatial correlation | |
CN107276999B (en) | Event detection method in wireless sensor network | |
Gaddam et al. | Anomaly detection models for detecting sensor faults and outliers in the IoT-a survey | |
US20050144537A1 (en) | Method to use a receiver operator characteristics curve for model comparison in machine condition monitoring | |
Karthik et al. | Data trust model for event detection in wireless sensor networks using data correlation techniques | |
CN112258689A (en) | Ship data processing method and device and ship data quality management platform | |
Zhang et al. | Cooperative sensor anomaly detection using global information | |
CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
CN110662220B (en) | Wireless sensor network anomaly detection method based on time-space correlation and information entropy | |
CN112437440A (en) | Malicious collusion attack resisting method based on correlation theory in wireless sensor network | |
CN109990803A (en) | The method, apparatus of method, apparatus and the sensor processing of detection system exception | |
Wang et al. | Abnormal event detection in wireless sensor networks based on multiattribute correlation | |
Chacko et al. | Data validation and sensor life prediction layer on cloud for IoT | |
WO2006052429A2 (en) | Attribute threshold evaluation scheme | |
CN116311739A (en) | Multi-sensor fire detection method based on long-short-term memory network and environment information fusion | |
CN112800110B (en) | Weak sensitive data abnormity detection system of power internet of things sensor | |
CN108260155B (en) | Wireless sensor network anomaly detection method based on space-time similarity | |
CN111121943A (en) | Zero point fault detection method and device, computer equipment and readable storage medium | |
CN117572159B (en) | Power failure detection method and system based on big data analysis | |
CN117407824B (en) | Health detection method, equipment and medium of power time synchronization device | |
Iyer et al. | Min loading max reusability fusion classifiers for sensor data model | |
JP7396361B2 (en) | Abnormality determination device and abnormality determination method |
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 |