CN205016036U - Intelligence combustible gas leakage alarm device - Google Patents
Intelligence combustible gas leakage alarm device Download PDFInfo
- Publication number
- CN205016036U CN205016036U CN201520652705.1U CN201520652705U CN205016036U CN 205016036 U CN205016036 U CN 205016036U CN 201520652705 U CN201520652705 U CN 201520652705U CN 205016036 U CN205016036 U CN 205016036U
- Authority
- CN
- China
- Prior art keywords
- alarm
- module
- combustible gas
- data
- gas
- 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.)
- Expired - Fee Related
Links
- 238000012545 processing Methods 0.000 claims abstract description 9
- 239000007789 gas Substances 0.000 claims description 64
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 6
- 239000003034 coal gas Substances 0.000 claims description 5
- 239000011435 rock Substances 0.000 claims description 4
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 3
- 239000001257 hydrogen Substances 0.000 claims description 3
- 229910052739 hydrogen Inorganic materials 0.000 claims description 3
- 230000008447 perception Effects 0.000 abstract description 4
- 230000002567 autonomic effect Effects 0.000 abstract 2
- 238000009434 installation Methods 0.000 abstract 1
- 238000000034 method Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000005070 sampling Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- -1 natural Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
The utility model provides an intelligence combustible gas leakage alarm device, include collection module, data processing module, report an emergency and ask for help or increased vigilance and judge module and autonomic learning module that collection module is used for gathering the combustible gas thickness data, data processing module carries out the preliminary treatment to the data that the device was gathered, report an emergency and ask for help or increased vigilance and judge that the module is used for judging whether smog concentration exceedes the smog concentration alarm threshold value in the current time window, the autonomic learning module is used for adding the sample sequence with sample data, confirms warning decision gate limit value again, solves present combustible gas and reveals the alarm installation and reveal the perception ability and reduce taking place combustible gas when too high, often takes place to miss the problem of reporting an emergency and asking for help or increased vigilance with combustible gas the time.
Description
Technical field
The utility model relates to a kind of gas leakage alarm, particularly a kind of Intelligent combustible gas leakage alarm.
Background technology
Can be there is related device and connect to loosen or do not close the tight inflammable gas that causes and reveals in people, once discovery may cause accident not in time, threaten people's safety of life and property in the process using the combustible gases such as natural, coal gas or liquefied gas; Inflammable gas leak detection is in the market reported to the police and is mainly contained two schemes, scheme one: compared by hardware circuit comparer and certain fixed level, report to the police if exceed this level point regular hour continuously; Scheme two: by inflammable gas smog sensing output level is converted to digital level by AD (digital simulation turns device) converter; Micro-process processes digitized combustable gas concentration, the combustable gas concentration collected and a combustable gas concentration pre-seted is compared, the combustable gas concentration a period of time pre-seted, then reports to the police if be greater than continuously.
Its essence of above-mentioned two schemes is all that the smokescope collecting smokescope and preset value compares; The general Dou Shi producer of this preset value research and develop time at laboratory test calibration out; But the practical application more complicated of product, installing occasion and time in difference has different requirements to inflammable gas leakage alarm to detection sensitivity; Such as when kitchen rock gas or coal gas are cooked, there is fuel combustion insufficient, inflammable gas content is caused to rise, if when the remolding sensitivity now arranging inflammable gas leakage alarm is higher, by generation alarm by mistake, if by sensitivity adjustment to time lower, may cannot the light gas leakage of Timeliness coverage when not cooking.
In sum, current inflammable gas leakage alarm does not possess the ability conformed.
Need to solve and when current inflammable gas leakage alarm is installed too high, perception is revealed to generation inflammable gas and reduce, by the problem that alarm by mistake often occurs during inflammable gas.
Utility model content
The utility model provides a kind of Intelligent combustible gas leakage alarm, solves to reveal perception to generation inflammable gas when current inflammable gas leakage alarm is installed too high and reduce, by the problem that by mistake alarm often occurs during inflammable gas.
A kind of Intelligent combustible gas leakage alarm of the present utility model, comprises acquisition module, data processing module, alarm determination module and autonomous learning module, and acquisition module is for gathering combustable gas concentration data; Data processing module carries out pre-service to the data that device collects; Alarm determination module is for judging whether smokescope exceedes the smokescope alarm threshold value in current time window; Autonomous learning module is used for sampled data to add sample sequence, redefine warning decision gate limit value, solve and when current inflammable gas leakage alarm is installed too high, perception is revealed to generation inflammable gas and reduce, by the problem that by mistake alarm often occurs during inflammable gas.
As preferably, described inflammable gas is rock gas or coal gas or liquefied gas or methane or hydrogen.
Accompanying drawing explanation
Fig. 1 is the utility model Intelligent combustible gas leakage alarm detection method overall procedure schematic diagram;
Fig. 2 is the utility model Intelligent combustible gas leakage alarm detection method detailed process schematic diagram;
Fig. 3 is the utility model Intelligent combustible gas leakage alarm detection method autonomous learning detailed process schematic diagram.
Embodiment
Below will be described an embodiment of the present utility model.
As shown in Figure 1, the utility model Intelligent combustible gas leakage alarm detection method comprises: step 101: device gathers combustable gas concentration; Step 102: pre-service is carried out to the data that device collects; Step 103: to this sampling time slip-window carry out alarm judgement; Step 104: sampled data is added sample sequence, and carry out machine learning.
As described in Figure 2, described Intelligent combustible gas leakage warning device detection method in detail specifically comprises the steps:
Step 201: device gathers combustable gas concentration data, and this inflammable gas comprises rock gas, coal gas, liquefied gas, methane and hydrogen.In every 2 seconds sampling periods, a sampling period samples 10 times, gets average after removing maximal value and minimum value, as the combustable gas concentration data of this sampling.
Step 202: to sampled data smoothing processing, to sampled data and time shift rectangular window function phase multiplication, take out the sample data sequence in current time window, to the smoothing process of data sequence data in current time window, sampling linear fitting and smoothing algorithm, but be not limited only to this algorithm.Described time shift rectangular window function is
wherein τ is the width of window, adopts window width to be 20 seconds in the utility model.
Step 203: judge whether smokescope exceedes the smokescope alarm threshold value in current time window; If exceed alarm threshold value, then go to step 204; If do not exceed alarm threshold value, then go to step 207;
Described alarm threshold value, when device does not complete autonomous learning, adopts producer to calibrate according to national standard test the warning decision gate limit value obtained.After completing autonomous learning, device learns a warning decision gate limit value according to device site environment situation.
Step 204: open local alarm voice and report, and record time and the combustible gas concentration of the generation of alarm.
Step 205: user is confirmed whether effective alarm by the button on device or mobile phone A PP;
Step 206: the alarm that user confirms is recorded to alarm sample queue;
Step 207: the mistake alarm record that user is confirmed alarm sample queue by mistake;
Step 208: run after one day, carries out device autonomous learning in the time that device is subscribed.
As shown in Figure 3, described Intelligent combustible gas leakage warning device detection method autonomous learning specifically comprises following implementation step:
Step 301: with 3 minutes for the time period, was divided into 480 time periods by one day; Obtain the combustable gas concentration average of each time period and the combustable gas concentration average of all day respectively;
Step 302: search the time slice that combustable gas concentration is maximum from each time slice, and this period is labeled as current slot;
Step 303: current slot Cmax is mistake concentration average all day 20% if not, then perform step 304; Otherwise go to step 310;
Step 304: if the concentration of the previous time period of current slot is higher by 10% than concentration average all day, performs step 305, otherwise goes to step 306;
Step 305: current slot and previous time period are merged into current slot, and goes to step 304;
Step 306: if the concentration of a rear time period of current slot is higher by 10% than concentration average all day, performs step 307, otherwise goes to step 308;
Step 307: current slot and a rear time period are merged into current slot, and goes to step 306;
Step 308: the concentration average calculating current slot concentration variance and concentration average maximum segment, and the start and end time of recording period, and be labeled as and use the gas time period;
Step 309: reject current time segment data, go to step 302;
Step 310: whether complete initialization study, described initialization study refer to device dispatch from the factory be installed to scene time, need a period of time to complete environment learning; Do not complete and then perform step 311, complete and then perform step 314.
Step 311: get each period concentration value period concentration value corresponding to today in historical record one by one and compare, select large concentration value to be stored in historical record;
Step 312: whether complete initialization study, if complete study, then performs step 313, does not complete then process ends.
Step 313: get each period concentration value in historical record one by one, takes advantage of the concentration threshold of 1.5 corresponding periods, exceedes national normal value, then substitute with national normal value by value.
Step 314: alarm sample queue exists alarm, then perform step 315, otherwise go to step 318;
Step 315: take out an alarm from alarm sample queue, judges whether alarm time of origin belongs to and uses the gas period; Be then perform step 316 with the gas period, otherwise go to step 317;
Step 316: the concentration threshold concentration threshold of all periods being greater than this alarm event of concentration threshold that this alarm event judges substitutes, and goes to step 314;
Step 317: the concentration threshold concentration threshold of non-gas period being greater than this alarm event of concentration threshold that this alarm event judges carries out substituting and going to step 314;
Step 318: the wrong alarm of alarm sample queue then performs step 319 by mistake, otherwise flow process terminates
Step 319: taking out an alarm by mistake from missing alarm sample queue, judging whether alarm time of origin belongs to the non-gas period by mistake; Be the non-gas period then perform step 320, otherwise go to step 321;
Step 320: all period concentration threshold are less than this alarm event and judge concentration threshold, then add 5% as decision threshold by the concentration average of this alarm event, exceed national normal value, then substitute with national normal value.
Step 321: this alarm event will be less than by concentration threshold in the gas period and judge concentration threshold, then add 5% as decision threshold by the concentration average of this alarm event, exceed national normal value, then substitute with national normal value.
A kind of Intelligent combustible gas leakage alarm, comprise acquisition module, data processing module, alarm determination module and autonomous learning module, acquisition module is for gathering combustable gas concentration data; Data processing module carries out pre-service to the data that device collects; Alarm determination module is for judging whether smokescope exceedes the smokescope alarm threshold value in current time window; Autonomous learning module is used for sampled data to add sample sequence, redefines warning decision gate limit value.
By specific embodiment, the utility model has been described in detail above, but the utility model is not limited to this.Under the prerequisite without prejudice to the utility model spirit, those skilled in the art can make various change and modification to the utility model.
Claims (2)
1. an Intelligent combustible gas leakage alarm, comprises acquisition module, data processing module, alarm determination module and autonomous learning module, and acquisition module is for gathering combustable gas concentration data; Data processing module carries out pre-service to the data that device collects; Alarm determination module is for judging whether smokescope exceedes the smokescope alarm threshold value in current time window; Autonomous learning module is used for sampled data to add sample sequence, redefines warning decision gate limit value.
2. according to Intelligent combustible gas leakage alarm described in claim 1, it is characterized in that: this inflammable gas is rock gas or coal gas or liquefied gas or methane or hydrogen.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201520652705.1U CN205016036U (en) | 2015-08-26 | 2015-08-26 | Intelligence combustible gas leakage alarm device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201520652705.1U CN205016036U (en) | 2015-08-26 | 2015-08-26 | Intelligence combustible gas leakage alarm device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN205016036U true CN205016036U (en) | 2016-02-03 |
Family
ID=55214628
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201520652705.1U Expired - Fee Related CN205016036U (en) | 2015-08-26 | 2015-08-26 | Intelligence combustible gas leakage alarm device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN205016036U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701952A (en) * | 2016-04-19 | 2016-06-22 | 北京小米移动软件有限公司 | Abnormal air alarming method and apparatus |
WO2018023467A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Method for acquiring data when reminding about natural gas leakage, and reminder system |
-
2015
- 2015-08-26 CN CN201520652705.1U patent/CN205016036U/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701952A (en) * | 2016-04-19 | 2016-06-22 | 北京小米移动软件有限公司 | Abnormal air alarming method and apparatus |
US10309673B2 (en) | 2016-04-19 | 2019-06-04 | Beijing Xiaomi Mobile Software Co., Ltd. | Air anomaly alarming method, device and storage medium |
WO2018023467A1 (en) * | 2016-08-02 | 2018-02-08 | 步晓芳 | Method for acquiring data when reminding about natural gas leakage, and reminder system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107179503B (en) | Wind turbine generator fault intelligent diagnosis and early warning method based on random forest | |
CN111024158B (en) | Kitchen electrical hazard intelligent monitoring method combined with edge calculation | |
CN111160616B (en) | Kitchen electrical equipment predictive maintenance system and method based on edge cloud cooperation | |
CN205016036U (en) | Intelligence combustible gas leakage alarm device | |
CN203250384U (en) | Smoke detection alarm system | |
CN110365534B (en) | Automatic chopping and recovery method for intelligent substation communication system | |
CN109347584A (en) | Frequency spectrum sensing method based on Smoothing Prediction | |
Oozeer et al. | Cognitive dynamic system for control and cyber-attack detection in smart grid | |
CN103892830A (en) | Emotion detection method and system based on human skin resistance changes | |
CN112699750A (en) | Safety monitoring method and system for intelligent gas station based on edge calculation and AI (Artificial Intelligence) | |
CN205193523U (en) | Feedback -type incident drive formula analog signal frequency conversion acquisition circuit | |
CN114969027A (en) | Artificial intelligence early warning system and method for forest fire dangerous case | |
CN100370229C (en) | Solitary old protector based on life supplying line | |
Cornes et al. | A reappraisal of the thermal growing season length across Europe | |
CN117807550A (en) | Intelligent quantitative detection method and system for building fire-fighting facilities | |
CN108806702B (en) | Detection method and device for ultrasonic voice hidden attack | |
Guohua et al. | Research on non-intrusive load monitoring based on random forest algorithm | |
CN113298175B (en) | Method and system for monitoring power consumption of solitary old people based on multiple scenes and multiple data | |
CN114759558A (en) | Non-invasive online rapid detection method for charging load of electric bicycle | |
CN114666236A (en) | Full-automatic signal detection, identification and alarm method | |
CN113970409A (en) | Liquefied gas leakage monitoring method and device based on time-frequency domain analysis | |
Odoi et al. | The use of principal component regression and time series analysis to predict nitrous oxide emissions in Ghana | |
CN111724575B (en) | Capacitive overflow detection alarm method | |
CN213485078U (en) | Biomass factory anaerobic fermentation intelligence cabinet | |
CN109631110B (en) | Oil absorption system capable of identifying harmful substances in oil smoke |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160203 |