CN108492506A - A kind of inside fire early warning method and system of multisource data fusion - Google Patents
A kind of inside fire early warning method and system of multisource data fusion Download PDFInfo
- Publication number
- CN108492506A CN108492506A CN201810357079.1A CN201810357079A CN108492506A CN 108492506 A CN108492506 A CN 108492506A CN 201810357079 A CN201810357079 A CN 201810357079A CN 108492506 A CN108492506 A CN 108492506A
- Authority
- CN
- China
- Prior art keywords
- temperature
- moment
- value
- indoor temperature
- cigarette sense
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
- G08B29/188—Data fusion; cooperative systems, e.g. voting among different detectors
Abstract
The invention discloses a kind of inside fire early warning methods of multisource data fusion, are related to fire monitoring field, including：Scanning obtains indoor temperature；Scan or obtain indoor smog image and/or smokescope；If the indoor temperature at a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting, the alarm condition probability value of decision sample is calculated according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smokescope；The trusting degree of the alarm condition is calculated using the alarm condition probability value of the decision sample and according to Dempster composition rules；Judge alert status according to the magnitude relationship of the trusting degree and preset thresholding.And a kind of inside fire early warning system of multisource data fusion.It can solve the problems, such as that current Initial Stage of Fire ignition point monitoring is difficult and fire alarm is inaccurate.
Description
Technical field
The present invention relates to fire monitoring field, the inside fire early warning method of specifically a kind of multisource data fusion
And system.
Background technology
With the fast development of China's economy, living standard, life style and the rhythm of life of the people are all changing,
In life, also obviously increased therewith with fire, electricity consumption, gas consumption.
Investigation finds that although many storages and building are mounted with fire alarm installation, but still cause heavy losses.
To find out its cause, the monitoring mode that mainly its fire alarm system uses cannot meet the needs of incipient fire early warning, miss
The best period of fire extinguishing and early warning.Fire alarm system mostly uses greatly warming and the temperature and cigarette of Smoke Detector induced environment at present
Mistiness degree changes, and fire alarm is carried out after temperature and smoke intensity are more than given threshold.But temp probe induction is that environment is average
The variation of temperature, on fire from combustible to room environment temperature is more than that the alarm threshold value of setting needs the time of at least a few minutes,
This period is the critical period to stamp out a fire, and fire alarm in this period also in monitoring, not generate alarm.
Invention content
In view of this, the present invention provides a kind of inside fire early warning method and system of multisource data fusion, with solution
The certainly current difficult problem with fire alarm inaccuracy of Initial Stage of Fire ignition point monitoring.
In a first aspect, the present invention provides a kind of inside fire early warning method of multisource data fusion, including：
Scanning obtains indoor temperature；
Obtain indoor smog image and/or smokescope；
If the indoor temperature at a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting
When, according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smokescope
Calculate the alarm condition probability value of decision sample；
The alarm is calculated using the alarm condition probability value of the decision sample and according to Dempster composition rules
The trusting degree of state；
Judge alert status according to the magnitude relationship of the trusting degree and preset thresholding.
Preferably, temperature profile extraction is carried out to the indoor temperature, obtains the comprehensive characteristics of temperature；
The indoor temperature carries out the step of temperature profile extraction and is：
The measured temperature at K moment and K-1 moment to adjacent moment makes the difference, and obtains the temperature changing speed at K moment
Characteristic value；
Extract temperature value tag of the measured temperature at K moment as the current K moment；
Calculate the sum of all measured temperatures until the K moment, it is described and for temperature is accumulative plus feature；
By the temperature changing speed characteristic value at the K moment, the temperature value tag at the current K moment and the temperature
Accumulative plus feature is added, and obtains the comprehensive characteristics of the temperature；
If the comprehensive characteristics of the cigarette sense at a certain moment are more than or equal to the indoor temperature synthesis of moment setting
When characteristic value, according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or cigarette
Mistiness degree calculates the alarm condition probability value of decision sample；
Wherein, the measured temperature is the indoor temperature.
Preferably, smoke characteristics extraction is carried out to the smokescope, obtains the comprehensive characteristics of cigarette sense；
The indoor smog concentration carries out the step of cigarette sense feature extraction and is：
If what is obtained is indoor smog image；Numeralization processing is carried out to the smog image, obtains smog picture number
Value, the smog image values are the smokescope；
The smokescope measured value at K moment and K-1 moment to adjacent moment makes the difference, and obtains the cigarette sense variation at K moment
Velocity characteristic value；
Extract cigarette inductance value feature of the smokescope measured value at K moment as the current K moment；
Calculate the sum of all smokescope measured values until the K moment, it is described and for cigarette sense is accumulative plus feature；
By the cigarette sense pace of change characteristic value, the cigarette inductance value feature at the current K moment and the cigarette sense at the K moment
Accumulative plus feature is added, and obtains the comprehensive characteristics of the cigarette sense；
If the indoor temperature at a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting
When, according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smokescope
Calculate the alarm condition probability value of decision sample；
Wherein, the smokescope measured value is indoor smog image and/or smokescope.
Preferably, the method for the alarm condition probability value for calculating decision sample is：
Alarm condition probability value, including：Indoor temperature probability value and smog image and/or smokescope probability value；
The alarm condition probability value is that the indoor temperature probability value and the smog image and/or smokescope are general
The sum of rate value；
The indoor temperature probability value, for indoor temperature comprehensive characteristics value and the interior described in the K moment set described in the K moment
The ratio of temperature；
The smog image and/or smokescope probability value, when being that smog image and/or smokescope are with K described in the K moment
Carve the ratio of the indoor temperature.
Preferably, alarm condition is divided into：Temperature alarming state and cigarette sense alarm condition；
Using the temperature alarming state of the decision sample and the probability value of the cigarette sense alarm condition and according to
Dempster composition rules calculate separately the trust journey of the trusting degree and the cigarette sense alarm condition of the temperature alarming state
Degree；
Respectively according to the trusting degree of the temperature alarming state and the trusting degree of the cigarette sense alarm condition and in advance
The magnitude relationship of the thresholding of setting judges alert status.
Preferably, the indoor temperature carries out the step of temperature profile extraction, further includes：
The temperature changing speed characteristic value at the K moment is modified, method is the temperature change speed at the K moment
Degree characteristic value is multiplied by given temperature pace of change deviation factor；
The temperature value tag at the current K moment is modified, method is the temperature value tag at the current K moment
It is multiplied by current given temperature value deviation factor；
The temperature is added up plus feature is modified, method is that the temperature is accumulative plus feature is multiplied by given temperature and tires out
Product deviation factor.
Preferably, the smokescope carries out the step of smoke characteristics extraction, further includes：
The cigarette sense pace of change characteristic value at the K moment is modified, method is the temperature change speed at the K moment
Degree characteristic value is multiplied by given cigarette sense pace of change deviation factor；
The cigarette inductance value feature at the K moment is modified, method is that the cigarette inductance value feature at the current K moment is multiplied by
Currently given cigarette inductance value deviation factor；
The cigarette sense is added up plus feature is modified, method is that the cigarette sense is accumulative plus feature is multiplied by given temperature and tires out
Product deviation factor.
Preferably, the method for the alarm condition probability value for calculating decision sample is to further include：Leading setting time；
If the indoor temperature be more than environment temperature, leading time starts timing, if the leading time be less than or
Equal to the leading setting time, then the alarm condition probability value is the indoor temperature probability value；If the leading time
More than the leading setting time, then the alarm condition probability value is the smog image and/or smokescope probability value.
Preferably, the temperature alarming state, including：Temperature alarming, temperature are not alarmed and state of temperature does not know shape
State；
The cigarette sense alarm condition, including：Cigarette sense alarm, cigarette sense are not alarmed and cigarette sense state is uncertain；
The preset thresholding, including：First setting thresholding and the second setting thresholding；
The temperature alarming condition adjudgement rule is：
If the difference for the trusting degree that the trusting degree of the temperature alarming is not alarmed with the temperature is more than described first
Set thresholding；And the trusting degree of the state of temperature nondeterministic statement is less than described second and sets thresholding；And the if temperature
The trusting degree of degree alarm is more than the trusting degree of the state of temperature nondeterministic statement, then meets temperature pre-warning condition；
The cigarette sense alarm condition judgment rule is：
If the difference for the trusting degree that the trusting degree of the cigarette sense alarm is not alarmed with the cigarette sense is more than described first
Set thresholding；And the trusting degree of the cigarette sense state nondeterministic statement is less than described second and sets thresholding；And the if cigarette
The trusting degree of sense alarm is more than the trusting degree of the cigarette sense state nondeterministic statement, then meets cigarette sense early-warning conditions；
Meet the temperature pre-warning condition or/and the cigarette sense early-warning conditions, then early warning is carried out to inside fire.
Second aspect, the present invention provide a kind of inside fire early warning system of multisource data fusion, including：
Memory and processor and storage on a memory and the computer program that can run on a processor, the calculating
Machine program is such as a kind of above-mentioned inside fire early warning method of multisource data fusion, when the processor executes described program
Realize following steps：
Scanning obtains indoor temperature；
Obtain indoor smog image and/or smokescope；
If the indoor temperature at a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting
When, according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smokescope
Calculate the alarm condition probability value of decision sample；
The alarm is calculated using the alarm condition probability value of the decision sample and according to Dempster composition rules
The trusting degree of state；
Judge alert status according to the magnitude relationship of the trusting degree and preset thresholding.
The present invention at least has the advantages that：
The present invention provides a kind of inside fire early warning method and system of multisource data fusion, by indoor temperature and
The multisource data fusion of indoor smog image and/or smokescope monitors difficulty to solve current Initial Stage of Fire ignition point
With the problem of fire alarm inaccuracy.It is demonstrated experimentally that reliability height of the present invention and strong antijamming capability, before there is preferable application
Scape.
Description of the drawings
By the description below with reference to attached drawing to the embodiment of the present invention, the above and other purposes of the present invention, feature and
Advantage is apparent, in the accompanying drawings：
Fig. 1 is a kind of inside fire early warning method flow schematic diagram of multisource data fusion of the embodiment of the present invention；
Fig. 2 is the curve synoptic diagram of the indoor temperature comprehensive characteristics value of the setting of the embodiment of the present invention；
Fig. 3 is the curve synoptic diagram of the warming law of three kinds of normal events of the embodiment of the present invention.
Specific implementation mode
Below based on embodiment, present invention is described, but it is worth noting that, the present invention is not limited to these realities
Apply example.Below to the present invention datail description in, it is detailed to describe some specific detail sections.However, for not detailed
The part described to the greatest extent, those skilled in the art can also understand the present invention completely.
In addition, it should be understood by one skilled in the art that the attached drawing provided simply to illustrate that the purpose of the present invention,
Feature and advantage, attached drawing are not to be actually drawn to scale.
Meanwhile unless the context clearly requires otherwise, "include", "comprise" etc. otherwise throughout the specification and claims
Similar word should be construed as the meaning for including rather than exclusive or exhaustive meaning；That is, being " including but not limited to "
Meaning.
Fig. 1 is a kind of inside fire early warning method flow schematic diagram of multisource data fusion of the embodiment of the present invention.
As shown in Figure 1, a kind of inside fire early warning method of multisource data fusion, including：Step 101 scans or obtains room
Interior temperature；Step 102 obtains indoor smog image and/or smokescope；If the indoor temperature at step 103 a certain moment is more than
Or equal to the moment setting indoor temperature comprehensive characteristics value when, according to indoor temperature comprehensive characteristics value, the indoor temperature of setting
And smog image and/or smokescope calculate the alarm condition probability value of decision sample；Step 104 utilizes the report of decision sample
Alert state probability values and the trusting degree that alarm condition is calculated according to Dempster composition rules；Step 105 is according to trust journey
The magnitude relationship of degree and preset thresholding judges alert status.
Wherein, in Fig. 1, step 101 scanning or acquisition indoor temperature obtain indoor smog image with step 102
And/or smokescope is without sequencing.
Specifically, the trusting degree of alarm condition be more than or equal to preset thresholding, then to inside fire into
Row early warning；The trusting degree of alarm condition is less than preset thresholding, then to inside fire without early warning.
Specifically, indoor temperature comprehensive characteristics value, indoor temperature and the smog image and/or smog according to setting are dense
The method that degree calculates the alarm condition probability value of decision sample is not unique, and those skilled in the art can as needed and existing probability
Calculation formula calculates the alarm condition probability value of decision sample, such as：In the present invention, indoor temperature and smog image and/or cigarette
Mistiness degree can be to regard two independent events as, and the alarm condition probability value of decision sample can regard indoor temperature and cigarette as
Mist image and/or smokescope distinguish the sum of the probability under temperature integrated characteristic value indoors；Can also by indoor temperature and
Smog image and/or smokescope, which regard two as, has associated event, because in general fire indoors, indoor temperature
Fire temperature and smog image and/or smokescope have certain proportionate relationship, in general, the ignition point temperature of indoor temperature
Degree is higher, then smog image is more apparent or smokescope is bigger, then can calculate smog image and/or smokescope condition
Under indoor temperature, utilize the indoor temperature divided by indoor temperature comprehensive characteristics value under the conditions of smog image and/or smokescope
Obtain the alarm condition probability value of decision sample；The multiplication formula of 2 interrelated events can also be utilized, 2 interrelated
Event is indoor temperature and smog image and/or smokescope, calculates indoor temperature and smog image and/or smokescope intersection
Or the probability of union is as alarm condition probability value.
In Fig. 1, a kind of inside fire early warning method of multisource data fusion further includes：Indoor temperature is carried out
Temperature profile extracts, and obtains the comprehensive characteristics of temperature；Indoor temperature carry out temperature profile extraction the step of be：To adjacent moment
The measured temperature at K moment and K-1 moment makes the difference, and obtains the temperature changing speed characteristic value at K moment；Extract the temperature at K moment
Spend temperature value tag of the measured value as the current K moment；The sum of all measured temperatures until the K moment is calculated, and is temperature
Degree is accumulative to add feature；The temperature changing speed characteristic value at K moment, the temperature value tag at current K moment and temperature are added up to add
Feature is added, and obtains the comprehensive characteristics of temperature；If the comprehensive characteristics of the cigarette sense at a certain moment are more than or equal to moment setting
When indoor temperature comprehensive characteristics value, according to indoor temperature comprehensive characteristics value, indoor temperature and the smog image and/or cigarette of setting
Mistiness degree calculates the alarm condition probability value of decision sample；Wherein, measured temperature is indoor temperature.
In Fig. 1, indoor temperature carries out the step of temperature profile extraction, further includes：It is special to the temperature changing speed at K moment
Value indicative is modified, and method is that the temperature changing speed characteristic value at K moment is multiplied by given temperature pace of change deviation factor；It is right
The temperature value tag at current K moment is modified, and method is that the temperature value tag at current K moment is multiplied by current given temperature
It is worth deviation factor；Accumulative to temperature that feature is added to be modified, method is that temperature is accumulative plus feature is multiplied by given temperature accumulation partially
Poor coefficient.
Specifically, indoor temperature is scanned or obtained using temperature sensing probe, and if indoor point of origin is different, temperature
Sensing probe is not known at a distance from point of origin, in order to enable point of origin in temperature sensing probe scanning or acquisition indoor temperature
Temperature is more accurate, then needs to be modified the temperature changing speed characteristic value at K moment, be similarly also required to the temperature to the K moment
Degree pace of change characteristic value and temperature add up plus feature is modified.
In order to make those skilled in the art that the present invention be better achieved, The present invention gives indoor temperatures to carry out temperature profile extraction
The step of (that is, the variation of indoor temperature is attributed to the variation for measuring reference information), its step are as follows.
The temperature changing speed characteristics extraction at K moment：
u1(k)=Kd×[e(k)-e(k-1)]。
The temperature value feature extraction at current K moment：
u2(k)=Kp×e(k)。
Temperature is accumulative to add feature extraction：
Temperature integrated feature extraction:
The comprehensive characteristics of temperature extract formula：
Ui(k)=u1(k)+u2(k)+u3(k)。
Wherein, u1(k) it is the temperature changing speed characteristic value at k moment；u2(k) it is the Current Temperatures characteristic value at k moment；u3
(k) it is the temperature build characteristic value at k moment.
Wherein, KdFor given temperature pace of change deviation factor；KpFor current given temperature value deviation factor； KiIt is given
Temperature build deviation factor, Kd、KpAnd KiIt can be adjusted according to the position of indoor size and structure or temperature sensing probe
Whole, the present invention does not limit Kd、KpAnd KiSpecific value.
Wherein, e (k) is the measured temperature at k moment, and e (k-1) is the measured temperature at k-1 moment.
More specifically, as particularly preferred embodiment, the temperature sensing probe in the present invention can have several
A, several temperature sensing probes scan or obtain respectively indoor temperature, and the indoor temperature surveyed in this way is more accurate, if then
Several temperature integrated characteristic formulas of dry temperature sensing probe are：
Ui(k)=u1(k)+u2(k)+u3(k)。
Wherein i=1,2,3..., i are the number of temperature sensing probe.
In turn, obtaining measuring temperature comprehensive characteristics matrix is：
Ai=[U1(k),U2(k),...]。
In Fig. 1, a kind of inside fire early warning method of multisource data fusion further includes：Smokescope is carried out
Smoke characteristics are extracted, and the comprehensive characteristics of cigarette sense are obtained；Indoor smog concentration carry out cigarette sense feature extraction the step of be：If obtaining
It is indoor smog image；Numeralization processing is carried out to smog image, obtains smog image values, smog image values are smog
Concentration；The smokescope measured value at K moment and K-1 moment to adjacent moment makes the difference, and obtains the cigarette sense pace of change at K moment
Characteristic value；Extract cigarette inductance value feature of the smokescope measured value at K moment as the current K moment；Calculate the institute until the K moment
There is the sum of smokescope measured value, and adds feature for cigarette sense is accumulative；When by the cigarette sense pace of change characteristic value at K moment, current K
The cigarette inductance value feature at quarter and cigarette sense add up plus feature is added, and obtain the comprehensive characteristics of cigarette sense；If the indoor temperature at a certain moment
More than or equal to the moment setting indoor temperature comprehensive characteristics value when, according to the indoor temperature comprehensive characteristics value of setting, interior
Temperature and smog image and/or smokescope calculate the alarm condition probability value of decision sample；Wherein, smokescope measured value
For indoor smog image and/or smokescope.
Specifically, it is smog image such as to obtain indoor, then need, to carrying out numeralization processing to smog image, to obtain
Smog image values, smog image values are smokescope；If it is smokescope to obtain indoor, directly can be to smog
Concentration carries out smoke characteristics extraction, obtains the comprehensive characteristics of cigarette sense.
