CN111796200A - AI algorithm for automatically identifying lamp fault based on current characteristic fingerprint curve - Google Patents
AI algorithm for automatically identifying lamp fault based on current characteristic fingerprint curve Download PDFInfo
- Publication number
- CN111796200A CN111796200A CN202010931593.9A CN202010931593A CN111796200A CN 111796200 A CN111796200 A CN 111796200A CN 202010931593 A CN202010931593 A CN 202010931593A CN 111796200 A CN111796200 A CN 111796200A
- Authority
- CN
- China
- Prior art keywords
- curve
- lamp
- current characteristic
- characteristic fingerprint
- detected
- 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
- 238000000034 method Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 241001465382 Physalis alkekengi Species 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/44—Testing lamps
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention discloses an AI algorithm for automatically identifying lamp faults based on a current characteristic fingerprint curve. The invention can realize real-time judgment of the fault lamp and has the advantage of high judgment accuracy.
Description
Technical Field
The invention relates to the field of intelligent AI (analog-to-digital) algorithms for lamp state identification, in particular to an AI algorithm for automatically identifying lamp faults based on a current characteristic fingerprint curve.
Background
At present, a global standard protocol (DMX 512 protocol) is generally adopted by intelligent lamps, remote control of the lamps can be realized based on the protocol, but real-time fault states of the lamps cannot be acquired based on the protocol, lamp faults can only be detected in a manual inspection mode, and the problem that labor cost is too high when inspection is performed on mountains, scenic spots and other businesses, and further the problem that operation and maintenance departments are difficult to acquire the fault states of the lamps in time is caused. In the actual operation and maintenance process, a small number of lamps are not maintained and replaced under the condition that the lamps are invalid and the landscape is not influenced. The lamp failure detection and identification device is designed for solving the problem of lamp failure detection and identification.
Disclosure of Invention
The invention aims to provide an AI algorithm for automatically identifying lamp faults based on a current characteristic fingerprint curve, so as to solve the problem that the real-time fault state of an intelligent lamp in the prior art cannot be acquired.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
AI algorithm based on current characteristic fingerprint curve automatic identification lamps and lanterns trouble, its characterized in that: the method comprises the following steps:
(1) enabling the plurality of normal lamps to respectively play the same set program, collecting the real-time current value of each normal lamp in the process of playing the set program, and training the collected real-time current value of each normal lamp by adopting a neural network to generate a first current characteristic fingerprint curve;
(2) selecting a plurality of lamps comprising a plurality of fault lamps to respectively play the same set program, collecting the real-time current value of each lamp in the process of playing the set program, training the collected real-time current value of each lamp by adopting a neural network, and generating a second current characteristic fingerprint curve;
(3) placing the plurality of normal lamps in the step (1) in a high-temperature environment, enabling the normal lamps to respectively play the same set program, simultaneously collecting the real-time current value of each normal lamp in the process of playing the set program in the high-temperature environment, and training the collected real-time current value of each normal lamp in the high-temperature environment by adopting a neural network to generate a third current characteristic fingerprint curve;
(4) placing the lamps in the step (2) in a high-temperature environment, enabling the lamps to respectively play the same set program, simultaneously collecting the real-time current value of each lamp in the process of playing the set program in the high-temperature environment, and training the collected real-time current value of each lamp in the high-temperature environment by adopting a neural network to generate a fourth current characteristic fingerprint curve;
(5) the method comprises the steps of enabling a plurality of lamps to be detected to respectively play the same set program, collecting the real-time current value of each lamp to be detected in the process of playing the set program, obtaining the current characteristic fingerprint curve of each lamp to be detected according to the real-time current value of each lamp to be detected, comparing the current characteristic fingerprint curve of each lamp to be detected with the first current characteristic fingerprint curve, the second current characteristic fingerprint curve, the third current characteristic fingerprint curve and the fourth current characteristic fingerprint curve respectively to obtain a matching curve, judging that the lamp to be detected is normal if the matching curve is any one of the first current characteristic fingerprint curve and the third current characteristic fingerprint curve, and judging that the lamp to be detected has a fault if the matching curve is any one of the second current characteristic curve and the fourth.
The AI algorithm for automatically identifying lamp faults based on the current characteristic fingerprint curve is characterized in that: in the step (5), a corresponding current characteristic curve function is obtained according to the current characteristic fingerprint curve during matching, and similarity comparison is performed based on the current characteristic curve function.
The AI algorithm for automatically identifying lamp faults based on the current characteristic fingerprint curve is characterized in that: in the step (5), the similarity between the current characteristic curve function of the lamp to be detected and the first, second, third and fourth current characteristic curve functions is calculated respectively to obtain a judgment result.
The AI algorithm for automatically identifying lamp faults based on the current characteristic fingerprint curve is characterized in that: and when the judgment result of the lamp to be detected is obtained, actually checking whether the judgment result has errors, if so, correcting the matching curve corresponding to the lamp to be detected, and updating the matching curve for detecting the subsequent lamp to be detected.
The invention can generate a curve function by AI training through the current characteristic curve, compare the similarity of the trained curve function with the current curve of the lamp to be detected collected in real time, confirm the current lamp state according to the comparison result, and finally analyze the abnormal state and report in real time, thereby realizing the real-time judgment of the lamp state and having the advantage of high judgment accuracy.
Drawings
FIG. 1 is a block diagram of an AI training process of the present invention.
FIG. 2 is a block diagram of the detection process of the present invention.
Fig. 3 is a graph of a first current signature fingerprint obtained in step (1) according to an embodiment of the present invention.
Fig. 4 is a second current signature graph obtained in step (2) according to an embodiment of the present invention.
Fig. 5 is a third current signature graph obtained in step (3) according to an embodiment of the present invention.
Fig. 6 is a fourth current fingerprint graph obtained in step (4) according to an embodiment of the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
As shown in fig. 1 and 2, the AI algorithm for automatically identifying the lamp fault based on the current characteristic fingerprint curve includes the following steps:
(1) and selecting 100 normal lamps, enabling the 100 normal lamps to respectively play the same set program, acquiring the real-time current value of each normal lamp in the process of playing the set program through the field current acquisition unit, training the acquired real-time current values of the 100 normal lamps by adopting a neural network, and generating a first current characteristic fingerprint curve as shown in fig. 3.
(2) And (3) selecting 100 lamps comprising a plurality of fault lamps to respectively play the same set program in the step (1), collecting the real-time current value of each lamp in the process of playing the set program, training the collected real-time current value of each lamp by adopting a neural network, and generating a second current characteristic fingerprint curve as shown in fig. 4.
(3) And (3) placing the 100 normal lamps in the step (1) in a high-temperature environment, enabling each normal lamp to play the same set program in the step (1), simultaneously collecting the real-time current value of each normal lamp in the process of playing the set program in the high-temperature environment, training the collected real-time current value of each normal lamp in the high-temperature environment by adopting a neural network, and generating a third current characteristic fingerprint curve as shown in fig. 5.
(4) And (3) placing the 100 lamps in the step (2) in a high-temperature environment, enabling the lamps to respectively play the same set program, simultaneously collecting the real-time current value of each lamp in the process of playing the set program in the high-temperature environment, training the collected real-time current value of each lamp in the high-temperature environment by adopting a neural network, and generating a fourth current characteristic fingerprint curve as shown in fig. 6.
(5) And (3) enabling a plurality of lamps to be detected to respectively play the set programs same as in the step (1), collecting the real-time current value of each lamp to be detected in the process of playing the set programs, obtaining the current characteristic fingerprint curve of each lamp to be detected according to the real-time current value of each lamp to be detected, and comparing the current characteristic fingerprint curve of each lamp to be detected with the first current characteristic fingerprint curve, the second current characteristic fingerprint curve, the third current characteristic fingerprint curve and the fourth current characteristic fingerprint curve respectively to obtain a matching curve.
And during matching, a current characteristic curve function corresponding to each current characteristic fingerprint curve of the lamp to be detected and current characteristic curve functions corresponding to the first, second, third and fourth current characteristic fingerprint curves are obtained according to the current characteristic fingerprint curves, and the similarity between the current characteristic curve function of the lamp to be detected and the first, second, third and fourth current characteristic curve functions is respectively calculated to obtain a judgment matching curve.
And if the matching curve is any one of the first current characteristic fingerprint curve and the third current characteristic fingerprint curve, judging that the lamp to be detected is normal, and if the matching curve is any one of the second current characteristic fingerprint curve and the fourth current characteristic fingerprint curve, judging that the lamp to be detected has a fault.
And when the judgment result of the lamp to be detected is obtained, actually checking whether the judgment result has errors, if so, correcting the matching curve corresponding to the lamp to be detected, and updating the matching curve for detecting the subsequent lamp to be detected.
The embodiments of the present invention are described only for the preferred embodiments of the present invention, and not for the limitation of the concept and scope of the present invention, and various modifications and improvements made to the technical solution of the present invention by those skilled in the art without departing from the design concept of the present invention shall fall into the protection scope of the present invention, and the technical content of the present invention which is claimed is fully set forth in the claims.
Claims (4)
1. AI algorithm based on current characteristic fingerprint curve automatic identification lamps and lanterns trouble, its characterized in that: the method comprises the following steps:
(1) enabling the plurality of normal lamps to respectively play the same set program, collecting the real-time current value of each normal lamp in the process of playing the set program, and training the collected real-time current value of each normal lamp by adopting a neural network to generate a first current characteristic fingerprint curve;
(2) selecting a plurality of lamps comprising a plurality of fault lamps to respectively play the same set program, collecting the real-time current value of each lamp in the process of playing the set program, training the collected real-time current value of each lamp by adopting a neural network, and generating a second current characteristic fingerprint curve;
(3) placing the plurality of normal lamps in the step (1) in a high-temperature environment, enabling the normal lamps to respectively play the same set program, simultaneously collecting the real-time current value of each normal lamp in the process of playing the set program in the high-temperature environment, and training the collected real-time current value of each normal lamp in the high-temperature environment by adopting a neural network to generate a third current characteristic fingerprint curve;
(4) placing the lamps in the step (2) in a high-temperature environment, enabling the lamps to respectively play the same set program, simultaneously collecting the real-time current value of each lamp in the process of playing the set program in the high-temperature environment, and training the collected real-time current value of each lamp in the high-temperature environment by adopting a neural network to generate a fourth current characteristic fingerprint curve;
(5) the method comprises the steps of enabling a plurality of lamps to be detected to respectively play the same set program, collecting the real-time current value of each lamp to be detected in the process of playing the set program, obtaining the current characteristic fingerprint curve of each lamp to be detected according to the real-time current value of each lamp to be detected, comparing the current characteristic fingerprint curve of each lamp to be detected with the first current characteristic fingerprint curve, the second current characteristic fingerprint curve, the third current characteristic fingerprint curve and the fourth current characteristic fingerprint curve respectively to obtain a matching curve, judging that the lamp to be detected is normal if the matching curve is any one of the first current characteristic fingerprint curve and the third current characteristic fingerprint curve, and judging that the lamp to be detected has a fault if the matching curve is any one of the second current characteristic curve and the fourth.
2. The AI algorithm for automatically identifying lamp faults based on current signature curve of claim 1, wherein: in the step (5), a corresponding current characteristic curve function is obtained according to the current characteristic fingerprint curve during matching, and similarity comparison is performed based on the current characteristic curve function.
3. The AI algorithm for automatically identifying lamp faults based on current signature curve of claim 2, wherein: in the step (5), the similarity between the current characteristic curve function of the lamp to be detected and the first, second, third and fourth current characteristic curve functions is calculated respectively to obtain a judgment result.
4. The AI algorithm for automatically identifying lamp faults based on current signature curve of claim 1, wherein: and when the judgment result of the lamp to be detected is obtained, actually checking whether the judgment result has errors, if so, correcting the matching curve corresponding to the lamp to be detected, and updating the matching curve for detecting the subsequent lamp to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010931593.9A CN111796200A (en) | 2020-09-08 | 2020-09-08 | AI algorithm for automatically identifying lamp fault based on current characteristic fingerprint curve |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010931593.9A CN111796200A (en) | 2020-09-08 | 2020-09-08 | AI algorithm for automatically identifying lamp fault based on current characteristic fingerprint curve |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111796200A true CN111796200A (en) | 2020-10-20 |
Family
ID=72834225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010931593.9A Pending CN111796200A (en) | 2020-09-08 | 2020-09-08 | AI algorithm for automatically identifying lamp fault based on current characteristic fingerprint curve |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111796200A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050062481A1 (en) * | 2003-09-19 | 2005-03-24 | Thomas Vaughn | Wayside LED signal for railroad and transit applications |
| CN102076145A (en) * | 2010-11-02 | 2011-05-25 | 深圳市航盛电子股份有限公司 | Accurate detection and control method and device for automobile LED steering lamp |
| CN103116139A (en) * | 2013-01-23 | 2013-05-22 | 重庆恒又源科技发展有限公司 | Detection method, detection device and detection system of street lamp failure |
| CN104808154A (en) * | 2014-08-25 | 2015-07-29 | 上海路辉电子科技有限公司 | Street lamp fault type determining method based on fuzzy set theory |
| CN108398656A (en) * | 2018-02-27 | 2018-08-14 | 安徽建筑大学 | High-voltage LED street lamp, method for diagnosing faults and readable storage medium storing program for executing |
| CN108414949A (en) * | 2018-02-27 | 2018-08-17 | 安徽建筑大学 | High-voltage LED lamp failure diagnostic method and medium based on illumination feature |
| CN109541498A (en) * | 2018-11-30 | 2019-03-29 | 苏州数言信息技术有限公司 | A kind of general lamp failure intelligent detecting method and system |
-
2020
- 2020-09-08 CN CN202010931593.9A patent/CN111796200A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050062481A1 (en) * | 2003-09-19 | 2005-03-24 | Thomas Vaughn | Wayside LED signal for railroad and transit applications |
| CN102076145A (en) * | 2010-11-02 | 2011-05-25 | 深圳市航盛电子股份有限公司 | Accurate detection and control method and device for automobile LED steering lamp |
| CN103116139A (en) * | 2013-01-23 | 2013-05-22 | 重庆恒又源科技发展有限公司 | Detection method, detection device and detection system of street lamp failure |
| CN104808154A (en) * | 2014-08-25 | 2015-07-29 | 上海路辉电子科技有限公司 | Street lamp fault type determining method based on fuzzy set theory |
| CN108398656A (en) * | 2018-02-27 | 2018-08-14 | 安徽建筑大学 | High-voltage LED street lamp, method for diagnosing faults and readable storage medium storing program for executing |
| CN108414949A (en) * | 2018-02-27 | 2018-08-17 | 安徽建筑大学 | High-voltage LED lamp failure diagnostic method and medium based on illumination feature |
| CN109541498A (en) * | 2018-11-30 | 2019-03-29 | 苏州数言信息技术有限公司 | A kind of general lamp failure intelligent detecting method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20150346066A1 (en) | Asset Condition Monitoring | |
| CN107707374A (en) | Fault diagnosis method and system, user terminal and server for fault diagnosis | |
| CN103278719A (en) | Power equipment fault detection method and system based on matrix diagram and confidence coefficient | |
| CN106909974B (en) | Method, data analyzer and system for analyzing multi-terminal state | |
| CN108919044B (en) | Active identification method for unit distribution power grid faults based on mutual verification mechanism | |
| CN103713215A (en) | System and method for detecting X-ray tube running state | |
| CN112333891B (en) | Lighting lamp fault prediction and health management device and method and railway vehicle | |
| CN104749467A (en) | Distribution terminal self-diagnostic method and system | |
| CN110503322A (en) | A kind of Military Maintenance appraisal procedure | |
| CN105891679A (en) | Fault detection system and method for electric power grid | |
| CN111309584B (en) | Data processing method, device, electronic equipment and storage medium | |
| KR102351538B1 (en) | System and method for predicting failure of automated facilities using and algorithm that learns and diagnoses patterns | |
| CN113821242A (en) | Intelligent firmware matching method and system | |
| CN105652144A (en) | Detection device and method of battery pack wire harness | |
| CN111796200A (en) | AI algorithm for automatically identifying lamp fault based on current characteristic fingerprint curve | |
| CN105319500A (en) | Disconnecting switch online monitoring system and method based on guyed sensor | |
| CN110399926B (en) | Street lamp fault diagnosis method and device | |
| CN108828469B (en) | Street lamp fault diagnosis circuit and diagnosis method thereof | |
| CN114040556B (en) | Intelligent illumination fault automatic alarm method, system and storage medium | |
| KR100768126B1 (en) | Sequence of event system for plant | |
| CN114239866A (en) | Power grid dispatching information flow abnormity and fault discrimination method | |
| CN113709065A (en) | Automatic detection method, system, equipment and storage medium for panel light of switch | |
| CN113591909B (en) | Abnormality detection method for power system, abnormality detection device, and storage medium | |
| CN108919169A (en) | A kind of fault self-diagnosis method of electric energy meter | |
| CN113114987A (en) | Hadoop-based power system inspection method and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201020 |