CN111640278A - Method for detecting cleanliness of window of multiband flame detector - Google Patents
Method for detecting cleanliness of window of multiband flame detector Download PDFInfo
- Publication number
- CN111640278A CN111640278A CN202010537868.0A CN202010537868A CN111640278A CN 111640278 A CN111640278 A CN 111640278A CN 202010537868 A CN202010537868 A CN 202010537868A CN 111640278 A CN111640278 A CN 111640278A
- Authority
- CN
- China
- Prior art keywords
- pollution
- window
- instrument
- signal
- samples
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000003749 cleanliness Effects 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 40
- 238000013528 artificial neural network Methods 0.000 claims abstract description 38
- 230000007246 mechanism Effects 0.000 claims abstract description 9
- 238000012423 maintenance Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 238000004904 shortening Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims 1
- 230000009471 action Effects 0.000 description 3
- 230000001010 compromised effect Effects 0.000 description 2
- 238000011109 contamination Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- 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
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C23/00—Non-electrical signal transmission systems, e.g. optical systems
- G08C23/04—Non-electrical signal transmission systems, e.g. optical systems using light waves, e.g. infrared
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Fire-Detection Mechanisms (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
- Fire Alarms (AREA)
Abstract
The invention discloses a method for detecting the cleanliness of a window of a multiband flame detector, which comprises the following steps of S1: starting an infrared transmitter according to the number of the channels and transmitting an infrared signal; s2, capture signal: after a period of time delay, the pyroelectric sensor starts to capture the reflection model of the infrared emitter, and continuously collects 100 data to form a group, and 100 groups are collected; s3, data processing, the invention relates to the technical field of flame detectors. According to the method for detecting the window cleanliness of the multiband flame detector, a compensation mechanism is provided by using an artificial neural network algorithm, the durability and reliability of the instrument are improved, the maintenance period of the instrument is reduced, the labor cost is reduced, different pollution conditions of different areas of the window are judged by matching with a multi-channel pyroelectric sensor when multiple channels are detected, the signal gain of each channel is dynamically adjusted through the algorithm, and the fire detection performance of the instrument is enhanced.
Description
Technical Field
The invention relates to the technical field of flame detectors, in particular to a method for detecting the cleanliness of a window of a multiband flame detector.
Background
The multiband infrared flame detector is used for judging flame by utilizing the absorption capacity of a multichannel pyroelectric sensor to infrared radiation of different wavebands and an artificial neural network technology, and has excellent response time, anti-interference capacity and detection distance. In order to detect whether the pyroelectric sensor can normally work, an infrared emitter is often arranged in a detector window, a reflector is arranged on a shell, a signal sent by the infrared emitter is reflected, and the pyroelectric sensor receives the signal of the infrared emitter to judge that the pyroelectric sensor does not break down.
The structure of the sensor part of the multiband infrared flame detector mainly comprises a window, a reflector, a light filter, an infrared emitter and a pyroelectric sensor, wherein the influence of the cleanliness of the window on the detection distance and the visual angle of the detector is very obvious. Most of the existing multiband infrared flame detectors utilize a reflective mirror and an infrared emitter to judge whether a pyroelectric sensor can normally work, but when the surface of a window is polluted, although the pyroelectric sensor can normally work, the detection capability of the pyroelectric sensor is greatly reduced, and even flames at a position far away from the pyroelectric sensor lose the detection capability.
Some multiband infrared flame detectors introduce that whether a window is polluted is judged by using reflection of an infrared emitter, but at present, only system composition and a structural model for detecting the cleanliness of the window have related descriptions, but internal processing and window cleanliness judgment methods after a sensor detects a reflection signal are lack of introduction, or whether the window is polluted is judged when a pyroelectric sensor cannot detect a signal of the infrared emitter, and the method is difficult to realize.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a method for detecting the cleanliness of a window of a multiband flame detector, which solves the problems that whether the window is polluted or not, and the pollution degree and the pollution source are difficult to judge.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: a method for detecting the cleanliness of a window of a multiband flame detector specifically comprises the following steps:
s1, turning on an infrared emitter: starting an infrared transmitter according to the number of the channels and transmitting an infrared signal;
s2, capture signal: after a period of time delay, the pyroelectric sensor starts to capture the reflection model of the infrared emitter, and continuously collects 100 data to form a group, and 100 groups are collected;
s3, data processing: according to time domain division, points where the maximum value and the minimum value in each group can occur are divided, wherein the maximum Tmax is found in 18 th to 36 th data, the minimum value Tmin is found in 50 th to 75 th data, the average values of the maximum value and the minimum value are obtained by adopting a sorting method, Tmax _ avg and Tmin _ avg are obtained, and the Tmax _ avg and the Tmin _ avg are written into an EEPROM as reference parameters of the instrument;
s4, judging the pollution degree: learning pollution degrees of different pollution sources and a certain pollution source as samples through an artificial neural network, and taking the samples as comparison samples, separating a compensatable pollution source and an uncompensable pollution source according to a compensation algorithm mechanism, simultaneously giving a compensation threshold value K by the compensation algorithm, considering that the K value is reasonable when the K value is in a range of 0-1, considering that the compensation is invalid when the K value exceeds 1, sending a fault indication, and making a decision according to the fault indication;
s5, cyclic detection: and collecting reflected signals of the infrared emitter by taking two minutes as a polling period, obtaining the maximum value Tmax _ o and the minimum value Tmin _ o of the single signal, shortening the polling period to 30 seconds when the Tmax _ o/Tmax _ avg is less than 0.8 and the Tmin _ o/Tmin _ avg is less than 0.75, and judging the pollution of the window through an artificial neural network if the conditions are continuously present for 3 times.
Preferably, in step S4, when the window is clean or contaminated, 128 feature extractions are performed on the infrared emitter reflection signal curve of the single channel by using an artificial neural network to describe the signal curve.
Preferably, after determining a certain pollution source in step S4, different pollution levels of the same pollution source have similar signal curves, but the threshold and the slope thereof change, the artificial neural network can learn the samples and give a determination of the pollution level, and a fault signal is sent when a certain pollution level is exceeded, so that a pollution information code can be displayed.
Preferably, in step S4, the artificial neural network collects infrared emitter reflection signal samples when the window is clean, and learns as clean reference samples, and applies various pollution sources that may occur in a simulation field usage situation on the window, and the artificial neural network collects infrared emitter reflection signal samples under various pollution sources, and learns as various pollution source samples.
Preferably, in step S4, the maximum fire detection capability of the meter, that is, the flame detection distance and the detection viewing angle, are obtained through a test or a meter specification, various pollution sources with three pollution levels are applied to the surface of the window, the artificial neural network collects samples of the reflected signal of the infrared emitter, the samples are used as samples of the three pollution levels of the various pollution sources for learning, and a compensation algorithm mechanism is provided according to the comparison samples.
Preferably, in the step S4, the pollution sources and the pollution levels in different areas of the window surface are comprehensively determined according to the difference of the threshold values of different channels and the artificial neural network criterion, and different decisions are given for the pollution sources and the pollution levels in different situations.
Preferably, the decision one: the pollution source and the pollution degree damage the fire detection performance of the instrument, the acquired signal cannot be compensated through the instrument to improve the fire detection performance, and a fault signal code is sent to request maintenance; and decision two: the source and level of contamination has compromised the fire detection performance of the meter, but the detection performance can be improved by compensating the acquired signal by the software and hardware of the meter itself. And then, carrying out algorithm compensation on the collected environment infrared signals according to different pollution sources and pollution degrees, and dynamically adjusting the signal gain, weight and threshold of each channel to improve the sensitivity of the instrument to flame, dynamically compensate the fire detection distance and fire detection visual angle, so that the instrument can maintain the fire detection performance. When the software and hardware compensation exceeds the threshold value and the performance of the instrument is inevitably reduced, a fault signal code is sent out to request maintenance.
Preferably, after the window pollution is judged by the extreme method in the step S5, the artificial neural network intervenes to capture the reflected signal of the infrared emitter at a frequency of 30 seconds, and learn a sample through an algorithm to judge the conditions of a pollution source and a pollution degree, if the conditions of the pollution source and the pollution degree given by the artificial neural network are compensable, the reflected signal of the infrared emitter is compensated according to the compensation algorithm, and a compensation threshold K is given, if the compensated signal is judged to be satisfactory by the artificial neural network, the polling cycle of two minutes is recovered, the instrument resumes working, and the artificial neural network monitors the dynamic adjustment of the compensation threshold K in real time; when the compensation threshold value K is larger than 1, the window pollution condition is considered to be incapable of being compensated through the instrument, and a fault signal code is sent out.
(III) advantageous effects
The invention provides a method for detecting the cleanliness of a window of a multiband flame detector. Compared with the prior art, the method has the following beneficial effects: the method for detecting the cleanliness of the window of the multiband flame detector comprises the following steps of S1: starting an infrared transmitter according to the number of the channels and transmitting an infrared signal; s2, capture signal: after a period of time delay, the pyroelectric sensor starts to capture the reflection model of the infrared emitter, and continuously collects 100 data to form a group, and 100 groups are collected; s3, data processing: according to time domain division, points where the maximum value and the minimum value in each group can occur are divided, wherein the maximum Tmax is found in 18 th to 36 th data, the minimum value Tmin is found in 50 th to 75 th data, the average values of the maximum value and the minimum value are obtained by adopting a sorting method, Tmax _ avg and Tmin _ avg are obtained, and the Tmax _ avg and the Tmin _ avg are written into an EEPROM as reference parameters of the instrument; s4, judging the pollution degree: learning pollution degrees of different pollution sources and a certain pollution source as samples through an artificial neural network, and taking the samples as comparison samples, separating a compensatable pollution source and an uncompensable pollution source according to a compensation algorithm mechanism, simultaneously giving a compensation threshold value K by the compensation algorithm, considering that the K value is reasonable when the K value is in a range of 0-1, considering that the compensation is invalid when the K value exceeds 1, sending a fault indication, and making a decision according to the fault indication; s5, cyclic detection: the method comprises the steps of collecting reflected signals of an infrared emitter by taking two minutes as a polling period, obtaining a maximum value Tmax _ o and a minimum value Tmin _ o of a single signal, shortening the polling period to 30 seconds when the Tmax _ o/Tmax _ avg is less than 0.8 and the Tmin _ o/Tmin _ avg is less than 0.75, judging window pollution by an artificial neural network if the conditions continuously occur for 3 times, providing a compensation mechanism by using an artificial neural network algorithm, improving the durability and reliability of the instrument, reducing the maintenance period of the instrument, reducing labor cost, judging different pollution conditions of different areas of a window by matching with a multi-channel pyroelectric sensor when detecting multiple channels, adjusting the signal gain of each channel by using a dynamic algorithm, and enhancing the fire detection performance of the instrument.
Drawings
FIG. 1 is a flowchart of a method for detecting window cleanliness according to the present invention;
FIG. 2 is a graph of the CHB pyroelectric sensor collecting the signal emitted by the infrared emitter in a single channel according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, an embodiment of the present invention provides a technical solution: a method for detecting the cleanliness of a window of a multiband flame detector specifically comprises the following steps:
s1, turning on an infrared emitter: starting an infrared transmitter according to the number of the channels and transmitting an infrared signal;
s2, capture signal: after a period of time delay, the pyroelectric sensor starts to capture the reflection model of the infrared emitter, and continuously collects 100 data to form a group, and 100 groups are collected;
s3, data processing: according to time domain division, points where the maximum value and the minimum value in each group can occur are divided, wherein the maximum Tmax is found in 18 th to 36 th data, the minimum value Tmin is found in 50 th to 75 th data, the average values of the maximum value and the minimum value are obtained by adopting a sorting method, Tmax _ avg and Tmin _ avg are obtained, and the Tmax _ avg and the Tmin _ avg are written into an EEPROM as reference parameters of the instrument;
s4, judging the pollution degree: learning pollution degrees of different pollution sources and a certain pollution source as samples through an artificial neural network, and taking the samples as comparison samples, separating a compensatable pollution source and an uncompensable pollution source according to a compensation algorithm mechanism, simultaneously giving a compensation threshold value K by the compensation algorithm, considering that the K value is reasonable when the K value is in a range of 0-1, considering that the compensation is invalid when the K value exceeds 1, sending a fault indication, and making a decision according to the fault indication;
s5, cyclic detection: and collecting reflected signals of the infrared emitter by taking two minutes as a polling period, obtaining the maximum value Tmax _ o and the minimum value Tmin _ o of the single signal, shortening the polling period to 30 seconds when the Tmax _ o/Tmax _ avg is less than 0.8 and the Tmin _ o/Tmin _ avg is less than 0.75, and judging the pollution of the window through an artificial neural network if the conditions are continuously present for 3 times.
In the present invention, when the window is clean or contaminated in step S4, 128 feature extractions are performed on the infrared emitter reflection signal curve of the single channel by using the artificial neural network to describe the signal curve.
In the invention, after a certain pollution source is judged in step S4, different pollution degrees of the same pollution source have similar signal curves, but the threshold value and the slope of the signal curve change, the artificial neural network can learn the samples and give out judgment of the pollution degree, and a fault signal is sent out when the pollution degree exceeds a certain pollution degree, so that a pollution information code can be displayed.
In the invention, in step S4, the artificial neural network collects infrared emitter reflection signal samples when the window is clean, the infrared emitter reflection signal samples are used as clean reference samples for learning, various pollution sources which can possibly occur under the simulation field use condition are applied on the window, and the artificial neural network collects infrared emitter reflection signal samples under various pollution sources and is used as various pollution source samples for learning.
In the invention, in step S4, the maximum fire detection capability of the instrument, namely the flame detection distance and the detection visual angle, are obtained through tests or instrument specifications, various pollution sources with three pollution degrees are applied to the surface of a window, an artificial neural network collects infrared emitter reflected signal samples which are used as three pollution degree samples of various pollution sources for learning, and a compensation algorithm mechanism is provided according to comparison samples
In the invention, in step S4, the pollution sources and the pollution degrees of different areas on the surface of the window are comprehensively judged according to the difference of the threshold values of different channels and the criterion of the artificial neural network, and different decisions are given according to the pollution sources and the pollution degrees under different conditions.
In the invention, decision one: the pollution source and the pollution degree damage the fire detection performance of the instrument, the acquired signal cannot be compensated through the instrument to improve the fire detection performance, and a fault signal code is sent to request maintenance; and decision two: the source and level of contamination has compromised the fire detection performance of the meter, but the detection performance can be improved by compensating the acquired signal by the software and hardware of the meter itself. And then, carrying out algorithm compensation on the collected environment infrared signals according to different pollution sources and pollution degrees, and dynamically adjusting the signal gain, weight and threshold of each channel to improve the sensitivity of the instrument to flame, dynamically compensate the fire detection distance and fire detection visual angle, so that the instrument can maintain the fire detection performance. When the software and hardware compensation exceeds the threshold value and the performance of the instrument is inevitably reduced, a fault signal code is sent out to request maintenance.
In the invention, after window pollution is judged by an extreme method in step S5, an artificial neural network intervenes to capture infrared emitter reflection signals at a frequency of 30 seconds, samples are learned through an algorithm to judge the conditions of pollution sources and pollution degrees, if the conditions of the pollution sources and the pollution degrees given by the artificial neural network are compensable, the infrared emitter reflection signals are compensated according to the compensation algorithm, a compensation threshold value K is given, if the compensated signals are judged to be in accordance with the requirements by the artificial neural network, a two-minute routing inspection period is recovered, the instrument resumes working, and the artificial neural network monitors the dynamic adjustment of the compensation threshold value K in real time; when the compensation threshold value K is larger than 1, the window pollution condition is considered to be incapable of being compensated through the instrument, and a fault signal code is sent out.
And those not described in detail in this specification are well within the skill of those in the art.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A method for detecting the cleanliness of a window of a multiband flame detector is characterized by comprising the following steps: the method specifically comprises the following steps:
s1, turning on an infrared emitter: starting an infrared transmitter according to the number of the channels and transmitting an infrared signal;
s2, capture signal: after a period of time delay, the pyroelectric sensor starts to capture the reflection model of the infrared emitter, and continuously collects 100 data to form a group, and 100 groups are collected;
s3, data processing: according to time domain division, points where the maximum value and the minimum value in each group can occur are divided, wherein the maximum Tmax is found in 18 th to 36 th data, the minimum value Tmin is found in 50 th to 75 th data, the average values of the maximum value and the minimum value are obtained by adopting a sorting method, Tmax _ avg and Tmin _ avg are obtained, and the Tmax _ avg and the Tmin _ avg are written into an EEPROM as reference parameters of the instrument;
s4, judging the pollution degree: learning pollution degrees of different pollution sources and a certain pollution source as samples through an artificial neural network, and taking the samples as comparison samples, separating a compensatable pollution source and an uncompensable pollution source according to a compensation algorithm mechanism, simultaneously giving a compensation threshold value K by the compensation algorithm, considering that the K value is reasonable when the K value is in a range of 0-1, considering that the compensation is invalid when the K value exceeds 1, sending a fault indication, and making a decision according to the fault indication;
s5, cyclic detection: and collecting reflected signals of the infrared emitter by taking two minutes as a polling period, obtaining the maximum value Tmax _ o and the minimum value Tmin _ o of the single signal, shortening the polling period to 30 seconds when the Tmax _ o/Tmax _ avg is less than 0.8 and the Tmin _ o/Tmin _ avg is less than 0.75, and judging the pollution of the window through an artificial neural network if the conditions are continuously present for 3 times.
2. The method of claim 1, wherein the method comprises the following steps: in step S4, when the window is clean or contaminated, 128 feature extractions are performed on the infrared emitter reflection signal curve of the single channel by using an artificial neural network to describe the signal curve.
3. The method of claim 1, wherein the method comprises the following steps: after a certain pollution source is determined in step S4, similar signal curves exist for different pollution levels of the same pollution source, but the threshold and the slope of the signal curves change, so that the artificial neural network can learn the samples and give a determination of the pollution level, and a fault signal is sent when the pollution level exceeds a certain pollution level, so that a pollution information code can be displayed.
4. The method of claim 1, wherein the method comprises the following steps: in the step S4, the artificial neural network collects infrared emitter reflection signal samples when the window is clean, and learns as clean reference samples, and applies various pollution sources that may occur in a simulation field usage situation on the window, and the artificial neural network collects infrared emitter reflection signal samples under various pollution sources, and learns as various pollution source samples.
5. The method of claim 1, wherein the method comprises the following steps: in the step S4, the maximum fire detection capability of the instrument, that is, the flame detection distance and the detection viewing angle, are obtained through a test or an instrument specification, various pollution sources with three pollution degrees are applied to the surface of the window, the artificial neural network collects samples of reflected signals of the infrared emitter, the samples are used as samples of the three pollution degrees of the various pollution sources for learning, and a compensation algorithm mechanism is provided according to comparison samples.
6. The method of claim 1, wherein the method comprises the following steps: in the step S4, the pollution sources and the pollution degrees in different areas of the window surface are comprehensively judged according to the difference of the threshold values of different channels and the criterion of the artificial neural network, and different decisions are given for the pollution sources and the pollution degrees under different conditions.
7. The method of claim 6, wherein the method comprises the following steps: the decision one is as follows: the pollution source and the pollution degree damage the fire detection performance of the instrument, the acquired signal cannot be compensated through the instrument to improve the fire detection performance, and a fault signal code is sent to request maintenance; and decision two: the pollution source and the pollution degree damage the fire detection performance of the instrument, but the acquired signals can be compensated through software and hardware of the instrument to improve the fire detection performance, algorithm compensation is carried out on the acquired environment infrared signals according to different pollution sources and pollution degrees, the signal gain, the weight and the threshold of each channel are dynamically adjusted to improve the sensitivity of the instrument to flame, the fire detection distance and the fire detection visual angle are dynamically compensated, the fire detection performance of the instrument can be maintained, and when the software and hardware compensation exceeds the threshold, and the performance of the instrument inevitably decreases, a fault signal code is sent out to request maintenance.
8. The method of claim 1, wherein the method comprises the following steps: after the window pollution is judged by an extreme method in the step S5, an artificial neural network intervenes to capture reflected signals of the infrared emitter at a frequency of 30 seconds, and a sample is learned through an algorithm to judge the conditions of a pollution source and a pollution degree; when the compensation threshold value K is larger than 1, the window pollution condition is considered to be incapable of being compensated through the instrument, and a fault signal code is sent out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537868.0A CN111640278B (en) | 2020-06-12 | 2020-06-12 | Method for detecting cleanliness of window of multiband flame detector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537868.0A CN111640278B (en) | 2020-06-12 | 2020-06-12 | Method for detecting cleanliness of window of multiband flame detector |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111640278A true CN111640278A (en) | 2020-09-08 |
| CN111640278B CN111640278B (en) | 2021-02-09 |
Family
ID=72331760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010537868.0A Active CN111640278B (en) | 2020-06-12 | 2020-06-12 | Method for detecting cleanliness of window of multiband flame detector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111640278B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114112074A (en) * | 2021-12-03 | 2022-03-01 | 无锡格林通安全装备有限公司 | Flame detector light path self-checking method and device and flame detector |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496236A (en) * | 2011-12-27 | 2012-06-13 | 公安部沈阳消防研究所 | Direct-injection type flame detector with self-checking light source and flame detection method |
| CN206340129U (en) * | 2017-01-06 | 2017-07-18 | 上海广域安防科技有限公司 | A kind of typical IR flame detector |
| CN206696198U (en) * | 2017-04-28 | 2017-12-01 | 无锡格林通安全装备有限公司 | Flame detector optical window cleanliness factor detection means |
| US10012545B2 (en) * | 2016-12-07 | 2018-07-03 | Wing Lam | Flame detector with proximity sensor for self-test |
| KR20190120015A (en) * | 2018-04-14 | 2019-10-23 | 장은선 | fire detector robotic vacuum claner |
| CN111105587A (en) * | 2019-12-31 | 2020-05-05 | 广州思瑞智能科技有限公司 | Intelligent flame detection method and device, detector and storage medium |
| CN111134573A (en) * | 2018-11-02 | 2020-05-12 | 添可智能科技有限公司 | Method for improving precision of dust detection sensor |
-
2020
- 2020-06-12 CN CN202010537868.0A patent/CN111640278B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496236A (en) * | 2011-12-27 | 2012-06-13 | 公安部沈阳消防研究所 | Direct-injection type flame detector with self-checking light source and flame detection method |
| US10012545B2 (en) * | 2016-12-07 | 2018-07-03 | Wing Lam | Flame detector with proximity sensor for self-test |
| CN206340129U (en) * | 2017-01-06 | 2017-07-18 | 上海广域安防科技有限公司 | A kind of typical IR flame detector |
| CN206696198U (en) * | 2017-04-28 | 2017-12-01 | 无锡格林通安全装备有限公司 | Flame detector optical window cleanliness factor detection means |
| KR20190120015A (en) * | 2018-04-14 | 2019-10-23 | 장은선 | fire detector robotic vacuum claner |
| CN111134573A (en) * | 2018-11-02 | 2020-05-12 | 添可智能科技有限公司 | Method for improving precision of dust detection sensor |
| CN111105587A (en) * | 2019-12-31 | 2020-05-05 | 广州思瑞智能科技有限公司 | Intelligent flame detection method and device, detector and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114112074A (en) * | 2021-12-03 | 2022-03-01 | 无锡格林通安全装备有限公司 | Flame detector light path self-checking method and device and flame detector |
| CN114112074B (en) * | 2021-12-03 | 2023-11-03 | 无锡格林通安全装备有限公司 | Flame detector light path self-checking method and device and flame detector |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111640278B (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1077992C (en) | Multiple sensor apparatus and method | |
| CN110573857A (en) | High-low frequency multi-core sensor system | |
| JP6442118B1 (en) | Anomaly detector | |
| CN111640278B (en) | Method for detecting cleanliness of window of multiband flame detector | |
| CN1871623A (en) | Multi-sensor device and methods for fire detection | |
| JP4002400B2 (en) | Smoke detection fire detection method of light section image | |
| WO2002069292A8 (en) | Method and device for detecting fires based on image analysis | |
| US20060167640A1 (en) | Apparatus and method for dynamic smoothing | |
| CN1487274A (en) | Infrared source heat image detecting method | |
| CN108538011B (en) | Laser radar fire detection method | |
| CN109489812B (en) | Method for expanding detection visual angle of flame detector | |
| US5838242A (en) | Fire detection system using modulation ratiometrics | |
| JP2003227750A (en) | Flame detector | |
| CN102509404B (en) | Environment compensation type wild-area full-optical fiber disturbance sensing enclosure type security monitoring system | |
| CN112461722A (en) | Smoke particle identification method and system based on temperature compensation and vehicle | |
| JP2020071698A (en) | Fire detection device, fire detection method, and fire monitoring system | |
| CN110500138B (en) | Colliery belt conflagration early warning system in pit | |
| CN111638226B (en) | Detection method, image processor and detection system | |
| FI111666B (en) | Fire alarm system for early detection of fires | |
| CN114112074B (en) | Flame detector light path self-checking method and device and flame detector | |
| CN115389457A (en) | Open type laser gas detection method and system based on variable area phase-locked amplification | |
| CN108169157A (en) | Sulfur hexafluoride compensation method and device | |
| JP2000187786A (en) | Fire detector and soil compensation method for fire detector | |
| CN113362560A (en) | Photoelectric smoke sensing detection method for accurately identifying fire smoke | |
| GB2223844A (en) | Flame detector |
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 |