In Fig. 1, smokescope carries out the step of smoke characteristics extraction, further includes：It is special to the cigarette sense pace of change at K moment
Value indicative is modified, and method is that the temperature changing speed characteristic value at K moment is multiplied by given cigarette sense pace of change deviation factor；It is right
The cigarette inductance value feature at K moment is modified, and method is that the cigarette inductance value feature at current K moment is multiplied by currently given cigarette inductance value deviation
Coefficient；Accumulative to cigarette sense that feature is added to be modified, method is that cigarette sense is accumulative plus feature is multiplied by given temperature cumulative departure coefficient.
Specifically, smog image and/or smokescope are obtained using cigarette sense sensing probe, if indoor point of origin is not
Together, cigarette sense sensing probe is not known at a distance from point of origin, in order to enable cigarette sense sensing probe obtains point of origin in indoor temperature
Smog image and/or smokescope it is more accurate, then need to be modified the cigarette sense pace of change characteristic value at K moment, together
Reason is also required to accumulative to the cigarette sense pace of change characteristic value at K moment and cigarette sense plus feature is modified.
In Fig. 1, the method for the alarm condition probability value of calculating decision sample is：Alarm condition probability value, including：It is indoor
Temperature probability value and smog image and/or smokescope probability value；Alarm condition probability value be indoor temperature probability value and
The sum of smog image and/or smokescope probability value；Indoor temperature probability value, the indoor temperature comprehensive characteristics set for the K moment
The ratio of value and K moment indoor temperatures；Smog image and/or smokescope probability value are K moment smog images and/or smog
The ratio of concentration and K moment indoor temperatures.
In order to make those skilled in the art that the present invention be better achieved, The present invention gives indoor smog image and/or smog are dense
Degree carries out cigarette sense feature extraction (that is, the variation of indoor smog image and/or smokescope is attributed to another measurement reference information
Variation) the step of, its step are as follows.
Cigarette sense pace of change feature extraction：
v1(k)=Ld×[w(k)-w(k-1)]。
Current cigarette inductance value feature extraction：
v2(k)=Lp×w(k)。
Cigarette sense is accumulative to add feature extraction：
Cigarette sense comprehensive characteristics extract, and the comprehensive characteristics extraction formula of cigarette sense is：
V (k)=v1(k)+v2(k)+v3(k)。
Wherein, v1(k) it is the cigarette sense pace of change characteristic value at k moment；v2(k) it is the current cigarette sense characteristic value at k moment；v3
(k) characteristic value is accumulated for the cigarette sense at k moment.
Wherein, LdTo give cigarette sense pace of change deviation factor；LpCurrently to give cigarette inductance value deviation factor；LiIt is given
Cigarette sense cumulative departure coefficient.Similarly, Ld、LpAnd LiIt can be according to indoor size and structure or the position of temperature sensing probe
It sets and is adjusted, the present invention does not limit Ld、LpAnd LiSpecific value.
Wherein, w (k) is that the cigarette at k moment senses magnitude, and w (k-1) is that the cigarette at k-1 moment senses magnitude.
More specifically, as particularly preferred embodiment, the cigarette sense sensing probe in the present invention can have several
A, several cigarette sense sensing probes obtain indoor smog image and/or smokescope respectively, the indoor smog figure surveyed in this way
Picture and/or smokescope are more accurate, then several cigarette sense comprehensive characteristics formula of several cigarette sense sensing probes are：
Wherein i=1,2,3..., i are the number of cigarette sense sensing probe.
In turn, obtaining measurement cigarette sense comprehensive characteristics matrix is：
Bi=[V1(k),V2(k),...]。
In Fig. 1, alarm condition is divided into：Temperature alarming state and cigarette sense alarm condition；Utilize the temperature of decision sample
It spends the probability value of alarm condition and cigarette sense alarm condition and temperature alarming state is calculated separately according to Dempster composition rules
Trusting degree and cigarette sense alarm condition trusting degree；Respectively according to the trusting degree of temperature alarming state and cigarette sense alarm shape
The trusting degree of state and the magnitude relationship of preset thresholding judge alert status.
In Fig. 1, temperature alarming state, including：Temperature alarming, temperature are not alarmed and state of temperature nondeterministic statement；
Cigarette sense alarm condition, including：Cigarette sense alarm, cigarette sense are not alarmed and cigarette sense state is uncertain；Preset thresholding, including：
First setting thresholding and the second setting thresholding.
Wherein, temperature alarming condition adjudgement rule is：If the trust journey that the trusting degree of temperature alarming is not alarmed with temperature
The difference of degree is more than the first setting thresholding；And the trusting degree of state of temperature nondeterministic statement is less than the second setting thresholding；And
If the trusting degree of temperature alarming is more than the trusting degree of state of temperature nondeterministic statement, meet temperature pre-warning condition.
Wherein, cigarette sense alarm condition judgment rule is：If the trust journey that the trusting degree of cigarette sense alarm is not alarmed with cigarette sense
The difference of degree is more than the first setting thresholding；And the trusting degree of cigarette sense state nondeterministic statement is less than the second setting thresholding；And
If the trusting degree of cigarette sense alarm is more than the trusting degree of cigarette sense state nondeterministic statement, meet cigarette sense early-warning conditions.
Such as meet temperature pre-warning condition or/and cigarette sense early-warning conditions, then early warning is carried out to inside fire.Specifically, such as
When fruit meets a condition in temperature pre-warning condition or cigarette sense early-warning conditions, then early warning is carried out to inside fire.
In order to make those skilled in the art that the present invention be better achieved, The present invention gives be to judge that alert status is most preferably real
Mode is applied, under different measurement reference informations (it is indoor temperature and smog image and/or smokescope to measure reference information)
Identification framework Θ, whereinJ is the alarm condition for needing to judge according to different measurement reference informations, alarm condition
Such as：Temperature alarming J1, temperature do not alarm J2, state of temperature do not know J3, cigarette sense alarm J4, cigarette sense do not alarm J5, cigarette sense state is not
Determine J6。
Assuming that the decision sample of limited a sensor (that is, temperature sensing probe and cigarette sense sensing probe) is respectively：m1,
m2,...,mn, work as Ui(k) its elementary probability (that is, alarm condition probability value of decision sample) of >=T (k) is assigned a value of：
Wherein, T (k) is the indoor environment temperature comprehensive characteristics value at k moment (that is, the indoor temperature comprehensive characteristics of setting
Value).
Wherein, h is leading setting time,
Since in Initial Stage of Fire, indoor temperature is being dominated, i.e.,：In Initial Stage of Fire, smog image unobvious, smokescope
Smaller, then in Initial Stage of Fire, the alarm condition probability value of decision sample mainly considers indoor temperature information；After Initial Stage of Fire,
Then smog image is apparent, and smokescope is larger, the alarm condition probability value of decision sample mainly consider indoor smog image and/
Or smokescope.It is 15 seconds that the present invention gives leading setting time simultaneously, that is, before 15 seconds, the alarm shape of decision sample
State probability value mainly considers indoor temperature information；After 15 seconds, the alarm condition probability value of decision sample mainly considers interior
Smog image and/or smokescope.Wherein, the 15 seconds time obtained for test of many times of setting time is dominated.
It is according to Dempster composition rules then：
Wherein, mi(Ji) it is JiBasic Probability As-signment, also illustrate that JiTrusting degree.
M (J) is the reference information trusting degree of whole sample space, normalization factorReflect the tightness degree of evidence.
Wherein, Dempster composition rules can refer to 04 phases in 2007 of modern defense technology《Based on Dempster groups
Electronic target recognizer research normally》Or 05 phases in 1999 of Xian Electronics Science and Technology University's journal《Weighting
Dempster Evidence Combination Methods algorithms》In specific description.
Finally, according to the measurement of whole sample space (that is, indoor temperature and smog image and/or smokescope) with reference to letter
It ceases reference information trusting degree and judges that alert status, concrete mode are as follows：
If having：
Then J1To judge as a result, wherein ε1,ε2For preset thresholding, U is uncertain set, U={ J3,J6,...}。
Specifically, ε1For the first setting thresholding, ε2For the second setting thresholding；Above-mentioned judgment formula gives, temperature alarming condition adjudgement
Rule, cigarette sense alarm condition judgment rule is identical as temperature alarming condition adjudgement rule, therefore no longer this is described in detail.
Meanwhile the present invention provides a kind of inside fire early warning systems of multisource data fusion, including：Memory and
Processor and storage are on a memory and the computer program that can run on a processor, computer program are that such as above-mentioned one kind is more
The inside fire early warning method of source data fusion, processor realize following steps when executing program：Step 101 scan or
Obtain indoor temperature；Step 102 obtains indoor smog image and/or smokescope；If the Indoor Temperature at step 103 a certain moment
When degree is more than or equal to the indoor temperature comprehensive characteristics value of moment setting, according to the indoor temperature comprehensive characteristics value of setting, room
Interior temperature and smog image and/or smokescope calculate the alarm condition probability value of decision sample；Step 104 utilizes decision sample
This alarm condition probability value and the trusting degree that alarm condition is calculated according to Dempster composition rules；Step 105 basis
The magnitude relationship of trusting degree and preset thresholding judges alert status.
Wherein, step 101 scanning or acquisition indoor temperature obtain indoor smog image and/or smog with step 102
Concentration is without sequencing.
Specifically, the trusting degree of alarm condition is more than or equal to preset thresholding, then a kind of multi-source data
The inside fire early warning system of fusion carries out early warning to inside fire；The trusting degree of alarm condition is less than preset
Thresholding, a kind of inside fire early warning system of multisource data fusion is then to inside fire without early warning.
It being scanned in step 101 or obtains indoor temperature, step 102 obtains indoor smog image and/or smokescope,
If the indoor temperature at step 103 a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting, according to setting
Fixed indoor temperature comprehensive characteristics value, indoor temperature and smog image and/or smokescope calculate the alarm shape of decision sample
State probability value, step 104 calculate alarm using the alarm condition probability value of decision sample and according to Dempster composition rules
The trusting degree of state, step 105 judge according to the magnitude relationship of trusting degree and preset thresholding in alert status
Processing method can refer to a kind of inside fire early warning method or above-mentioned for more detailed reality of above-mentioned multisource data fusion
Apply example.
Specifically, a kind of inside fire early warning system of multisource data fusion provided by the invention, including：Detection
Node and host, detection node are connected with host；Detection node is temperature sensing probe and cigarette sense sensing probe；Host, which has, to be deposited
Reservoir and processor and storage are on a memory and the computer program that can run on a processor, computer program are such as above-mentioned
A kind of inside fire early warning method of multisource data fusion, processor realize following steps when executing program：Step 101 is swept
Retouch or obtain indoor temperature；Step 102 obtains indoor smog image and/or smokescope；If the step 103 a certain moment
Indoor temperature when being more than or equal to the indoor temperature comprehensive characteristics value of moment setting, integrated according to the indoor temperature of setting special
Value indicative, indoor temperature and smog image and/or smokescope calculate the alarm condition probability value of decision sample；Step 104 profit
The trusting degree of alarm condition is calculated with the alarm condition probability value of decision sample and according to Dempster composition rules；Step
105 judge alert status according to the magnitude relationship of trusting degree and preset thresholding.
Invent provide a kind of multisource data fusion inside fire early warning system, further include：Repeater, repeater
It is connect respectively with detection node and host, repeater is to acquire the integrated information of multiple detection nodes, and information is classified
And display.Repeater is mainly made of man-machine operation part and signal transmission two parts.Human-machine operation part or host can be with
Relevant parameter is set：Given temperature pace of change deviation factor Kd, current given cigarette inductance value deviation system Kp, given temperature accumulation it is inclined
Poor COEFFICIENT Ki, given cigarette sense pace of change deviation factor Ld, current given cigarette inductance value deviation factor Lp, given cigarette sense cumulative departure
Coefficient Li, leading setting time, the first setting thresholding ε1, the second setting thresholding ε2And messaging parameter etc., it also can query node shape
State and warning message.Signal transmission part is mainly passed down by wired and wireless mode progress parameter and data upload, and will weigh
Information is wanted to be transferred to host.
Fig. 2 is the curve synoptic diagram of the indoor temperature comprehensive characteristics value of the setting of the embodiment of the present invention.As shown in Fig. 2, give
Combustion fire point is gone out from early stage on fire to temperature changing process completely on fire.As can be seen that the variation of entire fire temperature from Fig. 2
Process is divided into growth stage, animated period and degradation period.Degradation period has had resulted in the loss of personnel or economy, therefore is clearly not to go out
The best period of fire.When animated period, fire temperature is already close to 1000 DEG C, and the intensity of a fire is violent at this time, and fire extinguishing can be extremely difficult.Only
In the growth stage, although temperature change is very fast, fire temperature is low, is convenient for the progress of fire-fighting work.Especially at initial stage on fire
0-10 minutes, combustion fire temperature was low, and temperature change is slower, if can find that life can be saved to avoid the generation of fire incident in time
Life and people's property.
Fig. 3 is the curve synoptic diagram of the warming law of three kinds of normal events of the embodiment of the present invention.In addition to above-mentioned fire fires
Fiery, in order to exclude the interference that daily life heats up to system, we analyze main daily temperature change, and common is daily
Heating mainly has heating water heating, cigarette butt heating and gas-cooker heating etc..We test discovery, these daily heating transient temperatures
Variation is fast, and rapidly enters temperature stationary phase.When measurement distance is 5M, three kinds of situations are measured using infrared thermography instrument
Under, the actual temperature of fire's point of origin is as shown in Fig. 3.
According to features described above curve (Fig. 2 and Fig. 3), we have tested a variety of combustion fire point variations and combination change procedure to examine
The reliability and anti-interference of the present invention are tested, experimental data is as follows：
1 a single state of table test alarm reliability of the present invention (√ is current state, × not alarm, zero is alarm)
2 assembled state of table test present invention alarm anti-interference (√ is current state, × not alarm, zero is alarm)
Obviously, those skilled in the art should be understood that each unit of the above-mentioned present invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices compositions
On network, optionally, they can be realized with the program code that computing device can perform, it is thus possible to be stored in
It is performed by computing device in storage device, either they are fabricated to each integrated circuit units or will be in them
Multiple units or step be fabricated to single integrated circuit unit to realize.In this way, the present invention is not limited to any specific hard
Part and software combine.
Embodiment described above is only to express embodiments of the present invention, the description thereof is more specific and detailed, but can not
Therefore it is interpreted as the limitation to the scope of the claims of the present invention.It should be pointed out that those skilled in the art,
Under the premise of not departing from present inventive concept, several deformations, same replacement can also be made, improved etc., these belong to the present invention
Protection domain.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of inside fire early warning method of multisource data fusion, which is characterized in that including：
Scanning obtains indoor temperature；
Scan or obtain indoor smog image and/or smokescope；
If the indoor temperature at a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting, root
It is calculated according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smokescope
The alarm condition probability value of decision sample；
The alarm condition is calculated using the alarm condition probability value of the decision sample and according to Dempster composition rules
Trusting degree；
Judge alert status according to the magnitude relationship of the trusting degree and preset thresholding.
2. a kind of inside fire early warning method of multisource data fusion according to claim 1, which is characterized in that packet
It includes：
Temperature profile extraction is carried out to the indoor temperature, obtains the comprehensive characteristics of temperature；
The indoor temperature carries out the step of temperature profile extraction and is：
The measured temperature at K moment and K-1 moment to adjacent moment makes the difference, and obtains the temperature changing speed feature at K moment
Value；
Extract temperature value tag of the measured temperature at K moment as the current K moment；
Calculate the sum of all measured temperatures until the K moment, it is described and for temperature is accumulative plus feature；
The temperature changing speed characteristic value at the K moment, the temperature value tag at the current K moment and the temperature are added up
Add feature to be added, obtains the comprehensive characteristics of the temperature；
If the comprehensive characteristics of the cigarette sense at a certain moment are more than or equal to the indoor temperature comprehensive characteristics of moment setting
It is dense according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smog when value
Degree calculates the alarm condition probability value of decision sample；
Wherein, the measured temperature is the indoor temperature.
3. a kind of inside fire early warning method of multisource data fusion according to claim 1, which is characterized in that packet
It includes：
Smoke characteristics extraction is carried out to the smokescope, obtains the comprehensive characteristics of cigarette sense；
The indoor smog concentration carries out the step of cigarette sense feature extraction and is：
If what is obtained is indoor smog image；Numeralization processing is carried out to the smog image, obtains smog image values, institute
It is the smokescope to state smog image values；
The smokescope measured value at K moment and K-1 moment to adjacent moment makes the difference, and obtains the cigarette sense pace of change at K moment
Characteristic value；
Extract cigarette inductance value feature of the smokescope measured value at K moment as the current K moment；
Calculate the sum of all smokescope measured values until the K moment, it is described and for cigarette sense is accumulative plus feature；
The cigarette sense pace of change characteristic value, the cigarette inductance value feature at the current K moment and the cigarette sense at the K moment are added up
Add feature to be added, obtains the comprehensive characteristics of the cigarette sense；
If the indoor temperature at a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting, root
It is calculated according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smokescope
The alarm condition probability value of decision sample；
Wherein, the smokescope measured value is indoor smog image and/or smokescope.
4. a kind of inside fire early warning method of multisource data fusion according to claim 1, which is characterized in that packet
It includes：
The method of alarm condition probability value for calculating decision sample is：
Alarm condition probability value, including：Indoor temperature probability value and smog image and/or smokescope probability value；
The alarm condition probability value is the indoor temperature probability value and the smog image and/or smokescope probability value
Sum；
The indoor temperature probability value, for indoor temperature comprehensive characteristics value and the indoor temperature described in the K moment set described in the K moment
Ratio；
The smog image and/or smokescope probability value, for smog image described in the K moment and/or smokescope and K moment institutes
State the ratio of indoor temperature.
5. according to a kind of any one of Claims 1 to 4 inside fire early warning method of multisource data fusion, feature
It is, including：
Alarm condition is divided into：Temperature alarming state and cigarette sense alarm condition；
Using the temperature alarming state of the decision sample and the probability value of the cigarette sense alarm condition and according to
Dempster composition rules calculate separately the trust journey of the trusting degree and the cigarette sense alarm condition of the temperature alarming state
Degree；
Respectively according to the trusting degree of the temperature alarming state and the trusting degree of the cigarette sense alarm condition with preset
The magnitude relationship of thresholding judge alert status.
6. a kind of inside fire early warning method of multisource data fusion according to claim 2, it is characterised in that：
The indoor temperature carries out the step of temperature profile extraction, further includes：
The temperature changing speed characteristic value at the K moment is modified, method is that the temperature changing speed at the K moment is special
Value indicative is multiplied by given temperature pace of change deviation factor；
The temperature value tag at the current K moment is modified, method is that the temperature value tag at the current K moment is multiplied by
Current given temperature value deviation factor；
Accumulative to the temperature that feature is added to be modified, method is that the temperature is accumulative plus feature is multiplied by given temperature accumulation partially
Poor coefficient.
7. a kind of inside fire early warning method of multisource data fusion according to claim 3, it is characterised in that：
The smokescope carries out the step of smoke characteristics extraction, further includes：
The cigarette sense pace of change characteristic value at the K moment is modified, method is that the temperature changing speed at the K moment is special
Value indicative is multiplied by given cigarette sense pace of change deviation factor；
The cigarette inductance value feature at the K moment is modified, method is that the cigarette inductance value feature at the current K moment is multiplied by currently
Given cigarette inductance value deviation factor；
Accumulative to the cigarette sense that feature is added to be modified, method is that the cigarette sense is accumulative plus feature is multiplied by given temperature accumulation partially
Poor coefficient.
8. a kind of inside fire early warning method of multisource data fusion according to claim 4, which is characterized in that packet
It includes：
The method of the alarm condition probability value for calculating decision sample is to further include：Leading setting time；
If the indoor temperature is more than environment temperature, leading time starts timing, if the leading time is less than or equal to
The leading setting time, then the alarm condition probability value is the indoor temperature probability value；If the leading time is more than
The leading setting time, then the alarm condition probability value is the smog image and/or smokescope probability value.
9. a kind of inside fire early warning method of multisource data fusion according to claim 5, it is characterised in that：
The temperature alarming state, including：Temperature alarming, temperature are not alarmed and state of temperature nondeterministic statement；
The cigarette sense alarm condition, including：Cigarette sense alarm, cigarette sense are not alarmed and cigarette sense state is uncertain；
The preset thresholding, including：First setting thresholding and the second setting thresholding；
The temperature alarming condition adjudgement rule is：
It is set if the difference for the trusting degree that the trusting degree of the temperature alarming is not alarmed with the temperature is more than described first
Thresholding；And the trusting degree of the state of temperature nondeterministic statement is less than described second and sets thresholding；And the if temperature report
Alert trusting degree is more than the trusting degree of the state of temperature nondeterministic statement, then meets temperature pre-warning condition；
The cigarette sense alarm condition judgment rule is：
If the difference for the trusting degree that the trusting degree of the cigarette sense alarm is not alarmed with the cigarette sense is more than described first and sets
Thresholding；And the trusting degree of the cigarette sense state nondeterministic statement is less than described second and sets thresholding；And the if cigarette sense report
Alert trusting degree is more than the trusting degree of the cigarette sense state nondeterministic statement, then meets cigarette sense early-warning conditions；
Meet the temperature pre-warning condition or/and the cigarette sense early-warning conditions, then early warning is carried out to inside fire.
10. a kind of inside fire early warning system of multisource data fusion, which is characterized in that including：
Memory and processor and storage on a memory and the computer program that can run on a processor, the computer journey
Sequence is a kind of inside fire early warning method of multisource data fusion, the processor as described in any one of claim 1~9
Following steps are realized when executing described program：
Scanning obtains indoor temperature；
Obtain indoor smog image and/or smokescope；
If the indoor temperature at a certain moment is more than or equal to the indoor temperature comprehensive characteristics value of moment setting, root
It is calculated according to the indoor temperature comprehensive characteristics value of the setting, the indoor temperature and the smog image and/or smokescope
The alarm condition probability value of decision sample；
The alarm condition is calculated using the alarm condition probability value of the decision sample and according to Dempster composition rules
Trusting degree；
Judge alert status according to the magnitude relationship of the trusting degree and preset thresholding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810357079.1A CN108492506A (en) | 2018-04-20 | 2018-04-20 | A kind of inside fire early warning method and system of multisource data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810357079.1A CN108492506A (en) | 2018-04-20 | 2018-04-20 | A kind of inside fire early warning method and system of multisource data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108492506A true CN108492506A (en) | 2018-09-04 |
Family
ID=63313623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810357079.1A Pending CN108492506A (en) | 2018-04-20 | 2018-04-20 | A kind of inside fire early warning method and system of multisource data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108492506A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213238A (en) * | 2018-09-20 | 2019-01-15 | 合肥霞康电子商务有限公司 | A kind of education classroom environment monitoring system |
| CN109920192A (en) * | 2019-03-15 | 2019-06-21 | 深圳力维智联技术有限公司 | Fire alarm method, system and computer readable storage medium |
| CN111275951A (en) * | 2019-12-25 | 2020-06-12 | 中国移动通信集团江苏有限公司 | Information processing method, device and equipment and computer storage medium |
| CN111862557A (en) * | 2019-04-24 | 2020-10-30 | 广州煜煊信息科技有限公司 | Household accident handling method based on Internet of things monitoring mode |
| CN113313903A (en) * | 2021-04-06 | 2021-08-27 | 中国船舶重工集团公司第七0三研究所 | Multi-parameter data fusion fire judgment method |
| CN113572063A (en) * | 2021-02-26 | 2021-10-29 | 河南工业职业技术学院 | Electrical cabinet system with heat dissipation and dust removal functions |
| CN115171320A (en) * | 2022-06-29 | 2022-10-11 | 万霖消防技术有限公司 | Fire-fighting monitoring method and system |
| CN115206047A (en) * | 2022-05-24 | 2022-10-18 | 华能宁夏中卫光伏发电有限公司 | Photovoltaic module area fire prevention alarm method and system |
| CN115909645A (en) * | 2023-01-09 | 2023-04-04 | 西安易诺敬业电子科技有限责任公司 | Workshop production safety early warning system and early warning method |
| CN115206047B (en) * | 2022-05-24 | 2024-04-30 | 华能宁夏中卫光伏发电有限公司 | Fireproof alarm method and system for photovoltaic module area |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100228854A1 (en) * | 2009-03-09 | 2010-09-09 | At&T Mobility Ii Llc | Network operation management |
| CN102080569A (en) * | 2010-12-10 | 2011-06-01 | 煤炭科学研究总院重庆研究院 | Distributed optical fiber temperature measurement-based fire early warning method for belt conveyor |
| CN102945585A (en) * | 2012-11-21 | 2013-02-27 | 苏州两江科技有限公司 | Method for raising fire alarm through multi-sensor data fusion |
| CN104318688A (en) * | 2014-10-31 | 2015-01-28 | 湘潭大学 | Multi-sensor fire early-warning method based on data fusion |
| CN105338661A (en) * | 2015-07-13 | 2016-02-17 | 安徽农业大学 | Environment monitoring method and device taking cloud computing as configuration and employing data fusion calculation design |
| CN105741474A (en) * | 2016-04-11 | 2016-07-06 | 泉州师范学院 | Fire early-warning method based on multiple sensors |
-
2018
- 2018-04-20 CN CN201810357079.1A patent/CN108492506A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100228854A1 (en) * | 2009-03-09 | 2010-09-09 | At&T Mobility Ii Llc | Network operation management |
| CN102080569A (en) * | 2010-12-10 | 2011-06-01 | 煤炭科学研究总院重庆研究院 | Distributed optical fiber temperature measurement-based fire early warning method for belt conveyor |
| CN102945585A (en) * | 2012-11-21 | 2013-02-27 | 苏州两江科技有限公司 | Method for raising fire alarm through multi-sensor data fusion |
| CN104318688A (en) * | 2014-10-31 | 2015-01-28 | 湘潭大学 | Multi-sensor fire early-warning method based on data fusion |
| CN105338661A (en) * | 2015-07-13 | 2016-02-17 | 安徽农业大学 | Environment monitoring method and device taking cloud computing as configuration and employing data fusion calculation design |
| CN105741474A (en) * | 2016-04-11 | 2016-07-06 | 泉州师范学院 | Fire early-warning method based on multiple sensors |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109213238A (en) * | 2018-09-20 | 2019-01-15 | 合肥霞康电子商务有限公司 | A kind of education classroom environment monitoring system |
| CN109213238B (en) * | 2018-09-20 | 2020-12-11 | 深圳市安之源电子有限公司 | Classroom environment monitoring system for education |
| CN109920192A (en) * | 2019-03-15 | 2019-06-21 | 深圳力维智联技术有限公司 | Fire alarm method, system and computer readable storage medium |
| CN111862557A (en) * | 2019-04-24 | 2020-10-30 | 广州煜煊信息科技有限公司 | Household accident handling method based on Internet of things monitoring mode |
| CN111862557B (en) * | 2019-04-24 | 2022-08-16 | 广州煜煊信息科技有限公司 | Household accident handling method based on Internet of things monitoring mode |
| CN111275951A (en) * | 2019-12-25 | 2020-06-12 | 中国移动通信集团江苏有限公司 | Information processing method, device and equipment and computer storage medium |
| CN113572063A (en) * | 2021-02-26 | 2021-10-29 | 河南工业职业技术学院 | Electrical cabinet system with heat dissipation and dust removal functions |
| CN113313903A (en) * | 2021-04-06 | 2021-08-27 | 中国船舶重工集团公司第七0三研究所 | Multi-parameter data fusion fire judgment method |
| CN115206047A (en) * | 2022-05-24 | 2022-10-18 | 华能宁夏中卫光伏发电有限公司 | Photovoltaic module area fire prevention alarm method and system |
| CN115206047B (en) * | 2022-05-24 | 2024-04-30 | 华能宁夏中卫光伏发电有限公司 | Fireproof alarm method and system for photovoltaic module area |
| CN115171320A (en) * | 2022-06-29 | 2022-10-11 | 万霖消防技术有限公司 | Fire-fighting monitoring method and system |
| CN115171320B (en) * | 2022-06-29 | 2023-11-14 | 万霖消防技术有限公司 | Fire control monitoring method and system |
| CN115909645A (en) * | 2023-01-09 | 2023-04-04 | 西安易诺敬业电子科技有限责任公司 | Workshop production safety early warning system and early warning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108492506A (en) | A kind of inside fire early warning method and system of multisource data fusion | |
| Zervas et al. | Multisensor data fusion for fire detection | |
| CN106485868B (en) | Monitoring method, the monitoring server of system and fire behavior of fire behavior | |
| Wu et al. | An intelligent tunnel firefighting system and small-scale demonstration | |
| CN105741474B (en) | A kind of fire alarm method based on multisensor | |
| CN103063328B (en) | Method and device for non-contact measurement of interior temperature of open-air coal stack | |
| CN209118462U (en) | A kind of visualization phase battle array intelligent fire alarm system of front-end convergence | |
| CN113936413B (en) | Early fire monitoring and early warning method and device | |
| JP2011508191A (en) | Method, system and computer program for determining heat or energy loss in a building | |
| CN104318688A (en) | Multi-sensor fire early-warning method based on data fusion | |
| CN109738014B (en) | Intelligent diagnosis method and system for equipment faults of urban comprehensive pipe gallery | |
| CN113192283B (en) | Wireless fire early warning system with multi-sensor information fusion | |
| CN111986436B (en) | Comprehensive flame detection method based on ultraviolet and deep neural networks | |
| US8248253B2 (en) | Fire detector incorporating a gas sensor | |
| CN105184233A (en) | Method and apparatus for measuring and recording the number of indoor people based on multi-source information fusion | |
| Yang et al. | Evaluation on algorithm reliability and efficiency for an image flame detection technology | |
| CN108050397B (en) | Layering based on optical fiber source signal is sequential than pipe leakage monitoring method and system | |
| CN113671886A (en) | Fire safety monitoring method and system based on 5G | |
| CN108614803A (en) | A kind of meteorological data method of quality control and system | |
| CN206114570U (en) | Envelope synthesizes on --spot detecting system of thermal property | |
| CN116256016A (en) | Whole process health monitoring system of building structure system | |
| Hamzah et al. | Design and Built a Prototype Kit for Fire Detection in a Peat Swamp Forest: A Preliminary Results | |
| WO2021181585A1 (en) | Analysis device, analysis method, and analysis program | |
| Li et al. | A fire source localization algorithm based on temperature and smoke sensor data fusion | |
| Singh et al. | Homex: An Intelligent Home Automation and Security System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |