CN103914622A - Quick chemical leakage predicating and warning emergency response decision-making method - Google Patents
Quick chemical leakage predicating and warning emergency response decision-making method Download PDFInfo
- Publication number
- CN103914622A CN103914622A CN201410136961.5A CN201410136961A CN103914622A CN 103914622 A CN103914622 A CN 103914622A CN 201410136961 A CN201410136961 A CN 201410136961A CN 103914622 A CN103914622 A CN 103914622A
- Authority
- CN
- China
- Prior art keywords
- wind direction
- leakage
- sight
- sensor
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 239000000126 substance Substances 0.000 title claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 36
- 238000009792 diffusion process Methods 0.000 claims abstract description 31
- 230000009931 harmful effect Effects 0.000 claims abstract description 28
- 238000012216 screening Methods 0.000 claims abstract description 26
- 238000004088 simulation Methods 0.000 claims abstract description 25
- 230000010354 integration Effects 0.000 claims abstract description 6
- 230000001537 neural effect Effects 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 5
- 239000012530 fluid Substances 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000012502 risk assessment Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 abstract 3
- 238000010200 validation analysis Methods 0.000 abstract 1
- 239000007789 gas Substances 0.000 description 37
- 231100000331 toxic Toxicity 0.000 description 14
- 230000002588 toxic effect Effects 0.000 description 14
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 5
- 229910052801 chlorine Inorganic materials 0.000 description 5
- 239000000460 chlorine Substances 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 231100000614 poison Toxicity 0.000 description 4
- 230000007096 poisonous effect Effects 0.000 description 4
- 230000001235 sensitizing effect Effects 0.000 description 4
- KZBUYRJDOAKODT-UHFFFAOYSA-N Chlorine Chemical compound ClCl KZBUYRJDOAKODT-UHFFFAOYSA-N 0.000 description 3
- 239000002341 toxic gas Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 239000012852 risk material Substances 0.000 description 2
- YGYAWVDWMABLBF-UHFFFAOYSA-N Phosgene Chemical compound ClC(Cl)=O YGYAWVDWMABLBF-UHFFFAOYSA-N 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention relates to a quick chemical leakage predicating and warning emergency response decision-making method which combines diffusion model simulation with a neural network and a gas sensor system and is applied to quick warning and aid decision making of leakage of harmful gas in an industrial park. The method includes park risk factor identification, numerical simulation, data screening, neural network training and sensor system and neural network model integration, wherein the park risk factor identification is used for identifying various possible leakage accidents, the numerical simulation includes simulating all the possible accidents to obtain a range of influences of the harmful gas, the data screening includes extracting and reconstructing an effective part in a numerical simulation result according to actual sensor layout, the neural network training includes training specific neural network models by the aid of screened data so as to acquire model parameters aiming for the specific industrial park and surrounding conditions and using redundant data for parameter validation, and sensor system and neural network model integration includes combining the models with a sensor DCS (distributed control system).
Description
Technical field
The invention belongs to the safe early warning technical field in commercial production, particularly a kind of chemical leakage fast prediction early warning emergency response decision-making technique.
Background technology
A lot of process industries can use or produce some harmful poisonous, harmful gases in process of production (as chlorine, phosgene etc.), once toxic and harmful leakage accident occurs in these industrial parks, the toxic and harmful leaking out may cause serious harm to the mankind in periphery certain limit.In the time that toxic and harmful leakage accident occurs, the material of leakage and roughly leak position can be determined with comparalive ease, but the leakage rate of harmful gas or leak rate are difficult to obtain at the scene.Diffusion tendency and coverage at the limited information prediction toxic gas of limited time utilization are the important steps of accident emergency response process.At present, traditional numerical value DIFFUSION PREDICTION model, comprises Gaussian plume model, Fluid Mechanics Computation model, and some comparatively ripe diffusion simulations softwares all need user that detailed source of leaks leakage rate is provided, and need the regular hour to calculate just to obtain result.Therefore, have limited the leakage rate of source of leaks or leakage rate and longer computing time the application of these traditional gas diffusion models in accident emergency response and aid decision making process, the investigation and analysis after their accidents that is used to more occur.Due to historical reasons, quite a few may occur have residential block to exist within the scope of the industrial park periphery 3～5km of toxic and harmful leakage accident China, in the time there is serious toxic and harmful leakage accident, these toxic and harmfuls probably diffuse to outside battery limit (BL), industrial park, and residential block is produced and threatened.In the time fast and effeciently not predicting the method for toxic and harmful range of scatter, decision maker often considers the coverage of harmful gas with the worst situation, and predicting the outcome of worst case often means that government department need to evacuate several ten thousand tens0000 people even, this is very unpractical.Therefore a kind of method of fast and effeciently predicting harmful gases diffusion scope is significant for accident emergency response and aid decision making.
The factory that processes toxic and harmful all can arrange one or more harmful gas sensors targetedly near toxic and harmful storage tank, whether has Leakage Gas for monitoring.These gas sensors are all connected with control center, provide poisonous gas leakage alarm information.But at present a lot of industrial parks are not all brought into play the effect of gas sensor completely, when accident occurs, emergency response personnel can only obtain by sensor the kind of gas leakage, instantaneous concentration, and can not predict rapidly by these information the distribution situation of gas leakage, and then take effective control measure, formulate rational evacuation plan.
At present, the accident consequence analysis method generally using in the world mainly comprises the different types of numerical model (Gaussian plume model of use, Fluid Mechanics Computation model (CFD) and business prototype PHAST, FLACS etc. reappear the accident having occurred, the coverage that is illustrated in gas leakage under accident leakage condition at that time (comprises dead district, severely injured district and the zone of influence), and study the impact of atmospheric diffusion condition on gas leakage range of scatter and CONCENTRATION DISTRIBUTION.But the shortcoming that uses Numerical Model Analysis is to know source strength (leakage rate) and the leakage form (blast leakage/aperture leakage etc.) of source of leaks, simulate in conjunction with meteorologic parameter and mass transfer diffusion equation, model complexity, calculate length consuming time, can not be used for the real-time or fast prediction under accident condition.
Summary of the invention
In order to overcome the shortcoming of above-mentioned prior art, the object of the present invention is to provide a kind of chemical leakage fast prediction early warning emergency response decision-making technique, venture analysis is carried out in industrial park, reveal Scene Simulation, appropriate supplements and optimize the existing toxic and harmful sensing system in garden, the toxic gas alarm system of garden is combined with the analysis of gas DIFFUSION PREDICTION, for accident emergency Response Decision provides technical support.
To achieve these goals, the technical solution used in the present invention is:
A kind of chemical leakage fast prediction early warning emergency response decision-making technique, comprises the integrated double teacher altogether of risk factors identification, sight numerical simulation, analog result screening, neural metwork training and training result and sensing system, wherein:
Risk factors identification comprises: the risk factors of identification chemical industrial park, quantize each risk elements and according to risk elements and the span thereof of identification, reasonable value also combines various contingent leakage sights;
The sight numerical simulation stage comprises: all contingent leakage sight forming in garden risk factors identification step is simulated, to obtain the different coverages of revealing gas under sight of revealing;
Analog result screening comprises:
Key parameter in a kind of placement scheme that comprises 4 gas sensors is optimized, utilizes the leakage gas concentration distribution that simulation obtains to carry out simple optimizing, obtain Shi sensor placement;
According to definite sensor placement's scheme, be extracted in the environment sensitive spot gas leakage diffusion data that sensor placement can measure the virtual detection data within the scope of wind direction and match, prepare training data and checking data according to the training logic of neural network;
Neural metwork training step comprises:
Set up the feedforward neural network for Function Fitting, the input and output using ready training data as neural metwork training, computational grid parameter;
By check data importation input neural network, result part and the contrast of neural network prediction result, evaluation prediction precision;
Neural network and sensor and garden control system integration step:
The sunykatuib analysis of each risk source and training result are combined with the form of database and calling program with the geographical location information of risk source and environment sensitive spot, and provide and the data-interface of sensing system, realize the workflow of from the accident-sensor warning-model fast prediction-aid decision making.
Described garden risk identification part is made up of following steps:
Step 1, utilize risk assessment identification risks and assumptions and accident sight factor and judge the indispensable element of contingent all kinds of leakage sights, comprise risk elements and accident scenario factors.These key elements comprise and are not limited to specified risk material kind (poisonous/inflammable gas or volatile liquid), reserves/consumption, storage location (volume coordinate), storage form (pressure, temperature, equipment), wind speed, humidity, temperature, atmospheric stability, surrounding enviroment sensitive spot position (volume coordinate) etc.
The span (for continuous variable) of step 2, respectively definite each risks and assumptions and accident situational factor, in the span of each factor, respectively with a fixed step size number of partitions value sequence (step-length must not exceed this factor span 10%), finally each value of different risks and assumptions/accident sight factors is combined into a large amount of contingent leakage sights.As total n kind risk factors, each risk factors have N
iplant value (N
i>=1, integer), total
plant and reveal sight.
The numerical model that the described sight numerical simulation stage is used comprises: the Integrated Models such as Gauss and class Gauss diffusion model (Gaussian Plume Model), Fluid Mechanics Computation (CFD) model and PHAST, FLACS, SLAB, ALOHA, HGSYSTEM.Finally obtain J kind and reveal Scene Simulation result.
Described analog result screening step need to be carried out layout optimization to one group of 4 sensor, and 4 sensors employing regular polygon structures, and serial number is 1～4, and the spacing of adjacent numbering sensor is equal, and Optimization Steps is as follows:
Step 1, according to the position of source of leaks and garden layout, the detectability of sensor, determines basic layout parameter L
1, the span of d and α.Wherein L
1be the distance of No. 1 sensor distance source of leaks, d is transducer spacing, and α is 1/2. of 1-2 and 1-4 sensor angle
Step 2, according to wind frequently information determine cardinal wind, sensor is arranged symmetrically in cardinal wind leeward upwards, actual wind direction and cardinal wind angle are β.And get a higher value β
0interval as optimizing, by its discrete be actual wind direction sequence (β
1, β
2..., β
m), sequence length is M.(generally get β
0=50 °, by discrete to interval [50 °, 50 °] be the wind direction sequence at 1 °, interval)
Step 3, to layout parameter L1, d, α is separated into argument sequence in span, length is respectively P
1, P
2, P
3, composition
plant placement scheme.
Step 4, to k kind placement scheme (k=1,2 ..., K) usage data filtering algorithm, for j kind Scene Simulation result (j=1,2 ..., J), filtering out this placement scheme is β at wind direction
m(m=1,2 ..., M) time efficient layout number
Step 5, to k kind placement scheme (k=1,2 ..., K) and calculate different wind direction β
m(m=1,2 ..., M) time sight relevance factor
record meets
m=1,2, ..., the maximum wind direction scope W of M
k, get satisfied { max (W
k), k=1,2 ..., the layout of K} is optimization layout.
In described analog result screening step, judge that the standard of efficient layout is: for any sensor layout, to every kind of leakage sight under specific wind direction, in 4 sensors, have more than 3 or 3 and covered and claim this layout to be at this wind direction and to reveal the efficient layout under sight condition by plume.
In affiliated analog result screening step, sight relevance factor is
(m=1,2 ..., Mk=1,2 ..., K).
Described analog result data screening part comprises following filtering algorithm:
Step 1, inspection sensor placement parameter L 1, d, α, actual wind direction β, whether the responsive source position of lower wind direction (L2, Y2) and leakage sight sequence number J etc. meets the requirements
Step 2, to j reveal sight (j=1,2 ..., J) and the gas diffusion length of analog result, CONCENTRATION DISTRIBUTION, diffusion time and plume width carry out interpolation, determine screening starting point
Step 3, calculating parameter γ, θ
2, θ
4, W
1, and W
2, wherein γ be 2, No. 4 sensors taking source of leaks as summit with cardinal wind angle, θ
2, θ
4be 2, No. 4 sensors taking source of leaks as summit with the angle of actual wind direction, W
1for environment sensitive spot is apart from the vertical range of plume center line, W
2for the plume half-breadth at environment sensitive spot place
Whether step 4, inspection sensor placement are efficient layout under this leakage sight and actual wind direction, if so, continue; If not, skip and record this and reveal sight, continue step 2
Pollution source concentration and the diffusion time of step 5,3 effective sensor positions of extraction.
Step 6, inspection are revealed gas and whether can be diffused to lower wind direction environment sensitive spot, and computing environment sensitive spot is at j the location parameter Q revealing in sight
j.If can, continue step 7, if can not, record this sequence number and continue step 2.
Step 7, concentration and the diffusion time of extracting lower wind direction environment sensitive spot place harmful gas.
Step 8, all sensing station concentration of extracting and time value and lower wind direction sensitive spot concentration and time value are arranged and preserved.
The described method that judges whether gas leakage can diffuse to lower wind direction environment sensitive spot is: the location parameter Q of computing environment sensitive spot in gas leakage plume
j=W
1/ W
2if, Q
j≤ 1, environment sensitive spot is subject to gas leakage and extends influence, otherwise unaffected.
Described neural metwork training part implementation procedure is as follows:
Step 1, determine network input, using scene, available parameter is as input, comprise pressure store (p), wind speed (v), wind direction (β), temperature (T), humidity (h), atmospheric stability (S), the effective concentration measured value (c of 3 gas sensors of wind direction under risk source
1, c
2, c
3) and time of fire alarming (t
1, t
2, t
3), the position (L of lower wind direction sensitive spot
2, Y
2)
Step 2, determine network output, below the concentration (c) that arrives of wind direction environment sensitive spot place harmful gas and time (t) as exporting.
Step 3, network internal structure are determined, use feedforward neural network (BP network), comprise a non-linear hidden layer (sigmoid transport function) and a linear output layer (linear transport function), and network does not comprise backfeed loop.
Step 4, according to input and output requirement, usage data filtering algorithm is prepared the verification msg of input and output data matrix and redundancy.(matrix column is the each key elements of input and output, the inputoutput data of the different sights of behavior)
Step 5, use MATLAB Neural Network Toolbox, unify training method according to single neural network used to inputoutput data training, obtains network parameter.
Step 6, use redundant input data are inputted as neural network, the difference of comparing cell output and redundancy output, evaluation prediction precision.
Described neural network and sensing system integration section comprise the steps:
Step 1, set up the area map of the environment sensitive spot of wind direction under single risk source and cardinal wind.
Step 2, certain single risk source is carried out to venture analysis, identify possible leakage sight and simulate revealing sight.
The sensor placement of step 3, executing data screening step optimizes, and the maximum that obtains this sensor placement wind direction under cardinal wind is suitable for angle.
Step 4, all environment sensitive spots within the scope of the maximum use angle of wind direction under this risk source cardinal wind are carried out to data screening, obtain the input and output matrix of one group of neural metwork training.
Step 5, usage data screen that the neural network input and output matrix obtaining is trained and precision of prediction assessment.
Step 6, the neural network parameter that training is obtained are made into application program that can Automatically invoked, make the DCS data of sensor gather and to use application computes by data-interface.
When step 7, true accident occur, sensor impact (comprising the time and the concentration that whether affect environment sensitive spot or gas leakage and arrive the environment sensitive spot)-decision-maker that prefabricated application program-prediction reveals diffusion couple environment sensitive spot that reports to the police-start judges whether to need evacuation.
