CN103512922A - Electrical fire detection system and method based on electronic nose system - Google Patents
Electrical fire detection system and method based on electronic nose system Download PDFInfo
- Publication number
- CN103512922A CN103512922A CN201310333115.8A CN201310333115A CN103512922A CN 103512922 A CN103512922 A CN 103512922A CN 201310333115 A CN201310333115 A CN 201310333115A CN 103512922 A CN103512922 A CN 103512922A
- Authority
- CN
- China
- Prior art keywords
- sensor
- gas
- chamber
- data
- solenoid valve
- 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
Images
Landscapes
- Fire Alarms (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The invention relates to an electronic fire detection system and method based on electronic nose system to solve the problems that the prior art cannot determine the type of fire or effectively extinguish. A device comprises a gas recovery unit, a processing unit and a control unit. The gas recovery unit comprises a gas recovery straw and a sensor array; one end of the gas recovery straw is communicated with the outside, and the other end is connected to the chamber of each sensor; and each sensor is respectively connected to the processing unit. The invention has the following advantages: an electronic nose system is constructed to detect sampling gas and to determine the type of fire, so as to guide the fire department for quick selection of an effective fire extinguishing agent, and the system can be used as early-warning system for usual fire; and the electronic nose is composed of multiple types of sensors, and each sensor is located in an independent chamber to test the samples, in order to avoid mutual interferences of multiple sensors in a same box, improve the detection accuracy and realize fastness and good repeatability.
Description
Technical field
The present invention relates to a kind of technology to gas composition analysis, especially relate to the electrical fire detection system based on electric nasus system, and the electrical fire detection method based on electric nasus system.
Background technology
Along with the development of modern science and technology, there is great variety in people's living standard, and electric energy has correspondingly obtained develop and useining widely.Human society had both been benefited in the application of electric energy, also to the mankind, had brought the danger of electric shock and electrical fire accident simultaneously.In the eighties, the 15%, whole world that China's electrical fire accounts for fire sum accounts for the 3rd.
Electrical fire generally refers to the heat energy discharging due to electric wiring, consumer, utensil and breaking down property of power supplying and distributing equipment; As the energy of high temperature, electric arc, electric spark and the release of non-fault; As the red-hot surface of electric heating appliance, possessing the fire that ignites body or other combustibles under burning condition and cause, also comprise the fire being caused by thunder and lightning and static.
In recent years along with electric energy is develop and useedd widely, no matter be in rural area or in cities and towns, electrical fire is all surging, account for the more than 20% of fire sum, risen to No. 1 in the world.In electrical fire, electric wiring fire accounts for 60%, and low-voltage electrical circuit fire accounts for the more than 90% of electric wiring fire.The flame-retardant cable of the most of employing of China's electrical cable at present, flame-retardant cable type comprises again silicon rubber skin, Polyvinylchloride, neoprene, rubber peel etc., when the circuit fire of the dissimilar cable initiation of reply, if only adopt the fire extinguishing agent of single type, the effect of sometimes putting out a fire is also bad.
Therefore when the situation of reply electric wiring fire, be necessary to invent a kind of by gas componant being analyzed and can being judged it is the fire which kind of type causes, make it possible to instruct fire department to select fast efficient fire-extinguishing chemical, and can be as the early warning of fire early-warning system at ordinary times.
Summary of the invention
The present invention solves the existing fire that cannot judge which kind of type causes of prior art, and the problem that can not effectively put out a fire, provides a kind of electrical fire detection system and the method based on electric nasus system that can differentiate fire type.
Above-mentioned technical matters of the present invention is mainly solved by following technical proposals: a kind of electrical fire detection system based on electric nasus system, comprise gas production unit, processing unit and control module, described gas production unit comprises gas production suction pipe and the sensor array consisting of some sensors, each sensor setting is one independently in chamber, described gas production suction pipe one end is in communication with the outside, on this end, be provided with the first solenoid valve, on gas production suction pipe, be provided with the first air pump, the gas production suction pipe other end is connected respectively on the chamber of each sensor, each sensor is connected on processing unit, the first solenoid valve, the first air pump is connected on control module.The gas gathering is entered into respectively in the chamber of each sensor by gas production suction pipe, and sensor detects gas, and detection data are sent to processing unit.The chamber at each sensor place is independent, has avoided a plurality of sensors to coexist a Room and has formed mutual interference, improves accuracy of detection.Sample to gas in gas production unit, output signal is to processing unit, and processing unit carries out analyzing and processing to signal, analyzes the type of initiation fire.Control module is controlled the work of the first solenoid valve, the first air pump, sensor executive component, has made the step of gas production, detection gas.
As a kind of preferred version, described gas production suction pipe is in communication with the outside by gas collection unit, described gas collection unit comprises air chamber, sampler chamber, the first communicating pipe and the second communicating pipe, air chamber and sampler chamber all have import and outlet, be connected to described the first communicating pipe between air chamber outlet and sampler chamber entrance, be connected to described the second communicating pipe between air chamber entrance and sampler chamber outlet, make air chamber and sampler chamber form the circulation path of a hollow, in described gas compartment, be provided with carrier gas air intake opening, on carrier gas air intake opening, be provided with the second solenoid valve, on the second communicating pipe, be provided with gas outlet, on gas outlet, be provided with the solenoid valve of giving vent to anger, on sampler chamber, be also provided with sample gas air intake opening, the inlet end of described gas production suction pipe is connected on air chamber, the described solenoid valve of giving vent to anger is connected on control module.Gas collection unit carries out pre-service to the gas gathering, and gas is circulated and makes gas mixing more even, and the data that the gas gathering after processing detects are more accurate.This sample gas is passed into by sampler chamber, carrier gas is passed into by air chamber, carrier gas can also adopt various ways, can be pure air, filtered air or inert gas, by the first communicating pipe and the second communicating pipe, carrier gas is circulated between air chamber and sample chamber, drive sample sample gas to circulate together.Set out gas port emission gases, for gas collection unit is cleaned to use.
As a kind of preferred version, on the second communicating pipe between described air chamber and gas outlet, be provided with the 3rd solenoid valve, on the second communicating pipe, be also provided with the second air pump, described the 3rd solenoid valve and the second air pump are connected on control module.The 3rd solenoid valve is set and facilitates emission gases, when the 3rd closed electromagnetic valve, formed the independent route to the first communicating pipe, sample chamber, the second communicating pipe, gas outlet by air chamber, easy to exhaust.Air pump is for driving gas.
As a kind of preferred version, on the chamber of each sensor, be also connected with detergent line, in detergent line, be provided with the 4th solenoid valve and the 3rd air pump.For sensor is cleaned.
As a kind of preferred version, described sensor has 8, is respectively sulfide gas sensor, hydrogen gas sensor, ammonia gas sensor, NOx sensor, charcoal hydrogen component gas sensor, ethanol sensor, benzene class sensor and alkanes sensor.
An electrical fire detection method for electric nasus system, comprises the following steps:
Step 1: the sensor array to gas production unit cleans, is passed into pure air in the chamber of each sensor, and operation 8-12min, makes each sensor in original state;
Step 2: gather gas by gas production suction pipe, gas is drained in the chamber of each sensor, control each sensor the gas in chamber is detected by control module, be 40-60s detection time, and each sensor sends to processing unit by the information detecting;
Step 3: processing unit is processed the response curve that obtains each sensor to information, and at 30 points of each response curve up-sampling, the data that each curve sampling is obtained are as sampled data W, sampled data W substitution non-linear stochastic resonance model is calculated to signal to noise ratio snr, and this non-linear stochastic resonance model algorithm is as follows:
Stochastic resonance system comprises three factors: bistable system, and descriptive system feature carried out by power-actuated overdamping Brownian movement of cycle particle with one in input signal and external noise source in bistable state potential well,
V (x) is non-linear symmetric potential function, and ξ (t) is white Gaussian noise, and its auto-correlation connection function is: E[ξ (t) ξ (0)]=2D δ (t), a is input signal strength, f
0be frequency modulating signal, D is noise intensity, and a, b are all real parameters,
Therefore above formula can change into:
Obtaining signal to noise ratio (S/N ratio) is:
S (ω) is signal spectral density, S
n(Ω) be the noise intensity in signal frequency range;
Get this signal to noise ratio (S/N ratio) peak of curve as signal to noise ratio (S/N ratio) eigenwert;
Step 4: bring input variable into a kind of Nonlinear state space model
In formula:
σ is input variable, signal to noise ratio (S/N ratio) eigenwert, ε be intermediate transfer parameter, τ be initial phase,
for output variable, κ are that real parameter, η are that real parameter, Γ are the real parameter of correcting,
Then define residual error variable:
Defining classification master pattern again:
In formula, L is data length, and just Δ is compared with each threshold value Thr in predefined threshold library, if had
, can judge that tested gas is fire type under this threshold value, if
, need to re-start type judgement.
As a kind of preferred version, each threshold value of described threshold library is for obtaining in advance, its process is: in combined electrical apparatus cabinet, adopt current overload mode to form the analog case of various electrical fires, then mobile air is distributed to detection system, use detection system to detect the gas of every kind of electrical fire, detecting data input accidental resonance model, analyze, obtain signal to noise ratio (S/N ratio) eigenwert, again the gas of every kind of electrical fire is taken multiple measurements, get the mean value of the signal to noise ratio (S/N ratio) eigenwert that such sample repeatedly obtains as the threshold value Thr of such sample of judgement, the threshold value of all kinds of samples has formed threshold library jointly.
As a kind of preferred version, in step 3, to each response curve up-sampling, be stochastic sampling or in the sampling of each response curve equal intervals.
As a kind of preferred version, before being calculated to to-noise ratio, sampled data in step 3 is first normalized, processing procedure is: the data that each sensor response curve is sampled are as one group of detection data, by every group of sampled value substitution formula y=log detecting in data
10(x) calculate, x is the sampled value before normalized.
As a kind of preferred version, before being normalized, every group of detection data first carry out dealing of abnormal data, the steps include: that every group of sampled value W detecting in data meets normal distribution: W~N (μ, σ
2), μ is the average of sampled value W in every group of data, σ is the standard deviation of sampled value W in every group of data, through deriving, has:
P(|W-μ|>3σ)≤2-2Φ(3)=0.003
By the average μ of every group of data, standard deviation sigma and each sampled value W substitution formula | W-μ | > 3 σ, will meet formula | W-μ | the sampled value W of > 3 σ removes as abnormal data.
Therefore, advantage of the present invention is: built electric nasus system, by system, sample gas has been detected, can judge it is the fire which kind of type causes, make it possible to instruct fire department to select fast efficient fire-extinguishing chemical, and can be as the early warning of fire early-warning system at ordinary times; 2. the Electronic Nose that adopts polytype sensor to form, each sensor is all located at independently and in chamber, sample is detected, and has avoided a plurality of sensors to coexist one case and has formed phase mutual interference, has improved accuracy of detection, quick, reproducible.
Accompanying drawing explanation
Accompanying drawing 1 is a kind of structural representation of gas production unit in the present invention;
Accompanying drawing 2 is a kind of framework schematic diagram that in the present invention, unit is connected with sensor, air pump;
Accompanying drawing 3 is a kind of structural representations of gas collection unit in the present invention.
1-gas production unit 2-processing unit 3-control module 4-gas production suction pipe 5-sensor 6-chamber 7-first solenoid valve 8-first air pump 9-gas collection unit 10-air chamber 11-sampler chamber 12-the first communicating pipe 13-the second communicating pipe 14-the second solenoid valve 15-carrier gas air intake opening 16-gas outlet 17-solenoid valve 18-sample gas air intake opening 19-the 5th solenoid valve 20-the 3rd solenoid valve 21-the second air pump 22-the 4th solenoid valve 23-the 3rd air pump of giving vent to anger
Embodiment
Below by embodiment, and by reference to the accompanying drawings, technical scheme of the present invention is described in further detail.
Embodiment:
A kind of electrical fire detection system based on electric nasus system of the present embodiment, as shown in Figure 1 and Figure 2, includes gas production unit 1, processes the processing unit 2 that detects data and the control module 3 of controlling executable operations.
The sensor array that gas production unit 1 includes gas production suction pipe 4 and consists of 8 sensors 5, this gas production suction pipe one end is in communication with the outside, and on this end of gas production suction pipe, is provided with the first solenoid valve 7 and the first air-breathing air pump 8 of driving of controlling switching.Here 8 sensors are respectively sulfide gas sensor, hydrogen gas sensor, ammonia gas sensor, NOx sensor, charcoal hydrogen component gas sensor, ethanol sensor, benzene class sensor and alkanes sensor, each sensor is separately positioned on one independently in chamber 6, and the other end of this gas production suction pipe is connected to respectively in the separate chamber of each sensor.On the chamber of each sensor, be also connected with detergent line, in detergent line, be provided with the 4th solenoid valve 22 and the 3rd air pump 23.
In order to make sample gas more even, further improve accuracy of detection, gas production suction pipe is in communication with the outside by gas collection unit 9, as shown in Figure 3, gas collection unit comprises air chamber 10, sampler chamber 11, the first communicating pipe 12 and the second communicating pipe 13, air chamber and sampler chamber all have import and outlet, be connected to the first communicating pipe between air chamber outlet and sampler chamber entrance, be connected to the second communicating pipe between air chamber entrance and sampler chamber outlet, make air chamber and sampler chamber form the circulation path of a hollow, on the second communicating pipe 13 between air chamber 10Yu gas outlet, be provided with the 3rd solenoid valve 20, on the second communicating pipe, be also provided with the second air pump 21, in gas compartment, be provided with carrier gas air intake opening 15, on carrier gas air intake opening, be provided with the second solenoid valve 14, on the second communicating pipe, be provided with gas outlet 16, on gas outlet, be provided with the solenoid valve 17 of giving vent to anger, on sampler chamber, be also provided with sample gas air intake opening 18, on sample gas air intake opening, be provided with the 5th solenoid valve 19, the inlet end of gas production suction pipe is connected on air chamber.
Processing unit 2 is processed the data that each sensor detects, and as shown in Figure 1, each sensor is all connected on processing unit.
As shown in Figure 2, each sensor of gas production unit is controlled being connected on control module also, and control module is controlled working sensor.In addition, the first solenoid valve, the second solenoid valve, the 3rd solenoid valve, the 4th solenoid valve, the 5th solenoid valve, the first air pump, the second air pump, the 3rd air pump and all controlled being connected on control module of solenoid valve of giving vent to anger, control module is controlled their work, to complete gas collection, gas production process.
The electrical fire detection method of the present embodiment based on electric nasus system, comprises the following steps:
Step 1: first the sensor array of gas production unit is cleaned, close the first solenoid valve, open the 4th solenoid valve, pure air is passed in the chamber of each sensor, operation 10min, makes each sensor in original state.
Step 2: gather gas by gas production suction pipe, open the first solenoid valve, flow into extraneous sample gas, sample gas is drained in the chamber of each sensor, by control module, controlling each sensor detects the gas in chamber, be 50s detection time, and each sensor sends to processing unit by the information detecting;
If adopt gas collection unit, before gas production, first gas collection unit is cleaned, open the solenoid valve of giving vent to anger, the second solenoid valve, close the 3rd solenoid valve, pass into carrier gas Bing You gas outlet and discharge, until be full of carrier gas in gas collection unit, then close the solenoid valve of giving vent to anger, the second solenoid valve, open the 3rd solenoid valve and the 5th solenoid valve, pass into sample gas, by the second air pump, drive the sample gas 20s that circulates in gas collection unit again, and then gather gas by gas production suction pipe.
Step 3: the information that processing unit detects each sensor is processed, using time and response intensity as coordinate axis, obtain the response curve of each sensor, 8 sensors obtain 8 bar response curves, then equidistantly at 30 points of each response curve up-sampling, obtain 240 each point data, the data that each curve sampling is obtained are as sampled data W.
Step 4: sampled data is carried out to dealing of abnormal data, and the data that each sensor response curve is sampled are as one group of detection data, and every group of sampled value W detecting in data meets normal distribution: W~N (μ, σ
2), μ is the average of sampled value W in every group of data, σ is the standard deviation of sampled value W in every group of data, through deriving, has:
P(|W-μ|>3σ)≤2-2Φ(3)=0.003
By the average μ of every group of data, standard deviation sigma and each sampled value W substitution formula | W-μ | > 3 σ, will meet formula | W-μ | the sampled value W of > 3 σ removes as abnormal data.
Step 5: sampled data is first normalized, by every group of sampled value substitution formula y=log detecting in data
10(x) calculate, x is the sampled value before normalized.
Step 6: sampled data W substitution non-linear stochastic resonance model is calculated to signal to noise ratio snr, and this non-linear stochastic resonance model algorithm is as follows:
Stochastic resonance system comprises three factors: bistable system, and descriptive system feature carried out by power-actuated overdamping Brownian movement of cycle particle with one in input signal and external noise source in bistable state potential well,
V (x) is non-linear symmetric potential function, and ξ (t) is white Gaussian noise, and its auto-correlation connection function is: E[ξ (t) ξ (0)]=2D δ (t), a is input signal strength, f
0be frequency modulating signal, D is noise intensity, and a, b are all real parameters,
Therefore above formula can change into:
Obtaining signal to noise ratio (S/N ratio) is:
S (ω) is signal spectral density, S
n(Ω) be the noise intensity in signal frequency range;
Get this signal to noise ratio (S/N ratio) peak of curve as signal to noise ratio (S/N ratio) eigenwert;
Step 4: bring input variable into a kind of Nonlinear state space model
In formula:
σ is input variable, signal to noise ratio (S/N ratio) eigenwert, ε be intermediate transfer parameter, τ be initial phase,
for output variable, κ are that real parameter, η are that real parameter, Γ are the real parameter of correcting,
Then define residual error variable:
Defining classification master pattern again:
In formula, L is data length, and just Δ is compared with each threshold value Thr in predefined threshold library, if had
, can judge that tested gas is fire type under this threshold value, if
, need to re-start type judgement.
Wherein above-mentioned each threshold value of the threshold library of mentioning is for obtaining in advance, its process is: in combined electrical apparatus cabinet, adopt current overload mode to form the analog case of various electrical fires, then mobile air is distributed to detection system, use detection system to detect the gas of every kind of electrical fire, detecting data input accidental resonance model, analyze, obtain signal to noise ratio (S/N ratio) eigenwert, again the gas of every kind of electrical fire is taken multiple measurements, get the mean value of the signal to noise ratio (S/N ratio) eigenwert that such sample repeatedly obtains as the threshold value Thr of such sample of judgement, the threshold value of all kinds of samples has formed threshold library jointly.
Specific embodiment described herein is only to the explanation for example of the present invention's spirit.Those skilled in the art can make various modifications or supplement or adopt similar mode to substitute described specific embodiment, but can't depart from spirit of the present invention or surmount the defined scope of appended claims.
Although more used the terms such as gas collection unit, air chamber, sample chamber, the first communicating pipe, the second communicating pipe herein, do not got rid of the possibility of using other term.Use these terms to be only used to describe more easily and explain essence of the present invention; They are construed to any additional restriction is all contrary with spirit of the present invention.
Claims (10)
1. the electrical fire detection system based on electric nasus system, it is characterized in that: comprise gas production unit (1), processing unit (2) and control module (3), described gas production unit (1) comprises gas production suction pipe (4) and the sensor array consisting of some sensors (5), each sensor setting is one independently in chamber (6), described gas production suction pipe one end is in communication with the outside, on this end, be provided with the first solenoid valve (7), on gas production suction pipe, be provided with the first air pump (8), the gas production suction pipe other end is connected respectively on the chamber of each sensor, each sensor is connected on processing unit (2), the first solenoid valve, the first air pump is connected on control module.
2. a kind of electrical fire detection system based on electric nasus system according to claim 1, it is characterized in that described gas production suction pipe is in communication with the outside by gas collection unit (9), described gas collection unit comprises air chamber (10), sampler chamber (11), the first communicating pipe (12) and the second communicating pipe (13), air chamber and sampler chamber all have import and outlet, be connected to described the first communicating pipe between air chamber outlet and sampler chamber entrance, be connected to described the second communicating pipe between air chamber entrance and sampler chamber outlet, make air chamber and sampler chamber form the circulation path of a hollow, in described gas compartment, be provided with carrier gas air intake opening (15), on carrier gas air intake opening, be provided with the second solenoid valve (14), on the second communicating pipe, be provided with gas outlet (16), on gas outlet, be provided with the solenoid valve of giving vent to anger (17), on sampler chamber, be also provided with sample gas air intake opening (18), on sample gas air intake opening, be provided with the 5th solenoid valve (19), the inlet end of described gas production suction pipe is connected on air chamber, described solenoid valve and the 5th solenoid valve of giving vent to anger is connected on control module (3).
3. a kind of electrical fire detection system based on electric nasus system according to claim 2, it is characterized in that being provided with the 3rd solenoid valve (20) on the second communicating pipe (13) between described air chamber (10) and gas outlet, on the second communicating pipe, be also provided with the second air pump (21), described the 3rd solenoid valve and the second air pump are connected on control module (3).
4. a kind of electrical fire detection system based on electric nasus system according to claim 1, is characterized in that on the chamber of each sensor, being also connected with detergent line, is provided with the 4th solenoid valve (22) and the 3rd air pump (23) in detergent line.
5. a kind of electrical fire detection system based on electric nasus system according to claim 1, it is characterized in that described sensor (5) has 8, be respectively sulfide gas sensor, hydrogen gas sensor, ammonia gas sensor, NOx sensor, charcoal hydrogen component gas sensor, ethanol sensor, benzene class sensor and alkanes sensor.
6. the electrical fire detection method based on electric nasus system, is characterized in that: comprise the following steps:
Step 1: the sensor array to gas production unit cleans, is passed into pure air in the chamber of each sensor, and operation 8-12min, makes each sensor in original state;
Step 2: gather gas by gas production suction pipe, gas is drained in the chamber of each sensor, control each sensor the gas in chamber is detected by control module, be 40-60s detection time, and each sensor sends to processing unit by the information detecting;
Step 3: processing unit is processed the response curve that obtains each sensor to information, and at 30 points of each response curve up-sampling, the data that each curve sampling is obtained are as sampled data W, sampled data W substitution non-linear stochastic resonance model is calculated to signal to noise ratio snr, and this non-linear stochastic resonance model algorithm is as follows:
Stochastic resonance system comprises three factors: bistable system, and descriptive system feature carried out by power-actuated overdamping Brownian movement of cycle particle with one in input signal and external noise source in bistable state potential well,
V (x) is non-linear symmetric potential function, and ξ (t) is white Gaussian noise, and its auto-correlation connection function is: E[ξ (t) ξ (0)]=2D δ (t), a is input signal strength, f
0be frequency modulating signal, D is noise intensity, and a, b are all real parameters,
Therefore above formula can change into:
Obtaining signal to noise ratio (S/N ratio) is:
S (ω) is signal spectral density, S
n(Ω) be the noise intensity in signal frequency range;
Get this signal to noise ratio (S/N ratio) peak of curve as signal to noise ratio (S/N ratio) eigenwert;
Step 4: bring input variable into a kind of Nonlinear state space model
In formula:
σ is input variable, signal to noise ratio (S/N ratio) eigenwert, ε be intermediate transfer parameter, τ be initial phase,
for output variable, κ are that real parameter, η are that real parameter, Γ are the real parameter of correcting,
Then define residual error variable:
Defining classification master pattern again:
7. a kind of electrical fire detection method based on electric nasus system according to claim 1, it is characterized in that each threshold value of described threshold library is for obtaining in advance, its process is: in combined electrical apparatus cabinet, adopt current overload mode to form the analog case of various electrical fires, then mobile air is distributed to detection system, use detection system to detect the gas of every kind of electrical fire, detecting data input accidental resonance model, analyze, obtain signal to noise ratio (S/N ratio) eigenwert, again the gas of every kind of electrical fire is taken multiple measurements, get the mean value of the signal to noise ratio (S/N ratio) eigenwert that such sample repeatedly obtains as the threshold value Thr of such sample of judgement, the threshold value of all kinds of samples has formed threshold library jointly.
8. a kind of electrical fire detection method based on electric nasus system according to claim 7, is characterized in that in step 3 that to each response curve up-sampling be stochastic sampling or in each response curve equal intervals sampling.
9. a kind of electrical fire detection method based on electric nasus system according to claim 7, before it is characterized in that the sampled data in step 3 is calculated to to-noise ratio, be first normalized, processing procedure is: the data that each sensor response curve is sampled are as one group of detection data, by every group of sampled value substitution formula y=log detecting in data
10(x) calculate, x is the sampled value before normalized.
10. a kind of electrical fire detection method based on electric nasus system according to claim 9, before it is characterized in that every group of detection data to be normalized, first carry out dealing of abnormal data, the steps include: that every group of sampled value W detecting in data meets normal distribution: W~N (μ, σ
2), μ is the average of sampled value W in every group of data, σ is the standard deviation of sampled value W in every group of data, through deriving, has:
P(|W-μ|>3σ)≤2-2Φ(3)=0.003
By the average μ of every group of data, standard deviation sigma and each sampled value W substitution formula | W-μ | > 3 σ, will meet formula | W-μ | the sampled value W of > 3 σ removes as abnormal data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310333115.8A CN103512922A (en) | 2013-08-01 | 2013-08-01 | Electrical fire detection system and method based on electronic nose system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310333115.8A CN103512922A (en) | 2013-08-01 | 2013-08-01 | Electrical fire detection system and method based on electronic nose system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103512922A true CN103512922A (en) | 2014-01-15 |
Family
ID=49895981
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310333115.8A Pending CN103512922A (en) | 2013-08-01 | 2013-08-01 | Electrical fire detection system and method based on electronic nose system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103512922A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105806417A (en) * | 2016-05-06 | 2016-07-27 | 中科同德(北京)生态科技有限公司 | Detection air duct of indoor air environment monitoring equipment |
CN105823515A (en) * | 2016-05-06 | 2016-08-03 | 中科同德(北京)生态科技有限公司 | Indoor air environment monitoring equipment |
CN109562585A (en) * | 2016-09-30 | 2019-04-02 | 米其林集团总公司 | The method leaked by odor detection tire-mold bladder |
CN109633096A (en) * | 2018-12-30 | 2019-04-16 | 盐城工学院 | A kind of double gas chamber electronic noses |
CN110363950A (en) * | 2019-08-06 | 2019-10-22 | 北京数雨如歌智能科技有限公司 | A kind of intelligent fire classification managing and control system |
CN111784981A (en) * | 2020-08-03 | 2020-10-16 | 国网山东省电力公司寿光市供电公司 | Multifunctional intelligent monitoring equipment for cable tunnel |
CN113791128A (en) * | 2021-11-16 | 2021-12-14 | 南京尚中过滤与分析设备有限公司 | Safety alarm system and method for gas concentration in converter gas |
CN114104898A (en) * | 2020-08-26 | 2022-03-01 | 奥的斯电梯公司 | Elevator smoke and fire detection system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2540633Y (en) * | 2002-06-04 | 2003-03-19 | 复旦大学 | Structure of portable intelligence electronic noise |
CN101042408A (en) * | 2007-04-10 | 2007-09-26 | 浙江大学 | Portable electric nose system based on USB interface |
CN101893591A (en) * | 2010-06-24 | 2010-11-24 | 浙江大学 | Electronic nose system for banana quality detection |
CN102297878A (en) * | 2011-05-19 | 2011-12-28 | 浙江清华长三角研究院 | Electronic nose system for rapid detection of pollution of volatile chlorinated hydrocarbons |
-
2013
- 2013-08-01 CN CN201310333115.8A patent/CN103512922A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2540633Y (en) * | 2002-06-04 | 2003-03-19 | 复旦大学 | Structure of portable intelligence electronic noise |
CN101042408A (en) * | 2007-04-10 | 2007-09-26 | 浙江大学 | Portable electric nose system based on USB interface |
CN101893591A (en) * | 2010-06-24 | 2010-11-24 | 浙江大学 | Electronic nose system for banana quality detection |
CN102297878A (en) * | 2011-05-19 | 2011-12-28 | 浙江清华长三角研究院 | Electronic nose system for rapid detection of pollution of volatile chlorinated hydrocarbons |
Non-Patent Citations (1)
Title |
---|
尹芳缘 等: "基于电子鼻的芒果储存时间预测方法研究", 《传感技术学报》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105806417A (en) * | 2016-05-06 | 2016-07-27 | 中科同德(北京)生态科技有限公司 | Detection air duct of indoor air environment monitoring equipment |
CN105823515A (en) * | 2016-05-06 | 2016-08-03 | 中科同德(北京)生态科技有限公司 | Indoor air environment monitoring equipment |
CN109562585A (en) * | 2016-09-30 | 2019-04-02 | 米其林集团总公司 | The method leaked by odor detection tire-mold bladder |
CN109633096A (en) * | 2018-12-30 | 2019-04-16 | 盐城工学院 | A kind of double gas chamber electronic noses |
CN110363950A (en) * | 2019-08-06 | 2019-10-22 | 北京数雨如歌智能科技有限公司 | A kind of intelligent fire classification managing and control system |
CN111784981A (en) * | 2020-08-03 | 2020-10-16 | 国网山东省电力公司寿光市供电公司 | Multifunctional intelligent monitoring equipment for cable tunnel |
CN114104898A (en) * | 2020-08-26 | 2022-03-01 | 奥的斯电梯公司 | Elevator smoke and fire detection system |
CN113791128A (en) * | 2021-11-16 | 2021-12-14 | 南京尚中过滤与分析设备有限公司 | Safety alarm system and method for gas concentration in converter gas |
CN113791128B (en) * | 2021-11-16 | 2022-02-01 | 南京尚中过滤与分析设备有限公司 | Safety alarm system and method for gas concentration in converter gas |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103512922A (en) | Electrical fire detection system and method based on electronic nose system | |
US11489490B2 (en) | Arc fault detection method for photovoltaic system based on adaptive kernel function and instantaneous frequency estimation | |
CN103913663B (en) | Online detection method and protection device for direct current system arc faults | |
CN102288857B (en) | Fault arc identification and detection method and detection protection device | |
CN104569684B (en) | A kind of fault arc detection method based on arc spectrum signal | |
CN104125112B (en) | Physical-information fuzzy inference based smart power grid attack detection method | |
CN105403816A (en) | Identification method of DC fault electric arc of photovoltaic system | |
SE0101526D0 (en) | System, apparatus and method for diagnosing flow processes | |
CN104267343A (en) | Method and device for diagnosing failure state of circuit breaker | |
CN106370960B (en) | Mine power grid electric leakage identification method based on fault instantaneous positive sequence current real part component | |
CN202033865U (en) | Ultraviolet and infrared composite flame detector | |
CN104237777A (en) | Support vector machine high-voltage circuit breaker fault diagnosis method based on core principal component analysis | |
CN104251976B (en) | A kind of operation method of the protection feature test device of miniature circuit breaker | |
CN105954695A (en) | Synchronization-based homogeneous-sensor mutation parameter recognizing method and device | |
CN105866635B (en) | A kind of fault electric arc detection method and device | |
CN105335759A (en) | Transformer fault detection method based on probability model generation | |
CN103512921A (en) | Intelligent electronic nose system based device and method for analyzing freshness of pear | |
CN103970129B (en) | Control valve viscous detection method | |
CN206331127U (en) | The node type seismic prospecting instrument of wave detector state is monitored in real time | |
CN107843788A (en) | A kind of method for diagnosing faults that oil-immersed type transformer is carried out using characteristic gas | |
CN205541252U (en) | Electric fire detector of taking short circuit, opening circuit and report to police | |
CN109756189B (en) | A kind of detection of photovoltaic array communication failure and localization method | |
CN105022864A (en) | System test point selecting method based on extended dependence matrix | |
CN115267450A (en) | Direct-current arc fault detection method and device | |
CN104484968A (en) | Method, device and system for human detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20160706 |
|
C20 | Patent right or utility model deemed to be abandoned or is abandoned |