CN106961349A - A kind of sensor fault identifying system and method based on data fusion - Google Patents
A kind of sensor fault identifying system and method based on data fusion Download PDFInfo
- Publication number
- CN106961349A CN106961349A CN201710091603.0A CN201710091603A CN106961349A CN 106961349 A CN106961349 A CN 106961349A CN 201710091603 A CN201710091603 A CN 201710091603A CN 106961349 A CN106961349 A CN 106961349A
- Authority
- CN
- China
- Prior art keywords
- sensor
- data
- node
- sensor node
- fault
- 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
- 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
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L41/064—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis involving time analysis
-
- 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
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- 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
- H04L41/0677—Localisation of faults
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a kind of sensor fault identifying system and method based on cloud model, belong to agriculture Internet of Things field.The present invention realizes the Fault Identification of abnormity point first with the spatial simlanty of sensor node environmental information, recycle temporal correlation this nodal information of prediction current time of abnormity point historical data, this nodal information is predicted using the spatial coherence between homogeneity sensor node between Heterogeneous Sensor node, a variety of information of forecastings generate the estimate at this sensor node current time with reference to the data fusion method based on cloud model, so as to realize the fault diagnosis and data recovery of sensor node.The present invention can be realized to the abnormity point of the sensor node in industrialized agriculture and recognized, and diagnosis and data recovery, the effective accuracy for improving sensor node gathered data, simple and fast can be realized using method for diagnosing faults.Present invention can apply to the Fault Identification of sensor node abnormal data and diagnosis, the estimation of sensor abnormality data is realized.
Description
Technical field
The invention belongs to agriculture internet of things field, and in particular to a kind of sensor fault identification system based on cloud model
System and method.
Background technology
Sensor is the important component of industrialized agriculture greenhouse TT＆C system, and its main object monitored is greenhouse
Ambient parameter, therefore the environmental data of sensor collection has the features such as conversion is slow, redundancy is strong.Due to agriculture Internet of Things system
The residing environment of system is complicated, and the adverse circumstances such as high temperature, high humidity, pollution, electromagnetic interference are vulnerable in data acquisition and transmitting procedure,
So that sensor easily breaks down, the reliability, stability, accuracy of its gathered data is set all to be difficult to ensure that.
A kind of sensor fault diagnosis method and diagnostic device of application number " CN20120176322.2 ", it utilizes reception
The output signal of sensor, is decomposed using wavelet packet to output signal, filters out the wavelet package transforms with maximum amplitude
Coefficient, reservation can be with the data of characterization failure feature.Feature extraction is carried out according to the rate of change of each frequency content energy of sensor,
Characteristic vector is obtained, these characteristic vectors are input in the neutral net specified, the fault type of sensor is finally given, from
And it is capable of the mutation failure of efficient diagnosis sensor.
The content of the invention
It is an object of the invention to provide a kind of sensor fault identifying system and method based on cloud model, with realization pair
The failure of greenhouse inner sensor node carries out effective identification and diagnosis, and can realize diagnosis and number using method for diagnosing faults
According to recovery, the effective accuracy for improving sensor node gathered data, simple and fast.
In order to solve the above technical problems, concrete technical scheme of the present invention is as follows：
A kind of sensor fault identifying system based on cloud model, it is characterised in that：Greenhouse ring based on technology of Internet of things
Border TT＆C system is realized；The identifying system is specific by sensor node, control device, aggregation node, control node, relay
Device, coordinator node, intelligent gateway composition；
Sensor node by data wire connect aggregation node, aggregation node, control node by ZigBee MANETs without
Line is connected to coordinator node, and coordinator node connects intelligent gateway by data wire, and relay is connected to control section by data wire
Point；
Sensor node collection greenhouse data aggregation node processing, encapsulation, then by coordinator node transmit to
Intelligent gateway；Intelligent gateway realizes the functions such as parsing, processing, decision-making, control, and control information is transferred to control by coordinator node
Node；Control node is parsed to control information, and control relay realizes that control device is acted, and the state letter of returning equipment
Breath.Specifically include following steps：
Step one, sensor node abnormal data Fault Identification
Data mining is carried out to the information that sensor is gathered, the sensor node abnormal data based on spatial simlanty is utilized
The exceptional value of fault recognition method detection sensor node gathered data；Specially：Adopted using sensor node in industrialized agriculture
The spatial simlanty of the environmental data of collection is compared to sensor node information, and then sensor node is deposited when environmental information is close
All normal or failures may, information it is different when then at least one fault sensor node；Poll sensors node is carried out
Nodal information compares, and when the close number of environmental information is more than threshold value, then sensor node is normal, conversely, sensor node
Data exception；
Step 2, sensor fault diagnosis
It is input quantity using the predicted value based on temporal correlation for data exception point；Melted using data anastomosing algorithm
Close predicted value and generate final estimate；Specially：When generating current using the temporal correlation based on this sensor historic data
The discreet value at quarter；Using homogeneity sensor, Heterogeneous Sensor current time data, this nodes based on spatial simlanty are set up
According to discreet value；
Using the discreet value of a variety of Forecasting Methodologies as input quantity, sensor is reconstructed using the data anastomosing algorithm based on cloud model
The optimal estimation value of abnormity point；
Predicted value is compared with measuring value, and judges according to the fault signature of extraction the fault type of sensor node,
Finally realize the greenhouse TT＆C system fault diagnosis based on data fusion.
The predicted value of the temporal correlation includes the temporal predictive value based on temporal correlation, based on spatial simlanty
Spatial predictor.
The data anastomosing algorithm is a kind of data anastomosing algorithm based on cloud model.
The data anastomosing algorithm based on cloud model is to enter the characteristics extraction that racks using temporal correlation predicted value, profit
Water dust is produced with the positive generator of cloud；Standardized normal distribution N (0,1) is presented in the water dust；It is inverse using cloud based on a large amount of water dusts
Abnormal data estimate is produced to generator.
The spatial predictor includes homogeneity sensor predicted value, Heterogeneous Sensor predicted value.
The present invention has beneficial effect
The present invention is by handling the data that sensor is gathered, and the space using sensor node environmental information is similar
Property realize the Fault Identification of abnormity point, recycle the temporal correlation prediction current time information and homogeneity of abnormity point historical data
Spatial coherence between sensor node between Heterogeneous Sensor node predicts this nodal information, and a variety of information of forecastings are based on cloud mould
The data anastomosing algorithm of type produces the optimal estimation value at this node current time, is compared by measuring value with estimate, and according to
Fault signature, which is extracted, carrys out failure judgement type so that realize the fault diagnosis of sensor.The present invention is by sensor fault
Identification so that realize that sensor failure data is reconstructed so that the Decision Control of TT＆C system has the amount of accurately entering, improve and survey
The reliability of control system, reduces the possibility of TT＆C system misoperation, is conducive to the growth of industrial crops in greenhouse.
Brief description of the drawings
Fig. 1 is sensor fault identification structure chart of the present invention based on data fusion；
Fig. 2 is the greenhouse TT＆C system structure chart of the invention based on Internet of Things；
Fig. 3 is inventive sensor node abnormal data fault recognition method flow chart；
Fig. 4 is inventive sensor method for diagnosing faults block diagram.
Embodiment
In order that present disclosure is easier to be clearly understood, below according to instantiation and with reference to accompanying drawing, to this
Invention is described in further detail.
The identification of the sensor fault based on the data fusion structure of the present invention is as shown in Figure 1：
The present invention constructs a set of greenhouse TT＆C system based on Internet of Things, using the environmental data of the system acquisition as
Initial data, data mining is carried out to the environmental information that sensor is gathered, different using the sensor node based on spatial simlanty
Regular data fault recognition method finds out the exceptional value of sensor node gathered data, utilizes the sensor event based on temporal correlation
Barrier diagnostic method realizes sensor data predictive, and diagnosis and the trouble point of sensor fault are realized in combination failure feature extraction
Data reconstruction.
The greenhouse TT＆C system structure based on Internet of Things of the present invention is as shown in Figure 2：
The present invention devises a set of greenhouse TT＆C system based on Internet of Things, realizes greenhouse observing and controlling intelligent network
Close to functions such as measurement and control network unified management, greenhouse measuring and control data synchronous transfers, realize and greenhouse environment information is adopted
Collection, control, realize the detection to TT＆C system communications status.
TT＆C system gathers greenhouse environment information using sensor, and each sensor information is packaged into data in acquisition node
Bag, the packet is transmitted to intelligent gateway through aggregation node.Intelligent gateway is parsed to packet, handled, being judged, decision-making etc.
Operation, control information is transmitted to control node by aggregation node, so as to realize the action of control device, and then is realized to temperature
The regulation and control of room environmental；And intelligent gateway is realized by wireless network and communicated with server end, showing for webpage and mobile phone A PP is realized
Show and control.
Sensor of the invention node abnormal data fault recognition method flow chart is as shown in Figure 3：
It is compared between sensor node, when | xi(t)-xj(t)|<δ (δ is that sensor node is mutated threshold value), then it represents that
Comparison point ambient parameter data is similar, CiPlus 1.Otherwise, CiIt is not added with 1.Compare the information of adjacent node successively, compare after end, such as
Fruit Ci>θ, then represent sensor node viState it is normal, otherwise, work as CiSensor node v during≤θiAbnormal state, realize
The Fault Identification of sensor node.
Sensor of the invention method for diagnosing faults is as shown in Figure 4；
Sensor fault diagnosis method is to utilize the predicted value based on temporal correlation for input quantity, wherein temporal correlation
Including based on temporal correlation, spatial simlanty.
Temporal correlation refer to by greenhouse WSN TT＆C system monitoring of environmental data carry out analysis find, greenhouse inner ring
Border Parameters variation is slow, and the temperature of current slot is influenceed by eve temperature, is based on historical data, in event
The temporal predictive value based on temporal correlation is generated in barrier diagnostic method.
When spatial simlanty refers to be monitored same region, the greenhouse ginseng that different sensors are gathered in synchronization
Association is there is between number.In TT＆C system running, similar and different type sensor between adjacent sensors is found
Linear relationship is there is between the data of collection.Spatial simlanty is different according to the sensor type using contrast, can be by its point
For homogeneity sensor similitude and Heterogeneous Sensor similitude.
Spatial simlanty described above includes homogeneity sensor space similitude, Heterogeneous Sensor spatial simlanty etc.,
Based on above-mentioned spatial simlanty respectively obtain the spatial predictor based on homogeneity sensor, Heterogeneous Sensor spatial prediction
Value.
Using various types of temporal correlation predicted values, spatial simlanty predicted value as input variable, using based on cloud mould
The data anastomosing algorithm of type, sets up the positive generator of cloud and obtains a large amount of water dusts, optimal estimation value is obtained based on the reverse generator of cloud.
Optimal estimation value is generated using above-mentioned data anastomosing algorithm fusion forecasting value, by being compared with measuring value, and base
The diagnosis of sensor fault is realized in the fault signature of extraction, the reconstruct of sensor fault node data is realized, so as to realize event
Hinder the data recovery of node.
Particular embodiments described above, has been carried out further in detail to the purpose of the present invention, technical scheme and beneficial effect
Describe in detail it is bright, should be understood that the foregoing is only the present invention specific embodiment, be not intended to limit the invention, it is all
Within the spirit and principles in the present invention, any modifications, equivalent substitutions and improvements done etc., should be included in the guarantor of the present invention
Within the scope of shield.
Claims (6)
1. a kind of sensor fault identifying system based on cloud model, it is characterised in that：Greenhouse based on technology of Internet of things
TT＆C system is realized；The identifying system it is specific by sensor node, control device, aggregation node, control node, relay,
Coordinator node, intelligent gateway composition；
Sensor node connects aggregation node by data wire, and aggregation node, control node are wirelessly connected by ZigBee MANETs
Coordinator node is connected to, coordinator node connects intelligent gateway by data wire, and relay is connected to control node by data wire；
The greenhouse data of sensor node collection are transmitted to intelligence in aggregation node processing, encapsulation, then by coordinator node
Gateway；Intelligent gateway realizes the functions such as parsing, processing, decision-making, control, and control information is transferred to control section by coordinator node
Point；Control node is parsed to control information, and control relay realizes that control device is acted, and the state letter of returning equipment
Breath.
2. a kind of recognition methods of sensor fault identifying system based on cloud model according to claim 1, its feature
It is to comprise the following steps：
Step one, sensor node abnormal data Fault Identification
Data mining is carried out to the information that sensor is gathered, the sensor node abnormal data failure based on spatial simlanty is utilized
The exceptional value of recognition methods detection sensor node gathered data；Specially：Gathered using sensor node in industrialized agriculture
The spatial simlanty of environmental data is compared to sensor node information, and then sensor node is present full when environmental information is close
Portion is normal or failure may, information it is different when then at least one fault sensor node；Poll sensors node carries out node
Information compares, and when the close number of environmental information is more than threshold value, then sensor node is normal, conversely, sensor node data
It is abnormal；
Step 2, sensor fault diagnosis
It is input quantity using the predicted value based on temporal correlation for data exception point；It is pre- using data anastomosing algorithm fusion
Measured value generates final estimate；Specially：Utilize the temporal correlation generation current time based on this sensor historic data
Discreet value；Using homogeneity sensor, Heterogeneous Sensor current time data, this node data based on spatial simlanty is set up
Discreet value；
Using the discreet value of a variety of Forecasting Methodologies as input quantity, sensor abnormality is reconstructed using the data anastomosing algorithm based on cloud model
The optimal estimation value of point；
Predicted value is compared with measuring value, and judges the fault type of sensor node according to the fault signature of extraction, finally
Realize the greenhouse TT＆C system fault diagnosis based on data fusion.
3. a kind of sensor fault recognition methods based on data fusion according to claim 2, it is characterised in that：It is described
The predicted value of temporal correlation includes the temporal predictive value based on temporal correlation, the spatial predictor based on spatial simlanty.
4. a kind of sensor fault recognition methods based on data fusion according to claim 2, it is characterised in that：It is described
Data anastomosing algorithm is a kind of data anastomosing algorithm based on cloud model.
5. a kind of sensor fault recognition methods based on data fusion according to claim 2, it is characterised in that：It is described
Data anastomosing algorithm based on cloud model is to enter the characteristics extraction that racks using temporal correlation predicted value, is occurred using cloud forward direction
Device produces water dust；Standardized normal distribution N (0,1) is presented in the water dust；Based on a large amount of water dusts, produced using the reverse generator of cloud
Abnormal data estimate.
6. a kind of sensor fault recognition methods based on data fusion according to claim 3, it is characterised in that：It is described
Spatial predictor includes homogeneity sensor predicted value, Heterogeneous Sensor predicted value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710091603.0A CN106961349A (en) | 2017-02-20 | 2017-02-20 | A kind of sensor fault identifying system and method based on data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710091603.0A CN106961349A (en) | 2017-02-20 | 2017-02-20 | A kind of sensor fault identifying system and method based on data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106961349A true CN106961349A (en) | 2017-07-18 |
Family
ID=59481567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710091603.0A Pending CN106961349A (en) | 2017-02-20 | 2017-02-20 | A kind of sensor fault identifying system and method based on data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106961349A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107562007A (en) * | 2017-08-23 | 2018-01-09 | 中冶赛迪工程技术股份有限公司 | Control method and system based on fan-shaped section position sensor malfunction |
| CN109617874A (en) * | 2018-12-10 | 2019-04-12 | 绍兴文理学院 | A kind of heterogeneous Sensor Network rogue program propagation modeling method |
| CN109978010A (en) * | 2019-04-10 | 2019-07-05 | 广东省气象探测数据中心 | Rainy quantity sensor blending algorithm |
| CN110880062A (en) * | 2019-10-31 | 2020-03-13 | 广西电网有限责任公司电力科学研究院 | Method for determining state maintenance time of power distribution equipment |
| CN110941256A (en) * | 2019-12-25 | 2020-03-31 | 宁波鄞州诚来农业科技有限公司 | Greenhouse environment wireless monitoring system's fault diagnosis system |
| CN112672299A (en) * | 2020-12-09 | 2021-04-16 | 电子科技大学 | Sensor data reliability evaluation method based on multi-source heterogeneous information fusion |
| WO2021146927A1 (en) * | 2020-01-21 | 2021-07-29 | Siemens Schweiz Ag | Method and apparatus for sensor fault detection |
| CN115496127A (en) * | 2022-08-22 | 2022-12-20 | 佳源科技股份有限公司 | Multi-sensor fusion judgment method and system based on pipe gallery environment |
| CN116599867A (en) * | 2023-07-18 | 2023-08-15 | 中国人民解放军国防科技大学 | Internet of things sensor abnormality detection method and system based on dynamic diagram |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102340811A (en) * | 2011-11-02 | 2012-02-01 | 中国农业大学 | Method for carrying out fault diagnosis on wireless sensor networks |
| CN102572908A (en) * | 2012-02-20 | 2012-07-11 | 南京邮电大学 | Distributed failure detection method for wireless sensor network nodes |
-
2017
- 2017-02-20 CN CN201710091603.0A patent/CN106961349A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102340811A (en) * | 2011-11-02 | 2012-02-01 | 中国农业大学 | Method for carrying out fault diagnosis on wireless sensor networks |
| CN102572908A (en) * | 2012-02-20 | 2012-07-11 | 南京邮电大学 | Distributed failure detection method for wireless sensor network nodes |
Non-Patent Citations (1)
| Title |
|---|
| 王华东等: "温室测控系统无线传感器网络节点故障诊断研究", 《科学技术与工程》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107562007B (en) * | 2017-08-23 | 2019-09-13 | 中冶赛迪工程技术股份有限公司 | Control method and system based on fan-shaped section position sensor malfunction |
| CN107562007A (en) * | 2017-08-23 | 2018-01-09 | 中冶赛迪工程技术股份有限公司 | Control method and system based on fan-shaped section position sensor malfunction |
| CN109617874A (en) * | 2018-12-10 | 2019-04-12 | 绍兴文理学院 | A kind of heterogeneous Sensor Network rogue program propagation modeling method |
| CN109617874B (en) * | 2018-12-10 | 2021-04-06 | 绍兴文理学院 | Malicious program propagation modeling method for heterogeneous sensor network |
| CN109978010A (en) * | 2019-04-10 | 2019-07-05 | 广东省气象探测数据中心 | Rainy quantity sensor blending algorithm |
| CN109978010B (en) * | 2019-04-10 | 2021-03-05 | 广东省气象探测数据中心 | Fusion method of multiple rainfall sensors |
| CN110880062B (en) * | 2019-10-31 | 2022-07-08 | 广西电网有限责任公司电力科学研究院 | Method for determining state maintenance time of power distribution equipment |
| CN110880062A (en) * | 2019-10-31 | 2020-03-13 | 广西电网有限责任公司电力科学研究院 | Method for determining state maintenance time of power distribution equipment |
| CN110941256A (en) * | 2019-12-25 | 2020-03-31 | 宁波鄞州诚来农业科技有限公司 | Greenhouse environment wireless monitoring system's fault diagnosis system |
| WO2021146927A1 (en) * | 2020-01-21 | 2021-07-29 | Siemens Schweiz Ag | Method and apparatus for sensor fault detection |
| CN112672299A (en) * | 2020-12-09 | 2021-04-16 | 电子科技大学 | Sensor data reliability evaluation method based on multi-source heterogeneous information fusion |
| CN112672299B (en) * | 2020-12-09 | 2022-05-03 | 电子科技大学 | Sensor data reliability evaluation method based on multi-source heterogeneous information fusion |
| CN115496127A (en) * | 2022-08-22 | 2022-12-20 | 佳源科技股份有限公司 | Multi-sensor fusion judgment method and system based on pipe gallery environment |
| CN115496127B (en) * | 2022-08-22 | 2023-10-24 | 佳源科技股份有限公司 | Multi-sensor fusion judging method and system based on pipe gallery environment |
| CN116599867A (en) * | 2023-07-18 | 2023-08-15 | 中国人民解放军国防科技大学 | Internet of things sensor abnormality detection method and system based on dynamic diagram |
| CN116599867B (en) * | 2023-07-18 | 2023-11-24 | 中国人民解放军国防科技大学 | Internet of things sensor abnormality detection method and system based on dynamic diagram |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106961349A (en) | A kind of sensor fault identifying system and method based on data fusion | |
| CN105515184B (en) | Multisensor many reference amounts distribution synergic monitoring system based on wireless sensor network | |
| US11543440B2 (en) | Framework for fault detection and localization in power distribution networks | |
| US20220036199A1 (en) | System and method for predictive foliage impingement and wildfire management using generative adversarial network | |
| CN110401262A (en) | GIS device state intelligent monitoring system and method based on edge calculations technology | |
| Minovski et al. | Modeling quality of IoT experience in autonomous vehicles | |
| KR101214765B1 (en) | System and method for monitoring electrical power equipment | |
| EP3757583B1 (en) | System for determining electric parameters of an electric power grid | |
| WO2014183782A1 (en) | Method and network device for cell anomaly detection | |
| US20230062725A1 (en) | Data Analytics for Smart Electrical Protection Systems | |
| CN106325252A (en) | Multi-level large-span large data oriented power equipment state monitoring and evaluating system | |
| CN114039819B (en) | Edge intelligent gateway based on 5G | |
| CN108601047B (en) | Measurement method of opportunistic network key node | |
| CN112731827B (en) | Monitoring system for intelligent sensor for power equipment | |
| CN113763667B (en) | Fire disaster early warning and state monitoring device and method based on 5G edge calculation | |
| CN105634796A (en) | Network device failure prediction and diagnosis method | |
| CN112685472A (en) | Power grid multi-station fusion monitoring method and device, electronic equipment and storage medium | |
| CN102684902A (en) | Network fault positioning method based on probe prediction | |
| CN116295583A (en) | Sensor abnormal data correction method, device, equipment and readable storage medium | |
| US11657148B2 (en) | Event analysis in an electric power system | |
| Alcaraz et al. | Diagnosis mechanism for accurate monitoring in critical infrastructure protection | |
| CN104486786B (en) | A kind of fault detection method of wireless sensor network | |
| Garcés-Jiménez et al. | Industrial Internet of Things embedded devices fault detection and classification. A case study | |
| CN117835179A (en) | Power grid infrastructure safety management method and system | |
| Zhao et al. | Design of wireless sensor network middleware for agricultural applications |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170718 |
|
| WD01 | Invention patent application deemed withdrawn after publication |