Compared with prior art; the present invention proposes a kind of simple optimizing method of the sensor placement that processes toxic and harmful factory; and introducing and employment risk identification in early stage; the method for quick predicting of numerical simulation and neural metwork training; to can predict timely and effectively the range of scatter of toxic and harmful in the time that accident occurs, for garden surrounding resident district evacuating personnel and protection provide decision support.On the basis of the existing toxic and harmful sensor in garden, for garden production technology and surrounding enviroment, complete garden production run risk is identified, reveal Scene Simulation, improve sensor placement and carry out neural metwork training, overcome toxic gas leakage accident generation alarm information and be not enough to the deficiency of supporting that accident emergency responds, ensured applicability and the accuracy of method.
Brief description of the drawings
Fig. 1 is the process flow diagram of one embodiment of the invention method.
Fig. 2 is one embodiment of the invention method application scenario schematic diagram.
Fig. 3 is sensor placement's Optimal Curve that one embodiment of the invention method obtains.
Fig. 4 is the rudimentary algorithm of one embodiment of the invention method for data screening
Fig. 5 is the neural network structure figure of one embodiment of the invention method application.
Fig. 6 is the neural network redundant data checking of one embodiment of the invention method application.
Fig. 7 is that the neural network of one embodiment of the invention method application is to the whether affected judgement in sensitizing range.
Embodiment
Describe embodiments of the present invention in detail below in conjunction with drawings and Examples.
Fig. 1 is the process flow diagram of method according to an embodiment of the invention, and method according to an embodiment of the invention comprises:
-risk factors identification step
Utilize risk assessment identification risks and assumptions and accident sight factor and judge the indispensable element of contingent all kinds of leakage sights, comprise risk elements and accident scenario factors.These key elements comprise and are not limited to specified risk material kind (poisonous/inflammable gas or volatile liquid), reserves/consumption, storage location (volume coordinate), storage form (pressure, temperature, equipment), wind speed, humidity, temperature, atmospheric stability, surrounding enviroment sensitive spot position (volume coordinate) etc.Then determine respectively the span (for continuous variable) of each risks and assumptions and accident situational factor, in the span of each factor, respectively with a fixed step size number of partitions value sequence (step-length must not exceed this factor span 10%), finally each value of different risks and assumptions/accident sight factors is combined into a large amount of contingent leakage sights.As total n kind risk factors, each risk factors have N
iplant value (N
i>=1, integer), total
plant and reveal sight.
-leakage Scene Simulation step
This step is used traditional gas diffusion model, and all kinds of leakage sights that identify in previous step are carried out to numerical simulation, obtains toxic and harmful diffusion data and distribution situation under different situations.Available model comprises Gauss and class Gauss diffusion model (Gaussian Plume Model), Fluid Mechanics Computation (CFD) model and PHAST, FLACS, SLAB, ALOHA, HGSYSTEM etc.
-valid data screening step
Figure 2 shows that the location diagram of the risk source-plume-sensor-lower wind direction sensitive spot of valid data screening step.Analog result screening step need to be carried out layout optimization to one group of 4 sensor, and 4 sensors employing regular polygon structures, and serial number is 1～4, and the spacing of adjacent numbering sensor equates.Optimization Steps is as follows:
Step 1, according to the position of source of leaks and garden layout, the detectability of sensor, determines basic layout parameter L
1, the span of d and α.Wherein L
1be the distance of No. 1 sensor distance source of leaks, d is transducer spacing, and α is 1/2. of 1-2 and 1-4 sensor angle
Step 2, according to wind frequently information determine cardinal wind, sensor is arranged symmetrically in cardinal wind leeward upwards, actual wind direction and cardinal wind angle are β.And get a higher value β
0interval as optimizing, by its discrete be actual wind direction sequence (β
1, β
2..., β
m), sequence length is M.(generally get β
0=50 °, by discrete to interval [50 °, 50 °] be the wind direction sequence at 1 °, interval)
Step 3, to layout parameter L1, d, α is separated into argument sequence in span, length is respectively P
1, P
2, P
3, composition
plant placement scheme.
Step 4, to k kind placement scheme (k=1,2 ..., K) usage data filtering algorithm, for j kind Scene Simulation result (j=1,2 ..., J), filtering out this placement scheme is β at wind direction
m(m=1,2 ..., M) time efficient layout number
wherein efficient layout is defined as: for any sensor layout, to every kind of leakage sight under specific wind direction, have 3 or 3 above placement schemes that covered (can detect plume concentration) by plume in 4 sensors.
Step 5, to k kind placement scheme (k=1,2 ..., K) and calculate different wind direction β
m(m=1,2 ..., M) time sight relevance factor
(m=1,2 ..., M k=1,2 ..., K), record meets
m=1,2, ..., the maximum wind direction scope W of M
k, get satisfied { max (W
k), k=1,2 ..., the layout of K} is optimization layout.
Fig. 3 is by L
1=[40,60,80] m, d=[20,30,40] m and α=[30 °, 45 °, 60 °] value composition 27 in the layout optimization result of placement scheme (Fig. 3 d).Under the condition that is 95% in sight utilization rate, the scheme L of sensor placement
1=40m, d=20m and α=60 ° are optimization layout, the maximum wind direction scope of application of this layout is 20 °～20 ° of ﹣.After determining sensor optimization layout, use the filtering algorithm shown in Fig. 4 to carry out analog result screening:
Step 1, inspection sensor placement parameter L 1, d, α, actual wind direction β, whether the responsive source position of lower wind direction (L2, Y2) and leakage sight sequence number j etc. meets the requirements
Step 2, to j reveal sight (j=1,2 ..., J) and the gas diffusion length of analog result, CONCENTRATION DISTRIBUTION, diffusion time and plume width carry out interpolation, determine screening starting point
Step 3, calculating parameter γ, θ
2, θ
4, W
1, and W
2, wherein γ be 2, No. 4 sensors taking source of leaks as summit with cardinal wind angle, θ
2, θ
4be 2, No. 4 sensors taking source of leaks as summit with the angle of actual wind direction, W
1for environment sensitive spot is apart from the vertical range of plume center line, W
2for the plume half-breadth at environment sensitive spot place
Whether step 4, inspection sensor placement are efficient layout (effective sensor number is greater than 3) under this leakage sight and actual wind direction, if so, continue; If not, skip and record this and reveal sight, continue step 2
Pollution source concentration and the diffusion time of step 5,3 effective sensor positions of extraction.
Step 6, inspection are revealed gas and whether can be diffused to lower wind direction environment sensitive spot, and computing environment sensitive spot is at j the location parameter Q revealing in sight
j=W
1/ W
2.If can, i.e. Q
j≤ 1, continue step 7, if can not, i.e. Q
j>1, records this sequence number and continues step 2.
Step 7, concentration and the diffusion time of extracting lower wind direction environment sensitive spot place harmful gas.
Step 8, all sensing station concentration of extracting and time value and lower wind direction sensitive spot concentration and time value are arranged and preserved.
-neural metwork training step
Neural metwork training part implementation procedure is as follows:
Step 1, determine network input, using scene, available parameter is as input, comprise pressure store (p), wind speed (v), wind direction (β), temperature (T), humidity (h), atmospheric stability (S), the effective concentration measured value (c of 3 gas sensors of wind direction under risk source
1, c
2, c
3) and time of fire alarming (t
1, t
2, t
3), the position (L of lower wind direction sensitive spot
2, Y
2)
Step 2, determine network output, below the concentration (c) that arrives of wind direction environment sensitive spot place harmful gas and time (t) as exporting.
Step 3, network internal structure are determined, as shown in Figure 5, use feedforward neural network (BP network), comprise a non-linear hidden layer (sigmoid transport function) and a linear output layer (linear transport function), and network does not comprise backfeed loop.
Step 4, according to input and output requirement, usage data filtering algorithm is prepared the verification msg of input and output data matrix and redundancy.(matrix column is the each key elements of input and output, the inputoutput data of the different sights of behavior)
Step 5, use MATLAB Neural Network Toolbox, unify training method according to single neural network used to inputoutput data training, obtains network parameter.
Step 6, use redundant input data are inputted as neural network, the difference of comparing cell output and redundancy output, evaluation prediction precision.As Fig. 6 has shown the neural network prediction situation of a chlorine gas leakage embodiment.In figure, the ordinate of all subgraphs is under specific leakage situation, according to the position of 3 sensor warning messages, weather condition and lower wind direction sensitizing range, uses neural network to lower wind direction sensitizing range
(a) concentration of chlorine (ppm)
(b) chlorine arrives the time (s) of sensitive position
(c) the half-breadth W2(m of sensitive position plume)
(d) sensitive position is apart from the vertical range W1(m of actual wind direction)
The horizontal ordinate of Fig. 6 a～6d is the result of Phast simulation, in theory, in figure, the fitting result of loose point should be straight line y=x, actual result shows, only have the neural network prediction result of chlorine gas concentration to compare Phast analog result (slope is about 0.93) less than normal, predicting the outcome of chlorine time of arrival, W1 and W2 is all very accurate.
Utilize W1 that Fig. 6 c and 6d obtain and the value of W2 can predict whether lower wind direction sensitizing range is subject to the threat of chlorine leakage, as shown in Figure 7, horizontal ordinate is the quantity of the leakage sight used:
(a) relative error of neural network concentration prediction value and the Phast analogue value
(b) the W1/W2 ratio calculating according to the W1 of neural network prediction in Fig. 6 and W2
(c) according to W1/W2 ratio that in Phast simulation and plume, reconnaissance obtains
(d) subtract each other by predicting after W1/W2 and theoretical W1/W2 value round the logical consequence obtaining
Can find that according to (a) maximum error of neural network prediction value compared with theoretical value is no more than 30%, Fig. 7 b and 7c are very approaching, its difference shows in 7d: reveal in sight in 2780 examples, there are 2 examples to reveal wind direction sensitive spot under sight and are subject in theory chlorine gas leakage threat, but the result of neural network prediction shows that it is not on the hazard, be called " failing to report ", rate of failing to report is 0.072%; On the other hand, only have 14 examples to reveal to thank in sights and share sensitive spot and be not on the hazard in theory, but neural network prediction shows that it has been subject to threat, is called " wrong report ", rate of false alarm is 0.504%.
Step 7, the neural network parameter that training is obtained are made into application program that can Automatically invoked, make the DCS data of sensor gather and to use application computes by data-interface.
When step 8, true accident occur, sensor impact (comprising the time and the concentration that whether affect environment sensitive spot or gas leakage and arrive the environment sensitive spot)-decision-maker that prefabricated application program-prediction reveals diffusion couple environment sensitive spot that reports to the police-start judges whether to need evacuation.
Claims (10)
1. a chemical leakage fast prediction early warning emergency response decision-making technique, comprises the integrated double teacher altogether of risk factors identification, sight numerical simulation, analog result screening, neural metwork training and training result and sensing system, it is characterized in that:
Risk factors identification comprises: the risk factors of identification chemical industrial park, quantize each risk elements and according to risk elements and the span thereof of identification, reasonable value also combines various contingent leakage sights;
The sight numerical simulation stage comprises: all contingent leakage sight forming in garden risk factors identification step is simulated, to obtain the different coverages of revealing gas under sight of revealing;
Analog result screening comprises:
Key parameter in a kind of placement scheme that comprises 4 gas sensors is optimized, utilizes the leakage gas concentration distribution that simulation obtains to carry out simple optimizing, obtain Shi sensor placement;
According to definite sensor placement's scheme, be extracted in the environment sensitive spot gas leakage diffusion data that sensor placement can measure the virtual detection data within the scope of wind direction and match, prepare training data and checking data according to the training logic of neural network;
Neural metwork training step comprises:
Set up the feedforward neural network for Function Fitting, the input and output using ready training data as neural metwork training, computational grid parameter;
By check data importation input neural network, result part and the contrast of neural network prediction result, evaluation prediction precision;
Neural network and sensor and garden control system integration step:
The sunykatuib analysis of each risk source and training result are combined with the form of database and calling program with the geographical location information of risk source and environment sensitive spot, and provide and the data-interface of sensing system, realize the workflow of from the accident-sensor warning-model fast prediction-aid decision making.
2. chemical leakage fast prediction early warning emergency response decision-making technique according to claim 1, is characterized in that, described garden risk identification part is made up of following steps:
Step 1, utilize risk assessment identification risks and assumptions and accident sight factor and judge the indispensable element of contingent all kinds of leakage sights, comprise risk elements and accident scenario factors;
The span of step 2, respectively definite each risks and assumptions and accident situational factor, in the span of each factor respectively with a fixed step size number of partitions value sequence, wherein step-length must not exceed 10% of this factor span, finally each value of different risks and assumptions/accident sight factors is combined into a large amount of contingent leakage sights, in the time of total n kind risk factors, each risk factors have N
iplant value (N
i>=1, integer), total
plant and reveal sight.
3. chemical leakage fast prediction early warning emergency response decision-making technique according to claim 1, it is characterized in that, the numerical model that the described sight numerical simulation stage is used comprises: Gauss and class Gauss diffusion model (Gaussian Plume Model), Fluid Mechanics Computation (CFD) model and PHAST, FLACS, SLAB, ALOHA and HGSYSTEM Integrated Models, finally obtain J kind and reveal Scene Simulation result.
4. chemical leakage fast prediction early warning emergency response decision-making technique according to claim 1, it is characterized in that, described analog result screening step is carried out layout optimization to one group of 4 sensor, and 4 sensors adopt regular polygon structure, serial number is 1～4, the spacing of adjacent numbering sensor is equal, and Optimization Steps is as follows:
Step 1, according to the position of source of leaks and garden layout, the detectability of sensor, determines basic layout parameter L
1, the span of d and α, wherein L
1be the distance of No. 1 sensor distance source of leaks, d is transducer spacing, and α is 1/2 of 1-2 and 1-4 sensor angle;
Step 2, according to wind frequently information determine cardinal wind, upwards, actual wind direction and cardinal wind angle are β to the leeward that sensor is arranged symmetrically in cardinal wind, and get a higher value β
0interval as optimizing, by its discrete be actual wind direction sequence (β
1, β
2..., β
m), sequence length is M;
Step 3, to layout parameter L
1, d, α is separated into argument sequence in span, and length is respectively P
1, P
2, P
3, composition
plant placement scheme;
Step 4, to k kind placement scheme (k=1,2 ..., K) usage data filtering algorithm, for j kind Scene Simulation result (j=1,2 ..., J), filtering out this placement scheme is β at wind direction
m(m=1,2 ..., M) time efficient layout number
Step 5, to k kind placement scheme (k=1,2 ..., K) and calculate different wind direction β
m(m=1,2 ..., M) time sight relevance factor
record meets
m=1,2, ..., the maximum wind direction scope W of M
k, get satisfied { max (W
k), k=1,2 ..., the layout of K} is optimization layout.
5. chemical leakage fast prediction early warning emergency response decision-making technique according to claim 4, it is characterized in that, in described analog result screening step, judge that the standard of efficient layout is: for any sensor layout, to every kind of leakage sight under specific wind direction, in 4 sensors, have more than 3 or 3 and covered and claim this layout to be at this wind direction and to reveal the efficient layout under sight condition by plume.
6. according to the chemical leakage fast prediction early warning emergency response decision-making technique described in claim 4 or 5, it is characterized in that, in affiliated analog result screening step, sight relevance factor is
(m=1,2 ..., Mk=1,2 ..., K).
7. chemical leakage fast prediction early warning emergency response decision-making technique according to claim 6, is characterized in that, described analog result data screening part comprises following filtering algorithm:
Step 1, inspection sensor placement parameter L 1, d, α, actual wind direction β, whether the responsive source position of lower wind direction (L2, Y2) and leakage sight sequence number J meet the requirements;
Step 2, to j reveal sight (j=1,2 ..., J) and the gas diffusion length of analog result, CONCENTRATION DISTRIBUTION, diffusion time and plume width carry out interpolation, determine screening starting point;
Step 3, calculating parameter γ, θ
2, θ
4, W
1, and W
2, wherein γ be No. 2 or No. 4 sensors taking source of leaks as summit and the angle of cardinal wind, θ
2be No. 2 sensors taking source of leaks as summit and the angle of actual wind direction, θ
4be No. 4 sensors taking source of leaks as summit and the angle of actual wind direction, W
1for environment sensitive spot is apart from the vertical range of plume center line, W
2for the plume half-breadth at environment sensitive spot place;
Whether step 4, inspection sensor placement are efficient layout under this leakage sight and actual wind direction, if so, continue; If not, skip and record this and reveal sight, continue step 2;
Pollution source concentration and the diffusion time of step 5,3 effective sensor positions of extraction;
Step 6, inspection are revealed gas and whether can be diffused to lower wind direction environment sensitive spot, and computing environment sensitive spot is at j the location parameter Q revealing in sight
jif, can, continue step 7, if can not, record this sequence number and continue step 2;
Step 7, concentration and the diffusion time of extracting lower wind direction environment sensitive spot place harmful gas;
Step 8, all sensing station concentration of extracting and time value and lower wind direction sensitive spot concentration and time value are arranged and preserved.
8. according to the chemical leakage fast prediction early warning emergency response decision-making technique described in claim 1 or 7, it is characterized in that, the described method that judges whether gas leakage can diffuse to lower wind direction environment sensitive spot is: the location parameter Q of computing environment sensitive spot in gas leakage plume
j=W
1/ W
2if, Q
j≤ 1, environment sensitive spot is subject to gas leakage and extends influence, otherwise unaffected.
9. chemical leakage fast prediction early warning emergency response decision-making technique according to claim 1, is characterized in that, described neural metwork training part implementation procedure is as follows:
Step 1, determine network input, using scene, available parameter is as input, comprise pressure store (p), wind speed (v), wind direction (β), temperature (T), humidity (h), atmospheric stability (S), the effective concentration measured value (c of 3 gas sensors of wind direction under risk source
1, c
2, c
3) and time of fire alarming (t
1, t
2, t
3), the position (L of lower wind direction sensitive spot
2, Y
2);
Step 2, determine network output, below the concentration (c) that arrives of wind direction environment sensitive spot place harmful gas and time (t) as exporting;
Step 3, network internal structure are determined, using feedforward neural network is BP network, comprises a non-linear hidden layer and a linear output layer, and non-linear hidden layer is got sigmoid transport function, linear output layer is got linear transport function, and network does not comprise backfeed loop;
Step 4, according to input and output requirement, usage data filtering algorithm is prepared the verification msg of input and output data matrix and redundancy;
Step 5, use MATLAB Neural Network Toolbox, unify training method according to single neural network used to inputoutput data training, obtains network parameter;
Step 6, use redundant input data are inputted as neural network, the difference of comparing cell output and redundancy output, evaluation prediction precision.
10. chemical leakage fast prediction early warning emergency response decision-making technique according to claim 1, is characterized in that, described neural network and sensing system integration section comprise the steps:
Step 1, set up the area map of the environment sensitive spot of wind direction under single risk source and cardinal wind;
Step 2, certain single risk source is carried out to venture analysis, identify possible leakage sight and simulate revealing sight;
The sensor placement of step 3, executing data screening step optimizes, and the maximum that obtains this sensor placement wind direction under cardinal wind is suitable for angle;
Step 4, all environment sensitive spots within the scope of the maximum use angle of wind direction under this risk source cardinal wind are carried out to data screening, obtain the input and output matrix of one group of neural metwork training;
Step 5, usage data screen that the neural network input and output matrix obtaining is trained and precision of prediction assessment;
Step 6, the neural network parameter that training is obtained are made into application program that can Automatically invoked, make the DCS data of sensor gather and to use application computes by data-interface;
When step 7, true accident occur, the sensor impact-decision-maker that prefabricated application program-prediction reveals diffusion couple environment sensitive spot that reports to the police-start judges whether to need evacuation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410136961.5A CN103914622B (en) | 2014-04-04 | 2014-04-04 | A kind of chemical leakage fast prediction alarm emergency response decision-making method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410136961.5A CN103914622B (en) | 2014-04-04 | 2014-04-04 | A kind of chemical leakage fast prediction alarm emergency response decision-making method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103914622A true CN103914622A (en) | 2014-07-09 |
| CN103914622B CN103914622B (en) | 2017-07-07 |
Family
ID=51040298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410136961.5A Active CN103914622B (en) | 2014-04-04 | 2014-04-04 | A kind of chemical leakage fast prediction alarm emergency response decision-making method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103914622B (en) |
Cited By (56)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104346657A (en) * | 2014-11-10 | 2015-02-11 | 张江华 | Optimal evacuation method and system for dangerous chemical leakage |
| CN104376361A (en) * | 2014-10-15 | 2015-02-25 | 南京航空航天大学 | Nuclear accident source item inversion method based on BP neural network algorithm |
| CN104680023A (en) * | 2015-03-12 | 2015-06-03 | 重庆科技学院 | Multi-objective-decision-based pumping unit parameter optimization method |
| CN104680025A (en) * | 2015-03-12 | 2015-06-03 | 重庆科技学院 | Oil pumping unit parameter optimization method on basis of genetic algorithm extreme learning machine |
| CN104792468A (en) * | 2015-04-07 | 2015-07-22 | 中国石油大学(华东) | Optimal locating method of gas detection alarms of oil refining device |
| CN104792935A (en) * | 2015-03-20 | 2015-07-22 | 北京华泰诺安科技有限公司 | Cloud analysis system for nuclear biological and chemical threat |
| CN104880494A (en) * | 2015-06-02 | 2015-09-02 | 大连市环境监测中心 | Environmental monitoring terminal and quick deployment system of environmental emergency monitoring |
| CN104950708A (en) * | 2015-06-02 | 2015-09-30 | 大连市环境监测中心 | Aerial environment monitoring terminal and environmental emergency monitoring and deploying system |
| CN106267620A (en) * | 2015-06-10 | 2017-01-04 | 张国基 | Chemical leakage processes car |
| CN106644284A (en) * | 2016-12-16 | 2017-05-10 | 北京伟瑞迪科技有限公司 | Automatic leakage monitoring and repairing system for chemical plant device |
| CN106770930A (en) * | 2016-11-24 | 2017-05-31 | 北京蓝色星语科技有限公司 | A kind of use unmanned plane carries out the method and system of hazardous material detection |
| CN107607671A (en) * | 2017-08-24 | 2018-01-19 | 慧感(上海)物联网科技有限公司 | A kind of gas leakage source localization method |
| CN108091111A (en) * | 2017-11-20 | 2018-05-29 | 淮阴工学院 | A kind of oil truck oil and gas leakage intelligent early-warning system |
| CN108596364A (en) * | 2018-03-29 | 2018-09-28 | 杭州电子科技大学 | A kind of chemical industrial park major hazard source dynamic early-warning method |
| CN108733881A (en) * | 2018-04-13 | 2018-11-02 | 同济大学 | Cope with the processing method for the air pollution that happens suddenly in public building room |
| CN108733893A (en) * | 2018-04-25 | 2018-11-02 | 同济大学 | The public building burst pollution of coupling depth learning method is traced to the source |
| CN108932379A (en) * | 2018-06-26 | 2018-12-04 | 山东睿益环境技术有限公司 | A kind of evacuating personnel emergence treating method and its application |
| CN109324155A (en) * | 2018-10-31 | 2019-02-12 | 中国石油天然气股份有限公司 | Refining device tail gas pollutant on-line monitoring data early warning method and device |
| CN109737309A (en) * | 2019-01-09 | 2019-05-10 | 慧感(上海)物联网科技有限公司 | A kind of risk source based on risk identification leaks source tracing method and its system surely |
| CN110046834A (en) * | 2019-05-13 | 2019-07-23 | 苏州大学 | Workplace pernicious gas health risk quantitative evaluating system and its appraisal procedure |
| EP3378027A4 (en) * | 2015-11-19 | 2019-08-28 | Halliburton Energy Services, Inc. | Method and system for monitoring and predicting gas leak |
| CN110472359A (en) * | 2019-08-21 | 2019-11-19 | 东北大学 | High-temperature fusion molten aluminum and water contact explositions based on numerical simulation technology prevent method for early warning |
| CN110531030A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of method and device based on the analysis of Internet of Things big data atmosphere pollution |
| CN110674983A (en) * | 2019-09-05 | 2020-01-10 | 辽宁工程技术大学 | Working face gas early warning method based on copula function tail correlation analysis |
| CN110874807A (en) * | 2018-09-03 | 2020-03-10 | 中国石油化工股份有限公司 | Inhalation poison leakage emergency response disposal card and use method and application thereof |
| CN111105086A (en) * | 2019-12-16 | 2020-05-05 | 茂盟（上海）工程技术股份有限公司 | Visual layout system and method for cooling, heating and power load prediction |
| CN111127279A (en) * | 2019-12-31 | 2020-05-08 | 中国科学院合肥物质科学研究院 | Nuclear emergency decision-making system and method based on monitoring experiment database and storage medium |
| CN111144055A (en) * | 2019-12-27 | 2020-05-12 | 苏州大学 | Method, device and medium for determining toxic heavy gas leakage concentration distribution in urban environment |
| CN111157680A (en) * | 2019-12-31 | 2020-05-15 | 北京辰安科技股份有限公司 | Indoor volatile substance leakage tracing method and device |
| US10663367B2 (en) | 2017-07-28 | 2020-05-26 | International Business Machines Corporation | Adaptive sensing for a gas leak detection |
| CN111583067A (en) * | 2020-03-31 | 2020-08-25 | 西南交通大学 | Urban underground large space construction safety early warning and emergency decision-making method and system |
| CN112270502A (en) * | 2020-11-17 | 2021-01-26 | 北京三维天地科技股份有限公司 | Environment emergency task cooperative disposal platform based on artificial intelligence technology |
| CN112330082A (en) * | 2020-08-13 | 2021-02-05 | 青岛科技大学 | Intelligent quantitative risk assessment method based on dynamic mechanism model |
| CN113095552A (en) * | 2021-03-29 | 2021-07-09 | 中国海洋石油集团有限公司 | Method and system for predicting volume of combustible gas cloud cluster leaked from ocean platform |
| CN113159337A (en) * | 2021-04-08 | 2021-07-23 | 柳州东风容泰化工股份有限公司 | Emergency treatment method and device for o-chlorophenol leakage |
| CN113330483A (en) * | 2019-09-18 | 2021-08-31 | 拜耳公司 | Predicting magnetic resonance imaging images by predictive models trained by supervised learning |
| CN113468815A (en) * | 2021-07-12 | 2021-10-01 | 南京航空航天大学 | Liquid hazardous chemical substance volatilization concentration estimation method based on Gaussian diffusion model and deep neural network |
| CN113624921A (en) * | 2021-08-04 | 2021-11-09 | 杭州谱育科技发展有限公司 | Multi-mode comprehensive pollution tracing method |
| CN113821989A (en) * | 2020-06-18 | 2021-12-21 | 中国石油化工股份有限公司 | Emergency disposal simulation risk equipment modeling method and device and storage medium |
| CN114001867A (en) * | 2021-10-19 | 2022-02-01 | 北京伟瑞迪科技有限公司 | Monitoring and coping method for gas leakage of park |
| CN114023043A (en) * | 2021-10-13 | 2022-02-08 | 厦门理工学院 | Safety early warning method for leaked gas |
| CN114241723A (en) * | 2021-12-30 | 2022-03-25 | 武汉市三藏科技有限责任公司 | Environmental monitoring alarm device and method based on Gaussian atmospheric diffusion |
| CN114263855A (en) * | 2021-11-19 | 2022-04-01 | 合肥工业大学 | Method for predicting leakage of natural gas transportation pipeline and application thereof |
| WO2022126544A1 (en) * | 2020-12-17 | 2022-06-23 | 西门子（中国）有限公司 | Method and devices for determining pollution source, and computer-readable storage medium |
| CN114792165A (en) * | 2022-05-06 | 2022-07-26 | 湖南五凌电力科技有限公司 | Gas concentration early warning method and device based on wavelet neural network |
| CN115019482A (en) * | 2022-08-04 | 2022-09-06 | 武汉鼎业环保工程技术有限公司 | Dangerous gas itinerant early warning method and device based on big data |
| CN115600643A (en) * | 2022-10-17 | 2023-01-13 | 中国科学技术大学（Cn） | Method and system for rapidly predicting toxic gas |
| CN116403165A (en) * | 2023-06-05 | 2023-07-07 | 交通运输部水运科学研究所 | Dangerous chemical leakage emergency treatment method, dangerous chemical leakage emergency treatment device and readable storage medium |
| CN117172477A (en) * | 2023-09-05 | 2023-12-05 | 上海朗晖慧科技术有限公司 | Chemical product production monitoring management system and method based on big data |
| CN117290639A (en) * | 2023-11-24 | 2023-12-26 | 深圳大学 | Method and system for positioning and detecting material leakage in phase-change energy storage tank |
| CN117709845A (en) * | 2023-12-02 | 2024-03-15 | 国网浙江省电力有限公司 | Storage intelligent management and control system for distinguishing material properties |
| CN117789422A (en) * | 2024-02-26 | 2024-03-29 | 江西依爱弘泰消防安全技术有限公司 | Combustible gas alarm control system and method |
| EP4195091A4 (en) * | 2020-09-11 | 2024-04-03 | Siemens Ltd. China | Target available model-based environment prediction method and apparatus, program, and electronic device |
| CN117959902A (en) * | 2024-04-01 | 2024-05-03 | 大连华邦化学有限公司 | Gas purification function early warning system and method based on data feedback |
| CN118133709A (en) * | 2024-02-06 | 2024-06-04 | 同济大学 | Limited space hydrogen leakage detection and rapid positioning method based on hydrodynamic simulation |
| WO2024124861A1 (en) * | 2022-12-14 | 2024-06-20 | 中国石油大学(华东) | Method and system for optimizing hydrogen detector spatial-arrangement solution on basis of risk assessment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0916000D0 (en) * | 2009-09-11 | 2009-10-28 | Selex Sensors & Airborne Sys | Sensing network and method |
| CN102313793B (en) * | 2011-09-07 | 2014-03-05 | 中国环境科学研究院 | Monitoring system of multi-component gas pollutants in air of chemical industrial park |
-
2014
- 2014-04-04 CN CN201410136961.5A patent/CN103914622B/en active Active
Cited By (77)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376361A (en) * | 2014-10-15 | 2015-02-25 | 南京航空航天大学 | Nuclear accident source item inversion method based on BP neural network algorithm |
| CN104346657A (en) * | 2014-11-10 | 2015-02-11 | 张江华 | Optimal evacuation method and system for dangerous chemical leakage |
| CN104680023A (en) * | 2015-03-12 | 2015-06-03 | 重庆科技学院 | Multi-objective-decision-based pumping unit parameter optimization method |
| CN104680025A (en) * | 2015-03-12 | 2015-06-03 | 重庆科技学院 | Oil pumping unit parameter optimization method on basis of genetic algorithm extreme learning machine |
| CN104680023B (en) * | 2015-03-12 | 2017-08-29 | 重庆科技学院 | Oil pumper parameter optimization method based on multiobjective decision-making |
| CN104680025B (en) * | 2015-03-12 | 2017-08-25 | 重庆科技学院 | Oil pumper parameter optimization method based on genetic algorithm extreme learning machine |
| CN104792935A (en) * | 2015-03-20 | 2015-07-22 | 北京华泰诺安科技有限公司 | Cloud analysis system for nuclear biological and chemical threat |
| CN104792468A (en) * | 2015-04-07 | 2015-07-22 | 中国石油大学(华东) | Optimal locating method of gas detection alarms of oil refining device |
| CN104792468B (en) * | 2015-04-07 | 2016-04-06 | 中国石油大学(华东) | A kind of oil refining apparatus gas detecting and alarming instrument optimization placement method |
| CN104880494A (en) * | 2015-06-02 | 2015-09-02 | 大连市环境监测中心 | Environmental monitoring terminal and quick deployment system of environmental emergency monitoring |
| CN104950708A (en) * | 2015-06-02 | 2015-09-30 | 大连市环境监测中心 | Aerial environment monitoring terminal and environmental emergency monitoring and deploying system |
| CN106267620A (en) * | 2015-06-10 | 2017-01-04 | 张国基 | Chemical leakage processes car |
| CN106267620B (en) * | 2015-06-10 | 2019-06-28 | 张国基 | Chemical leakage handles vehicle |
| EP3378027A4 (en) * | 2015-11-19 | 2019-08-28 | Halliburton Energy Services, Inc. | Method and system for monitoring and predicting gas leak |
| CN106770930B (en) * | 2016-11-24 | 2019-04-16 | 北京蓝色星语科技有限公司 | A kind of method and system carrying out hazardous material detection using unmanned plane |
| CN106770930A (en) * | 2016-11-24 | 2017-05-31 | 北京蓝色星语科技有限公司 | A kind of use unmanned plane carries out the method and system of hazardous material detection |
| CN106644284A (en) * | 2016-12-16 | 2017-05-10 | 北京伟瑞迪科技有限公司 | Automatic leakage monitoring and repairing system for chemical plant device |
| CN106644284B (en) * | 2016-12-16 | 2019-07-12 | 北京伟瑞迪科技有限公司 | Automatic leakage monitoring and repairing system for chemical plant device |
| US10663367B2 (en) | 2017-07-28 | 2020-05-26 | International Business Machines Corporation | Adaptive sensing for a gas leak detection |
| CN107607671A (en) * | 2017-08-24 | 2018-01-19 | 慧感(上海)物联网科技有限公司 | A kind of gas leakage source localization method |
| CN108091111A (en) * | 2017-11-20 | 2018-05-29 | 淮阴工学院 | A kind of oil truck oil and gas leakage intelligent early-warning system |
| CN108596364B (en) * | 2018-03-29 | 2021-09-21 | 杭州电子科技大学 | Dynamic early warning method for major hazard source in chemical industry park |
| CN108596364A (en) * | 2018-03-29 | 2018-09-28 | 杭州电子科技大学 | A kind of chemical industrial park major hazard source dynamic early-warning method |
| CN108733881A (en) * | 2018-04-13 | 2018-11-02 | 同济大学 | Cope with the processing method for the air pollution that happens suddenly in public building room |
| CN108733881B (en) * | 2018-04-13 | 2021-10-12 | 同济大学 | Treatment method for dealing with sudden indoor air pollution of public building |
| CN108733893A (en) * | 2018-04-25 | 2018-11-02 | 同济大学 | The public building burst pollution of coupling depth learning method is traced to the source |
| CN108932379A (en) * | 2018-06-26 | 2018-12-04 | 山东睿益环境技术有限公司 | A kind of evacuating personnel emergence treating method and its application |
| CN110874807A (en) * | 2018-09-03 | 2020-03-10 | 中国石油化工股份有限公司 | Inhalation poison leakage emergency response disposal card and use method and application thereof |
| CN109324155A (en) * | 2018-10-31 | 2019-02-12 | 中国石油天然气股份有限公司 | Refining device tail gas pollutant on-line monitoring data early warning method and device |
| CN109737309A (en) * | 2019-01-09 | 2019-05-10 | 慧感(上海)物联网科技有限公司 | A kind of risk source based on risk identification leaks source tracing method and its system surely |
| CN109737309B (en) * | 2019-01-09 | 2021-05-04 | 慧感(上海)物联网科技有限公司 | Risk source and leakage tracing method and system based on risk identification |
| CN110046834A (en) * | 2019-05-13 | 2019-07-23 | 苏州大学 | Workplace pernicious gas health risk quantitative evaluating system and its appraisal procedure |
| CN110046834B (en) * | 2019-05-13 | 2022-06-24 | 苏州大学 | Workplace harmful gas health risk quantitative evaluation system and evaluation method thereof |
| CN110531030B (en) * | 2019-08-16 | 2021-11-12 | 北京慧辰资道资讯股份有限公司 | Method and device for analyzing atmospheric pollutants based on Internet of things big data |
| CN110531030A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of method and device based on the analysis of Internet of Things big data atmosphere pollution |
| CN110472359A (en) * | 2019-08-21 | 2019-11-19 | 东北大学 | High-temperature fusion molten aluminum and water contact explositions based on numerical simulation technology prevent method for early warning |
| CN110674983A (en) * | 2019-09-05 | 2020-01-10 | 辽宁工程技术大学 | Working face gas early warning method based on copula function tail correlation analysis |
| CN113330483A (en) * | 2019-09-18 | 2021-08-31 | 拜耳公司 | Predicting magnetic resonance imaging images by predictive models trained by supervised learning |
| CN111105086A (en) * | 2019-12-16 | 2020-05-05 | 茂盟（上海）工程技术股份有限公司 | Visual layout system and method for cooling, heating and power load prediction |
| CN111144055B (en) * | 2019-12-27 | 2024-02-02 | 苏州大学 | Method, device and medium for determining concentration distribution of toxic heavy gas leakage in urban environment |
| CN111144055A (en) * | 2019-12-27 | 2020-05-12 | 苏州大学 | Method, device and medium for determining toxic heavy gas leakage concentration distribution in urban environment |
| CN111127279B (en) * | 2019-12-31 | 2023-07-21 | 中国科学院合肥物质科学研究院 | Nuclear emergency decision system, method and storage medium based on monitoring experiment database |
| CN111157680A (en) * | 2019-12-31 | 2020-05-15 | 北京辰安科技股份有限公司 | Indoor volatile substance leakage tracing method and device |
| CN111127279A (en) * | 2019-12-31 | 2020-05-08 | 中国科学院合肥物质科学研究院 | Nuclear emergency decision-making system and method based on monitoring experiment database and storage medium |
| CN111583067A (en) * | 2020-03-31 | 2020-08-25 | 西南交通大学 | Urban underground large space construction safety early warning and emergency decision-making method and system |
| CN113821989A (en) * | 2020-06-18 | 2021-12-21 | 中国石油化工股份有限公司 | Emergency disposal simulation risk equipment modeling method and device and storage medium |
| CN112330082A (en) * | 2020-08-13 | 2021-02-05 | 青岛科技大学 | Intelligent quantitative risk assessment method based on dynamic mechanism model |
| CN112330082B (en) * | 2020-08-13 | 2023-08-15 | 青岛科技大学 | Intelligent quantitative risk assessment method based on dynamic mechanism model |
| EP4195091A4 (en) * | 2020-09-11 | 2024-04-03 | Siemens Ltd. China | Target available model-based environment prediction method and apparatus, program, and electronic device |
| CN112270502A (en) * | 2020-11-17 | 2021-01-26 | 北京三维天地科技股份有限公司 | Environment emergency task cooperative disposal platform based on artificial intelligence technology |
| WO2022126544A1 (en) * | 2020-12-17 | 2022-06-23 | 西门子（中国）有限公司 | Method and devices for determining pollution source, and computer-readable storage medium |
| CN113095552A (en) * | 2021-03-29 | 2021-07-09 | 中国海洋石油集团有限公司 | Method and system for predicting volume of combustible gas cloud cluster leaked from ocean platform |
| CN113095552B (en) * | 2021-03-29 | 2023-12-26 | 中国海洋石油集团有限公司 | Ocean platform leakage combustible gas cloud cluster volume prediction method and system |
| CN113159337A (en) * | 2021-04-08 | 2021-07-23 | 柳州东风容泰化工股份有限公司 | Emergency treatment method and device for o-chlorophenol leakage |
| CN113468815A (en) * | 2021-07-12 | 2021-10-01 | 南京航空航天大学 | Liquid hazardous chemical substance volatilization concentration estimation method based on Gaussian diffusion model and deep neural network |
| CN113624921B (en) * | 2021-08-04 | 2024-03-29 | 杭州谱育科技发展有限公司 | Multi-mode comprehensive pollution tracing method |
| CN113624921A (en) * | 2021-08-04 | 2021-11-09 | 杭州谱育科技发展有限公司 | Multi-mode comprehensive pollution tracing method |
| CN114023043A (en) * | 2021-10-13 | 2022-02-08 | 厦门理工学院 | Safety early warning method for leaked gas |
| CN114001867A (en) * | 2021-10-19 | 2022-02-01 | 北京伟瑞迪科技有限公司 | Monitoring and coping method for gas leakage of park |
| CN114263855A (en) * | 2021-11-19 | 2022-04-01 | 合肥工业大学 | Method for predicting leakage of natural gas transportation pipeline and application thereof |
| CN114263855B (en) * | 2021-11-19 | 2024-04-26 | 合肥工业大学 | Natural gas transportation pipeline leakage prediction method and application thereof |
| CN114241723A (en) * | 2021-12-30 | 2022-03-25 | 武汉市三藏科技有限责任公司 | Environmental monitoring alarm device and method based on Gaussian atmospheric diffusion |
| CN114792165A (en) * | 2022-05-06 | 2022-07-26 | 湖南五凌电力科技有限公司 | Gas concentration early warning method and device based on wavelet neural network |
| CN115019482A (en) * | 2022-08-04 | 2022-09-06 | 武汉鼎业环保工程技术有限公司 | Dangerous gas itinerant early warning method and device based on big data |
| CN115600643B (en) * | 2022-10-17 | 2023-06-09 | 中国科学技术大学 | Method and system for rapidly predicting toxic gas |
| CN115600643A (en) * | 2022-10-17 | 2023-01-13 | 中国科学技术大学（Cn） | Method and system for rapidly predicting toxic gas |
| WO2024124861A1 (en) * | 2022-12-14 | 2024-06-20 | 中国石油大学(华东) | Method and system for optimizing hydrogen detector spatial-arrangement solution on basis of risk assessment |
| CN116403165B (en) * | 2023-06-05 | 2023-08-04 | 交通运输部水运科学研究所 | Dangerous chemical leakage emergency treatment method, dangerous chemical leakage emergency treatment device and readable storage medium |
| CN116403165A (en) * | 2023-06-05 | 2023-07-07 | 交通运输部水运科学研究所 | Dangerous chemical leakage emergency treatment method, dangerous chemical leakage emergency treatment device and readable storage medium |
| CN117172477A (en) * | 2023-09-05 | 2023-12-05 | 上海朗晖慧科技术有限公司 | Chemical product production monitoring management system and method based on big data |
| CN117290639B (en) * | 2023-11-24 | 2024-02-27 | 深圳大学 | Method and system for positioning and detecting material leakage in phase-change energy storage tank |
| CN117290639A (en) * | 2023-11-24 | 2023-12-26 | 深圳大学 | Method and system for positioning and detecting material leakage in phase-change energy storage tank |
| CN117709845A (en) * | 2023-12-02 | 2024-03-15 | 国网浙江省电力有限公司 | Storage intelligent management and control system for distinguishing material properties |
| CN118133709A (en) * | 2024-02-06 | 2024-06-04 | 同济大学 | Limited space hydrogen leakage detection and rapid positioning method based on hydrodynamic simulation |
| CN117789422A (en) * | 2024-02-26 | 2024-03-29 | 江西依爱弘泰消防安全技术有限公司 | Combustible gas alarm control system and method |
| CN117959902A (en) * | 2024-04-01 | 2024-05-03 | 大连华邦化学有限公司 | Gas purification function early warning system and method based on data feedback |
| CN117959902B (en) * | 2024-04-01 | 2024-06-04 | 大连华邦化学有限公司 | Gas purification function early warning system and method based on data feedback |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103914622B (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103914622A (en) | Quick chemical leakage predicating and warning emergency response decision-making method | |
| RU2680652C2 (en) | Method of integrated environmental monitoring | |
| CN104750949B (en) | A kind of poisoning individual risk's qualitative assessment of Leakage Gas and characterizing method | |
| CN112633553B (en) | Gas pipeline-hazardous chemical enterprise coupling hidden danger identification and risk assessment method and system | |
| CN102567808B (en) | Method for forecasting and warning accident consequence of major hazard installation by combining with real-time meteorological information | |
| KR101885350B1 (en) | System for integrated managment of air pollution | |
| CN110457829A (en) | A kind of source item release inverting and DIFFUSION PREDICTION method based on integrated model of atmospheric diffusion | |
| KR101956188B1 (en) | Method for providing of analyzing information about hazardous chemicals dispersion | |
| CN203533216U (en) | Real-time positioning analysis system of gas pipe network leak sources | |
| CN104897853A (en) | Thermal power plant pollutant discharging monitoring display method based on tower type diffusion model | |
| CN103196038A (en) | Real-time positioning analysis method and system for fuel gas pipeline network leakage source | |
| Feng et al. | How much can temporally stationary factors explain cellular automata-based simulations of past and future urban growth? | |
| Mousavi et al. | A sensitivity analysis of parameters affecting the hydrogen release and dispersion using ANOVA method | |
| CN108280849A (en) | A kind of correction of pipe gallery gas leakage concentration field prediction and slip method of estimation | |
| CN115952926B (en) | Dangerous gas diffusion range prediction method, system, electronic equipment and storage medium | |
| CN116384255B (en) | Park dangerous situation perception method and system based on multi-source data fusion | |
| CN115906706A (en) | High-precision risk analysis method for domino comprehensive risk of hazardous chemical tank area | |
| CN101739790B (en) | Forecasting, early warning and emergency controlling method for a plurality of fixed chemical risk sources | |
| CN102750456B (en) | earthquake damage assessment system | |
| KR20150144380A (en) | System and method for providing air quality information by integrating virtual sensor and monitoring sensor | |
| CN115730535A (en) | Artificial intelligence reverse tracing and leakage determining method based on gas monitoring | |
| US20200117840A1 (en) | Injection of simulated sources in a system of networked sensors | |
| CN105510535B (en) | Chemical industrial park gas sensor Sector Optimization dispositions method based on field experiment | |
| CN105717257A (en) | Gas source wireless positioning method based on nonlinear least square method and extended set membership filtering | |
| KR101728611B1 (en) | 3d wind flows chemical transport model system and its modeling method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |