CN114660231B - Gas concentration prediction method, system, machine-readable storage medium and processor - Google Patents
Gas concentration prediction method, system, machine-readable storage medium and processor Download PDFInfo
- Publication number
- CN114660231B CN114660231B CN202011530289.XA CN202011530289A CN114660231B CN 114660231 B CN114660231 B CN 114660231B CN 202011530289 A CN202011530289 A CN 202011530289A CN 114660231 B CN114660231 B CN 114660231B
- Authority
- CN
- China
- Prior art keywords
- gas
- output
- sequence
- concentration
- sensor
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 230000008859 change Effects 0.000 claims abstract description 112
- 239000011159 matrix material Substances 0.000 claims abstract description 96
- 238000005259 measurement Methods 0.000 claims abstract description 39
- 238000002360 preparation method Methods 0.000 claims abstract description 29
- 239000007789 gas Substances 0.000 claims description 350
- 238000012360 testing method Methods 0.000 claims description 43
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000005070 sampling Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 11
- 230000004044 response Effects 0.000 abstract description 32
- 238000011155 quantitative monitoring Methods 0.000 abstract description 5
- 238000002474 experimental method Methods 0.000 description 22
- 238000012544 monitoring process Methods 0.000 description 18
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 16
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 16
- 238000009423 ventilation Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 231100001261 hazardous Toxicity 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 150000001335 aliphatic alkanes Chemical class 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- NNPPMTNAJDCUHE-UHFFFAOYSA-N isobutane Chemical compound CC(C)C NNPPMTNAJDCUHE-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011524 similarity measure Methods 0.000 description 2
- 238000005273 aeration Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000001282 iso-butane Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000011540 sensing material Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0063—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a threshold to release an alarm or displaying means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0067—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display by measuring the rate of variation of the concentration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
- G01N33/0068—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a computer specifically programmed
Landscapes
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The embodiment of the invention provides a gas concentration prediction method, a gas concentration prediction system, a machine-readable storage medium and a processor. The method comprises the following steps: acquiring a first output sequence and a first output change rate sequence of a sensor array in a preparation stage aiming at the change of an output value of target gas along with time to obtain a first sensor dynamic output matrix; acquiring a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time in an actual measurement stage to obtain a second sensor dynamic output matrix; calculating the similarity between the dynamic output matrix of the second sensor and the dynamic output matrix of the first sensor at the moment of the change trend; and determining the gas prediction concentration of the suspected gas type according to the similarity. By using a plurality of groups of output values of the sensor array to be calculated and compared with a plurality of corresponding groups of dynamic response data, the rapid qualitative and quantitative monitoring of the target gas can be realized at the initial stage of the response of the sensor array, and the early warning capability of the target harmful gas is improved.
Description
Technical Field
The invention relates to the technical field of gas detection, in particular to a gas concentration prediction method, a gas concentration prediction system, a machine-readable storage medium and a processor.
Background
In recent years, various safety production accidents such as fire, explosion, poisoning and the like caused by leakage of hazardous gases frequently occur, and serious threat is formed to national and people's life and property safety, so that the rapid capture and early warning of the hazardous gases have important safety significance for industrial sites. After the gas sensor contacts the target gas, the output value can reach a stable state only after the response process, and the output of the gas sensor only represents the concentration of the target gas. Because the response speed of the traditional gas sensor is low, the leakage condition is serious when alarm information is sent out; and for the short-time sudden leakage working condition of the gas, the gas sensor does not respond to the stable state completely, and the gas leaves the surface of the sensor, so that the variation of the output value of the sensor is small, the concentration of the reacted gas is obviously lower than the actual condition and is easy to ignore by safety management staff, and potential safety hazards are buried. If the gas concentration value can be found and predicted at the initial stage of gas leakage, early warning can be performed in time, and accident hazard is obviously reduced.
With the rapid development of material synthesis technology and semiconductor manufacturing process, various novel gas sensors with better performance are sequentially developed, and the sensitivity is as high as 10 -9 The novel gas sensor with high response speed reaching millisecond level provides more possibility for breaking through the bottleneck of the traditional gas detection technology and early warning leakage accidents in advance. However, such gas sensors often have no strong specificity due to the characteristics of the sensing material, and are susceptible to interference by other gases in detection of a specific target gas, thereby affecting the detection result.
In view of the above, developing a method that is highly versatile and that can rapidly and effectively predict gas concentration is a technical problem that needs to be solved in this field.
Disclosure of Invention
The embodiment of the invention aims to provide a gas concentration prediction method, a system, a machine-readable storage medium and a processor, and the method aims to solve the problems of low detection rate and low detection rate of industrial field harmful gas leakage.
In order to achieve the above object, an embodiment of the present invention provides a gas concentration prediction method, including: acquiring a first output sequence and a first output change rate sequence of a sensor array in a preparation stage aiming at the change of an output value of target gas along with time to obtain a first sensor dynamic output matrix; acquiring a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time in an actual measurement stage to obtain a second sensor dynamic output matrix; calculating the similarity between the dynamic output matrix of the second sensor and the dynamic output matrix of the first sensor at the moment of the change trend; and determining the gas prediction concentration of the suspected gas type according to the similarity.
In another aspect, the present application provides a gas concentration prediction system comprising: the first acquisition module is used for acquiring a first output sequence and a first output change rate sequence of the sensor array in the preparation stage aiming at the change of the output value of the target gas along with time to obtain a first sensor dynamic output matrix; the second acquisition module is used for acquiring a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time in an actual measurement stage to obtain a second sensor dynamic output matrix; the similarity calculation module is used for calculating the similarity between the dynamic output matrix of the second sensor and the dynamic output matrix of the first sensor at the moment of change trend; and the concentration prediction module is used for determining the gas prediction concentration of the suspected gas type according to the similarity.
In another aspect, the application provides a machine-readable storage medium having stored thereon instructions for causing a machine to perform any of the above-described gas concentration prediction methods of the application.
In another aspect, the present application provides a processor for running a program, wherein the program, when executed, is configured to perform any one of the above-described gas concentration prediction methods of the present application.
According to the technical scheme, according to the standardized test experiment in the preparation stage, a test data set of response values of the sensor array to different kinds of target gases with different concentrations is obtained; and acquiring the output value and the output value change rate of the sensor array in real time in the actual measurement stage, monitoring the moment when the sensor array starts to respond in real time, comparing the response data in the actual measurement stage with the response data of the sensor array in the test data set in real time at the moment, judging the gas type and the concentration corresponding to the test data set which are similar to the output value in the actual measurement stage according to the similarity, and using the gas type and the concentration as a pre-judging result, comparing the pre-judging result with the pre-warning value, and judging whether to send a concentration pre-warning signal. According to the method, the response difference characteristics of a plurality of groups of sensors are utilized, a plurality of groups of output values of the sensor array are used for calculation and comparison with corresponding plurality of groups of dynamic response data, rapid qualitative and quantitative monitoring of target gas can be realized at the initial stage of response of the sensor array, and whether a concentration early warning signal is sent or not is judged.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain, without limitation, the embodiments of the invention. In the drawings:
FIG. 1 is a flow chart of a method for predicting gas concentration according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for predicting gas concentration according to a second embodiment of the present invention;
FIG. 3 is a flow chart of a method for predicting gas concentration according to a fourth embodiment of the present invention;
fig. 4 is a block diagram of a gas concentration prediction system according to a sixth embodiment of the present invention.
Detailed Description
The following describes the detailed implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
Various gas alarm instruments used in the industrial scene at the present stage are limited by the performance of the sensor, and most of the gas alarm instruments only can realize the function of gas concentration overrun alarm, and the leakage condition is serious when alarm information is sent out due to the slow response speed of the sensor; also, because the response speed is slower, the gas alarm equipment cannot capture sudden and short-time leakage with lower total leakage amount, so that hidden danger of the leakage is easily ignored in enterprise management; on the other hand, new high-sensitivity gas sensors such as MEMS gas sensors have been increasingly used, and such sensors, although having a high response speed, have poor specificity and are susceptible to interference of other gases in detection of a specific target gas, thereby affecting the detection result.
In order to solve the above problems, embodiments of the present invention provide a gas concentration prediction method, a system, a machine-readable storage medium, and a processor, where the method obtains a test data set of response values of a sensor array to different kinds of target gases with different concentrations according to a standardized test experiment in a preparation stage; and acquiring the output value and the output value change rate of the sensor array in real time in the actual measurement stage, monitoring the moment when the sensor array starts to respond in real time, comparing the response data in the actual measurement stage with the response data of the sensor array in the test data set in real time at the moment, judging the gas type and the concentration corresponding to the test data set which are similar to the output value in the actual measurement stage according to the similarity, and using the gas type and the concentration as a pre-judging result, comparing the pre-judging result with the pre-warning value, and judging whether to send a concentration pre-warning signal. According to the method, the response difference characteristics of a plurality of groups of sensors are utilized, a plurality of groups of output values of the sensor array are used for calculation and comparison with corresponding plurality of groups of dynamic response data, rapid qualitative and quantitative monitoring of target gas can be realized at the initial stage of response of the sensor array, and whether a concentration early warning signal is sent or not is judged.
Example 1
An embodiment of the present invention provides a gas concentration prediction method, and fig. 1 is a flowchart of a gas concentration prediction method provided in an embodiment of the present invention, including S101-S104:
s101, a first output sequence and a first output change rate sequence of the sensor array in the preparation stage aiming at the change of the output value of the target gas along with time are obtained, and a first sensor dynamic output matrix is obtained.
The sensor array used in the gas concentration prediction method disclosed by the invention consists of a plurality of broad-spectrum gas sensors, wherein the broad-spectrum sensors are sensors with broad-spectrum sensing performance, and are characterized by responding to most of target gases, but different types of gases with the same concentration have different response degrees, so that the corresponding specific gas sensors are not required to be screened for each target gas, the universality is strong, and the defect that the specificity of a single novel high-sensitivity gas sensor such as an MEMS gas sensor is poor is overcome.
The gas concentration prediction method actually includes two stages of preparation and actual measurement, the data of the preparation stage acquired in S101 is obtained in the preparation stage, and the preparation stage includes steps (1) to (4):
(1) Aiming at application scenes and requirements, determining the types of the harmful gases to be monitored, recording the number of the types as N, selecting proper gas sensors according to the types of the target gases, requiring the gas sensors to respond to the N types of the target gases, and recording the number of the sensors in the sensor array as M, wherein the responses to different types of gases with the same concentration are different.
(2) Constructing a standardized experiment environment, carrying out a harmful gas ventilation test on M gas sensors, selecting different types of target gases with different concentrations to be marked as Cij, wherein i is the target harmful gas type number, i=1, 2,3 … … N, j is the target gas concentration number of the test experiment, L groups of concentrations are taken, j=1, 2,3 … … L are taken, and preferably, periodically acquiring the output values of the sensor array in a preparation stage to obtain a first output sequence of the sensor array with the output values changing along with timeWhere T is the time of the test experiment, t=0, T,2T, … T ij T is the sampling period of the experimental process, tij is the time required to reach steady state from the first time when the sensor starts to respond in the j concentration experiment of the i gas.
(3) For the first output sequence E ij Obtaining a first output change rate sequence by solving the change rate of the sequence (t)Where t=0, T,2T, … (T ij -T)。
(4) Recording a first sensor dynamic output matrixIt can be seen that the first sensor dynamic output matrix G ij (t) is in the first output sequence E ij (t) and the first output change rate sequence F ij (t) a matrix formed as a column vector, the matrix being an M-row 2-column matrix.
Testing the sensor array for multiple target gases and concentrations to construct a test data set including the first sensor dynamic output matrix G ij (t) first sensor dynamic output matrix G in test dataset ij And (t) comparing the gas type and concentration corresponding to the test data set with the sensor output value in the actual measurement stage as the reference of the gas prediction concentration.
S102, acquiring a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time in an actual measurement stage to obtain a second sensor dynamic output matrix.
After the test data set is obtained through the preparation stage, the actual measurement stage can be entered, the actual measurement stage uses the same sensor array as the preparation stage to perform experiments, and the actual measurement stage can comprise the steps (1) to (3):
(1) Danger to sensor arrayIn the harmful gas ventilation test experiment, the output value of the sensor array in the actual measurement stage is preferably periodically collected to obtain a second output sequence of the output value of the sensor array changing along with time
(2) Real time alignment of second output sequence E un (t) deriving a second output rate of change sequence
(3) Recording a dynamic output matrix of the second sensor Visible second sensor dynamic output matrix G un (t) is in the second output sequence E un (t) and the second output rate of change sequence F un (t) a matrix formed as a column vector, which is also an M-row 2-column matrix.
S103, calculating the similarity between the dynamic output matrix of the second sensor and the dynamic output matrix of the first sensor at the moment of the change trend.
Preferably, the change trend time may be: from the sampling start timing, a timing at which a monotonically increasing trend of the continuous plurality of output values in the second output sequence occurs (set to increase with the target gas concentration) or a timing at which a monotonically decreasing trend of the continuous plurality of output values in the second output sequence occurs (set to decrease with the target gas concentration). In this embodiment, the time of change trend is regarded as the time when the gas sensor starts to respond, for example, when E is detected un (t) when the trend is increasing in all the plurality of sampling periods, setting the starting time of the trend to be the time of the trend. By calculating the similarity of the two matrixes at the moment of the change trend, the aim of aiming at the initial stage of the response of the sensor array is realizedThe rapid qualitative and quantitative monitoring of the target gas is realized without waiting for the sensor array in the actual measurement stage to completely respond to a stable state, thereby being beneficial to monitoring and capturing the instantaneous leakage.
The process of calculating the similarity is a process of comparing the second sensor dynamic output matrix obtained in the actual measurement stage with the test data set (first sensor dynamic output matrix) already established in the preliminary stage. The similarity may be a distance measure, such as euclidean distance, the smaller the distance measure, the smaller the measured inter-individual differences; or a similarity measure, such as cosine similarity, the smaller the similarity measure, the larger the measured inter-individual difference.
And S104, determining the gas prediction concentration of the suspected gas according to the similarity.
Generally taking a concentration value corresponding to the minimum difference of the two matrixes as a reference of the gas prediction concentration, and if the calculated distance measurement is the distance measurement, taking the gas concentration of the gas type corresponding to the minimum distance measurement as the gas prediction concentration of the suspected gas type; and if the similarity measurement is calculated, taking the gas concentration of the corresponding gas type when the similarity measurement value is the maximum value as the gas prediction concentration of the suspected gas type.
According to the gas concentration prediction method provided by the embodiment, according to the standardized test experiment in the preparation stage, a test data set of the sensor array aiming at different target gas response values of different concentrations is obtained; collecting the output value and the output value change rate of the sensor array in each sampling period of the actual measurement stage, comparing the output value and the output value change rate with the response data of the sensor array in the test data set in real time, and judging the gas type and concentration corresponding to the test data set which is similar to the output value of the actual measurement stage according to the similarity, wherein the gas type and concentration are used as the pre-judging result of the gas prediction concentration; according to the method, rapid qualitative and quantitative monitoring of the target gas can be realized at the initial stage of the response of the sensor array, the sensor array does not need to wait for complete response to a stable state, burst short-time leakage is facilitated to be rapidly captured, and the early warning capability of the target hazard gas is remarkably improved.
Example two
Fig. 2 is a flowchart of a gas concentration prediction method according to a second embodiment of the present invention. The second embodiment further provides a gas concentration prediction method based on the first embodiment, including S201-S205, where S201 and S202 are the same as S101 and S102 in the first embodiment, and are not described in detail in this embodiment.
S201, a first output sequence and a first output change rate sequence of the sensor array in the preparation stage aiming at the change of the output value of the target gas along with time are obtained, and a first sensor dynamic output matrix is obtained.
S202, a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time are obtained in an actual measurement stage, and a second sensor dynamic output matrix is obtained.
S203, calculating a first Euclidean distance weighted sum of the second sensor dynamic output matrix and the first sensor dynamic output matrix at the moment of change trend, namely G un (t)=[E un (t)F un (t)]And G ij (t)=[E ij (t)F ij (t)]The Euclidean distance weighted sum of the corresponding column vector group has the following calculation formula:
wherein L is un (i, j) is a first Euclidean distance weighted sum, i is a target gas type number, j is a target gas concentration number, M is the number of sensors of the sensor array, z represents each sensor number in the sensor array, θ z Weight coefficient, θ, for Euclidean distance of the z-th sensor z Can be selected according to the absolute value of the output value of the sensor or the reliability degree of the sensor, E z (t) is the second output sequence, E ijz (t) is the first output sequence, F z (t) is the second output rate of change sequence, F ijz (t) is the first output rate of change sequence.
And S204, taking the gas concentration of the gas type corresponding to the minimum value obtained by the weighted sum of the first Euclidean distances as the gas prediction concentration of the suspected gas type.
The smaller the Euclidean distance weighted sum is, the more similar the dynamic output matrix of the second sensor is to the dynamic output matrix of the first sensor, and the more reasonable the gas concentration corresponding to the minimum Euclidean distance weighted is selected as the reference of gas prediction.
Weighted sum of the first Euclidean distances L un (i, j) taking a minimum value L min The corresponding gas species i min And gas concentration j min As the predicted gas concentration of the suspected gas species, i.e., for i min The gas prediction concentration of the gas of the species is j min 。
S205, sending out an early warning signal under the condition that the gas predicted concentration exceeds a corresponding early warning value.
According to i min And j min And judging whether the type and concentration of the predicted hazardous gas at the moment exceeds the enterprise specified early warning value. If the early warning value is exceeded, an early warning signal is sent, and the early warning information is: i.e min The seed gas may be j min Concentration exceeding, please note precautions; if the pre-warning value is not exceeded, the method returns to S203 without pre-warning, judges the change trend time in real time and predicts and calculates the gas concentration at the change trend time.
Based on the first embodiment, the second embodiment uses the euclidean distance weighted sum as a measure standard of the similarity, uses the gas concentration of the gas type corresponding to the minimum value obtained by the first euclidean distance weighted sum as the gas prediction concentration of the suspected gas type, compares the gas prediction concentration with the early warning value, and judges whether to send out a concentration early warning signal; according to the method, the target gas prediction concentration contacted with the sensor can be predicted at the initial stage of the sensor response, the response time of the sensor is theoretically eliminated, the gas early warning response speed is remarkably improved, and the method is beneficial to monitoring and capturing the instantaneous leakage.
Example III
Based on the second embodiment, the third embodiment provides a gas concentration prediction method, which uses hydrogen sulfide gas leakage monitoring at the key flange connection of the petrochemical device pipeline as a monitoring scene to perform a gas concentration prediction experiment, and also includes a preparation stage and an actual measurement stage, wherein the preparation stage includes S301-S304, and the actual measurement stage includes S305-S309:
S301, determining that the monitoring scene is hydrogen sulfide gas leakage monitoring at the key flange connection part of the petrochemical device pipeline, wherein alkane combustible gas leakage can exist at the flange interface. And a GM series MEMS sensor array of Weisheng in Zhengzhou is selected, and four types of GM-402B/502B/602B/702B are used for forming the sensor array to perform online leakage monitoring and early warning. The monitored hazardous gas type n=1, the sensor array number m=4, the sensor numbers correspond to 1 to 4, and the sampling period of the sensor array is 0.5s.
S302, constructing a standardized experimental environment, and carrying out a harmful gas ventilation test experiment on 4 sensors. For the possible leakage gas components, air-based methane and hydrogen sulfide single gas is configured, the aeration flow is 500ml/min, and the concentration C of each component is ij The configuration is shown in table 1, wherein i is the target hazard gas type number, i=1, 2, j is the target gas concentration number of the preliminary stage test experiment, and j=1, 2,3.
TABLE 1 experiment gas mixture concentration
Performing ventilation test on the sensor array, wherein the ventilation time is 10s, the sampling period T=0.5 s, the total test duration is 100s, and recording a first output sequence of the output value of the sensor array changing along with time
S303, for the first output sequence E ij (t) deriving a rate of change to obtain a first output rate of change sequenceWhere t= 0,0.5,1, … 99.5.5.
S304, recording a dynamic output matrix of the first sensorThe matrix is a 4 row and 2 column matrix, representing the output value sequence and the output value change rate sequence of the 4 sensors for the gas.
The sensor array is tested for multiple target gases and concentrations to construct a test dataset.
S305, using a sensor array, introducing unknown gas with unknown type and concentration to be detected at a flow rate of 500ml/min, and recording a second output sequence of the output value of the sensor array changing with time in real time
S306, real-time outputting the second output sequence E un (t) deriving a second output rate of change sequence
S307, judging E in real time un Trend of change in (t), if E un (t) in the increasing trend (the output value of the sensor matrix is set to be increased along with the increase of the concentration of the target gas) in three sampling periods, and G corresponding to the starting moment of the increasing trend is calculated un (t)=[E un (t) F un (t)]And G ij (t)=[E ij (t) F ij (t)]Euclidean distance weighted sum of corresponding column vector groups in (a)
S308, calculating to obtain L un (i, j) taking a minimum value L min Corresponding i when= 25.53 min =1 and j min =2, indicating that the gas predicted concentration for the hydrogen sulfide gas is 5ppm.
S309, judging the magnitude relation between the predicted concentration of the hydrogen sulfide gas and the hydrogen sulfide early warning value 7ppm specified by the enterprise, and returning to S307 without sending out early warning information when the predicted concentration of the hydrogen sulfide gas does not exceed the early warning value.
In the third embodiment, the hydrogen sulfide gas leakage monitoring at the key flange joint of the petrochemical device pipeline is used as a monitoring scene to carry out a gas concentration prediction experiment, so that the target gas prediction concentration contacted with the sensor can be predicted at the initial stage of the sensor response, and the gas early warning response speed is obviously accelerated.
Example IV
Fig. 3 is a flowchart of a gas concentration prediction method according to a fourth embodiment of the present invention. The fourth embodiment provides an approximate prediction method for gas concentration based on the second embodiment, including S401-S407, where S401, S402, S403 are the same as S201, S202, S203 in the second embodiment, and are not described in detail in this embodiment.
S401, a first output sequence and a first output change rate sequence of the sensor array in the preparation stage aiming at the change of the output value of the target gas along with time are obtained, and a first sensor dynamic output matrix is obtained.
S402, acquiring a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time in an actual measurement stage, and obtaining a second sensor dynamic output matrix.
S403, calculating a first Euclidean distance weighted sum of the second sensor dynamic output matrix and the first sensor dynamic output matrix at the moment of change trend.
S404, judging the weighted sum L of the first Euclidean distance un Minimum value L of (i, j) min Whether the accuracy threshold delta is exceeded.
The accuracy threshold delta is a judgment standard of whether to perform approximate prediction, if L min If delta is not exceeded, then approximate prediction is not necessary, if L min Beyond delta, an approximate prediction is performed.
And S405, when the minimum value of the first Euclidean distance weighted sum does not exceed an accuracy threshold, taking the gas concentration of the gas type corresponding to the minimum value obtained by the first Euclidean distance weighted sum as the gas prediction concentration of the suspected gas type.
And S406, performing approximate prediction of the gas concentration when the minimum value of the weighted sum of the first Euclidean distances exceeds an accuracy threshold.
Due to the first sensor dynamic output matrix G ij The acquisition of (t) requires the development of experiments under corresponding conditions, and the more the number of experiments in the preparation stage is, the finer the concentration gradient is, and the more accurate the early warning concentration is. Whereas for the case where the minimum value of the first euclidean distance weighted sum is not small enough and the test data set is small, the target gas concentration can be predicted by approximate calculation. The approximation calculation steps are as follows:
taking a minimum value L by the weighted sum of the first Euclidean distances min The corresponding gas species i min Performing approximate calculation, including the steps (1) - (2):
step (1), calculating the exclusive first Euclidean distance weighted sum to obtain a minimum value L min The corresponding gas species i min Is a first sensor dynamic output matrix of (a)And the second sensor dynamic output matrix G un (t)=[E un (t) F un (t)]A second euclidean distance weighted sum of (c).
Step (2), taking the weighted sum of the second Euclidean distances as a next-smallest value L smin I corresponding to time min Gas concentration j of gas species smin The gas prediction concentration is approximately calculated by the following calculation formula:
wherein C is un For the gas to be predicted a concentration of the gas,the gas concentration of the corresponding gas species when taking the minimum value for the first Euclidean distance weighted sum, the +.>Is the firstThe weighted sum of the two Euclidean distances is used for taking the gas concentration of the corresponding gas type when the next small value is taken, wherein,
wherein M is the number of sensors in the sensor array, z is the number of each sensor in the sensor array, E z (t) is said second output sequence,for the output sequence corresponding to the gas type and gas concentration, which is exclusive of the first Euclidean distance weighted sum and takes the minimum value, F z (t) is said second output rate of change sequence,>for the->Determining the sequence of the change rate, < > >For exclusive use of the output sequence corresponding to the gas type and gas concentration when the second Euclidean distance weighted sum takes the next small value in the first output sequence, +.>For the->The sequence obtained from the rate of change was obtained.
S407, sending out an early warning signal under the condition that the gas predicted concentration exceeds a corresponding early warning value.
According to i min And C un And judging whether the type and concentration of the predicted hazardous gas at the moment exceeds the enterprise specified early warning value. If the early warning value is exceeded, send outThe early warning signal, early warning information is: i.e min The seed gas may have C un Concentration exceeding, please note precautions; if the early warning value is not exceeded, the early warning is not needed; returning to S403, the change trend time is determined in real time, and the gas concentration is predicted and calculated at the change trend time.
In the fourth embodiment, based on the second embodiment, the accuracy threshold δ is used as a criterion for judging whether to perform approximate prediction, if the minimum value of the first euclidean distance weighted sum does not exceed the accuracy threshold, the approximate prediction is not needed, and if the minimum value of the first euclidean distance weighted sum exceeds the accuracy threshold, the approximate prediction is performed, so that the defect that the predicted concentration is not accurate enough due to less test data sets acquired in the preparation stage is overcome, and the accuracy of the gas predicted concentration is improved.
Example five
Based on the fourth embodiment, the fifth embodiment provides a gas concentration prediction method, and the gas concentration prediction experiment is performed by using hydrogen sulfide gas leakage monitoring at the key flange joint of the petrochemical device pipeline as a monitoring scene, where the gas concentration prediction experiment includes a preparation stage and an actual measurement stage, the preparation stage is S501-S504, and the actual measurement stage is S505-S509:
s501, determining that the monitoring scene is hydrogen sulfide gas leakage monitoring at the key flange joint of the petrochemical device pipeline, and possibly also having alkane combustible gas leakage at the flange interface. And a GM series MEMS sensor array of Weisheng in Zhengzhou is selected, and four types of GM-402B/502B/602B/702B are used for forming the sensor array to perform online leakage monitoring and early warning. The monitored hazardous gas species n=1, the sensor array number m=4, and the sensor numbers correspond to 1 to 4.
S502, constructing a standardized experimental environment, and carrying out a harmful gas ventilation test experiment on 4 sensors. For the possible leakage gas components, air-based methane, isobutane and hydrogen sulfide single gas is configured, the ventilation flow rate is 500ml/min, and the concentration C of each component is ij The configuration is shown in table 2, wherein i is the target hazard gas type number, i=1, 2,3, j is the target gas concentration number of the test experiment, and j=1, 2,3 is taken.
TABLE 2 experiment of the concentration of the mixed gas
Performing ventilation test on the sensor array, wherein the ventilation time is 10s, the sampling period T=0.5 s, the total test duration is 100s, and recording a first output sequence of the output value of the sensor array changing along with time
S503, for the first output sequence E ij (t) deriving a rate of change to obtain a first output rate of change sequenceWhere t= 0,0.5,1, … 99.5.5.
S504, recording the dynamic output matrix of the first sensorThe matrix is a 4 row and 2 column matrix, representing the output value sequence and the output value change rate sequence of the 4 sensors for the gas.
The sensor array is tested for multiple target gases and concentrations to construct a test dataset.
S505, using a sensor array, introducing unknown gas with unknown type and concentration at a flow rate of 500ml/min, and recording a second output sequence of the sensor array output value changing with time in real time
S506, real-time outputting the second output sequence E un (t) deriving a second output rate of change sequence
S507,Real-time judgment E un Trend of change in (t), if E un (t) in the increasing trend (the target gas is set to increase the output value of the sensor matrix) in three sampling periods, and calculating G corresponding to the starting moment of the increasing trend un (t)=[E un (t) F un (t)]And G ij (t)=[E ij (t) F ij (t)]Euclidean distance weighted sum of corresponding column vector groups in (a)
S508, calculating to obtain L un (i, j) taking a minimum value L min Corresponding i when= 79.91 min =1 and j min =2, indicating that the gas predicted concentration for the hydrogen sulfide gas is 10ppm.
S509, judging the weighted sum L of the first Euclidean distances un Minimum value L of (i, j) min Whether the accuracy threshold δ=50 is exceeded, compared L min >Delta, performing approximate prediction of gas concentration.
S510, calculating the specific gas type i min First sensor dynamic output matrix g=1 1j (t)=[E 1j (t) F 1j (t)]And the second sensor dynamic output matrix G un (t)=[E un (t) F un (t)]A second euclidean distance weighted sum of (c).
S511, taking the weighted sum of the second Euclidean distances as the next smallest value L smin Corresponding i when=103.5 min Gas concentration j of =1 gas species smin =3 was used to approximate the gas prediction concentration, calculated using the following formula:
C un =P|C 12 -C 13 |+C 12
wherein the method comprises the steps ofThen there is a predicted concentration of gas C un =P|C 12 -C 13 |+C 12 =0.62*|10-15|+10=13.1ppm。
S512, the gas to be detected is hydrogen sulfide, the predicted concentration of the gas is about 13.1ppm, the predicted concentration exceeds the hydrogen sulfide early warning value of 7ppm specified by enterprises, an early warning signal is sent at the moment, and the early warning information is as follows: hydrogen sulfide gas may be present at a concentration of 13.1ppm exceeding the standard, taking care of precautions. Return to S507.
In the fifth embodiment, the hydrogen sulfide gas leakage monitoring at the key flange joint of the petrochemical device pipeline is used as a monitoring scene to carry out a gas concentration prediction experiment, and the defect that the predicted concentration is not accurate enough due to less test data sets obtained in the preparation stage is overcome by carrying out approximate prediction on the gas predicted concentration, so that the accuracy of the gas predicted concentration is improved.
Example six
Fig. 4 is a block diagram of a gas concentration prediction system according to a sixth embodiment of the present invention. Based on the above disclosed gas concentration prediction method, a sixth embodiment provides a gas concentration prediction system, including:
a first obtaining module 601, configured to obtain a first output sequence and a first output change rate sequence of the output value of the sensor array in the preparation stage for the target gas over time, so as to obtain a first sensor dynamic output matrix;
the second obtaining module 602 is configured to obtain, in an actual measurement stage, a second output sequence and a second output change rate sequence of the sensor array for a change over time of an output value of the gas to be measured, so as to obtain a second sensor dynamic output matrix;
a similarity calculating module 603, configured to calculate a similarity between the second sensor dynamic output matrix and the first sensor dynamic output matrix at a time of a trend of change;
the concentration prediction module 604 is configured to determine a gas predicted concentration of the suspected gas according to the magnitude of the similarity.
In some optional implementations of this embodiment, the first output sequence includes a sequence obtained by periodically acquiring output values of the sensor array in a preparation phase;
The first output change rate sequence is a sequence obtained by calculating a change rate of the first output sequence;
the second output sequence comprises a sequence obtained by periodically collecting output values of the sensor array in an actual measurement stage;
the second output change rate sequence is a sequence obtained by calculating a change rate of the second output sequence;
the first sensor dynamic output matrix comprises a matrix formed by taking the first output sequence and the first output change rate sequence as column vectors;
the second sensor dynamic output matrix comprises a matrix formed by taking the second output sequence and the second output change rate sequence as column vectors;
the change trend time includes: and starting from the sampling starting time, the continuous multiple output values in the second output sequence have the time of monotonically increasing trend.
In some optional implementations of this embodiment, the similarity of the second sensor dynamic output matrix to the first sensor dynamic output matrix includes:
the first Euclidean distance weighted sum of the second sensor dynamic output matrix and the first sensor dynamic output matrix has the following calculation formula:
Wherein L is un (i, j) is a first Euclidean distance weighted sum, i is a target gas type number, j is a target gas concentration number, M is the number of sensors of the sensor array, z represents each sensor number in the sensor array, θ z Weight coefficient for Euclidean distance of each sensor, E z (t) is the second output sequence, E ijz (t) is the first output sequence, F z (t) is the second output rate of change sequence, F ijz (t) is the first output rate of change sequence.
In some optional implementations of this embodiment, the concentration prediction module 604 is specifically configured to:
and taking the gas concentration of the gas type corresponding to the minimum value obtained by the weighted sum of the first Euclidean distances as the gas prediction concentration of the suspected gas type.
In some embodiments of the invention, the concentration prediction module is specifically configured to:
judging whether the minimum value of the first Euclidean distance weighted sum exceeds an accuracy threshold value;
when the minimum value of the first euclidean distance weighted sum exceeds the accuracy threshold, performing approximate calculation on the gas type corresponding to the minimum value obtained by the first euclidean distance weighted sum, wherein the method comprises the following steps:
Calculating a second Euclidean distance weighted sum of a first sensor dynamic output matrix and a second sensor dynamic output matrix, which are exclusive to the first Euclidean distance weighted sum and correspond to the gas type when the minimum value is obtained;
taking the gas concentration of the gas species corresponding to the second Euclidean distance weighted sum as the next-smallest value for approximately calculating the gas predicted concentration, wherein the calculation formula is as follows:
wherein C is un For the gas to be predicted a concentration of the gas,the gas concentration of the corresponding gas species when taking the minimum value for the first Euclidean distance weighted sum, the +.>And weighting and taking the gas concentration of the corresponding gas type when the second Euclidean distance is small, wherein,
wherein M is the number of sensors in the sensor array, z is the number of each sensor in the sensor array, E z (t) is the second output sequenceThe number of columns in a row,for the output sequence corresponding to the gas type and gas concentration, which is exclusive of the first Euclidean distance weighted sum and takes the minimum value, F z (t) is said second output rate of change sequence,>for the->Determining the sequence of the change rate, < >>For exclusive use of the output sequence corresponding to the gas type and gas concentration when the second Euclidean distance weighted sum takes the next small value in the first output sequence, +. >For the->The sequence obtained from the rate of change was obtained.
In some optional implementations of this embodiment, the concentration prediction module 604 is further configured to: and when the minimum value of the first Euclidean distance weighted sum does not exceed the accuracy threshold value, taking the gas concentration of the gas type corresponding to the minimum value obtained by the first Euclidean distance weighted sum as the gas prediction concentration of the suspected gas type.
In some optional implementations of this embodiment, the gas concentration prediction system further comprises:
and the early warning module is configured to send out an early warning signal under the condition that the gas predicted concentration exceeds a corresponding early warning value.
The specific working principle and benefits of the gas concentration prediction system provided by the embodiment of the present invention are the same as those of the gas concentration prediction method provided by the embodiment of the present invention, and will not be described here again.
Embodiments of the present invention provide a machine-readable storage medium having stored thereon instructions for causing a machine to perform implementing the gas concentration prediction method.
The embodiment of the invention provides a processor which is used for running a program, wherein the program runs to execute the gas concentration prediction method.
The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the gas concentration prediction method. The device herein may be a server, PC, PAD, cell phone, etc.
The application also provides a computer program product adapted to perform, when executed on a data processing apparatus, initializing the gas concentration prediction method.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (14)
1. A gas concentration prediction method, comprising:
acquiring a first output sequence and a first output change rate sequence of a sensor array in a preparation stage aiming at the change of an output value of target gas along with time to obtain a first sensor dynamic output matrix, wherein the sensor array is subjected to testing of multiple target gases and concentrations to construct a test data set, and the test data set comprises the first sensor dynamic output matrix;
acquiring a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time in an actual measurement stage to obtain a second sensor dynamic output matrix;
calculating the similarity between the dynamic output matrix of the second sensor and the dynamic output matrix of the first sensor at the moment of the change trend;
determining the gas prediction concentration of the suspected gas type according to the similarity, wherein the gas concentration of the corresponding gas type in the preliminary stage test data set when the difference between the two dynamic output matrixes is the minimum is taken as the gas prediction concentration of the suspected gas type in the actual measurement stage;
The first output sequence comprises a sequence obtained by periodically collecting output values of the sensor array in a preparation stage;
the first output change rate sequence is a sequence obtained by calculating a change rate of the first output sequence;
the second output sequence comprises a sequence obtained by periodically collecting output values of the sensor array in an actual measurement stage;
the second output change rate sequence is a sequence obtained by calculating a change rate of the second output sequence;
the first sensor dynamic output matrix comprises a matrix formed by taking the first output sequence and the first output change rate sequence as column vectors;
the second sensor dynamic output matrix comprises a matrix formed by taking the second output sequence and the second output change rate sequence as column vectors;
the change trend time includes: and starting from the sampling starting time, the continuous multiple output values in the second output sequence have the time of monotonically increasing trend.
2. The method of claim 1, wherein the similarity of the second sensor dynamic output matrix to the first sensor dynamic output matrix comprises:
The first Euclidean distance weighted sum of the second sensor dynamic output matrix and the first sensor dynamic output matrix has the following calculation formula:
wherein L is un (i, j) is a first Euclidean distance weighted sum, i is a target gas type number, j is a target gas concentration number, M is the number of sensors of the sensor array, z represents each sensor number in the sensor array, θ z Weight coefficient for Euclidean distance of each sensor, E z (t) is the second output sequence, E ijz (t) is the first output sequence, F z (t) is the second output rate of change sequence, F ijz (t) is the first output rate of change sequence.
3. The gas concentration prediction method according to claim 2, wherein the determining the gas prediction concentration of the suspected gas species according to the magnitude of the similarity includes:
and taking the gas concentration of the gas type corresponding to the minimum value obtained by the weighted sum of the first Euclidean distances as the gas prediction concentration of the suspected gas type.
4. The gas concentration prediction method according to claim 2, wherein the determining the gas prediction concentration of the suspected gas species according to the magnitude of the similarity includes:
Judging whether the minimum value of the first Euclidean distance weighted sum exceeds an accuracy threshold value;
when the minimum value of the first euclidean distance weighted sum exceeds the accuracy threshold, performing approximate calculation on the gas type corresponding to the minimum value obtained by the first euclidean distance weighted sum, wherein the method comprises the following steps:
calculating a second Euclidean distance weighted sum of a first sensor dynamic output matrix and a second sensor dynamic output matrix, which are exclusive to the first Euclidean distance weighted sum and correspond to the gas type when the minimum value is obtained;
taking the gas concentration of the gas species corresponding to the second Euclidean distance weighted sum as the next-smallest value for approximately calculating the gas predicted concentration, wherein the calculation formula is as follows:
wherein C is un For the gas to be predicted a concentration of the gas,the gas concentration of the corresponding gas species when taking the minimum value for the first Euclidean distance weighted sum, the +.>And weighting and taking the gas concentration of the corresponding gas type when the second Euclidean distance is small, wherein,
wherein M is the number of sensors in the sensor array, z is the number of each sensor in the sensor array, E z (t) is said second output sequence,for the output sequence corresponding to the gas type and gas concentration, which is exclusive of the first Euclidean distance weighted sum and takes the minimum value, F z (t) is said second output rate of change sequence,>for the->Determining the sequence of the change rate, < >>Weighting and taking the next small value for the exclusive second Euclidean distance in the first output sequenceOutput sequence corresponding to degree,/>For the->The sequence obtained from the rate of change was obtained.
5. The gas concentration prediction method according to claim 4, wherein when the minimum value of the first euclidean distance weighted sum does not exceed the accuracy threshold value, the gas concentration of the gas type corresponding to the time when the first euclidean distance weighted sum obtained the minimum value is used as the gas prediction concentration of the suspected gas type.
6. The gas concentration prediction method according to claim 1, wherein after the step of determining the gas concentration of the suspected gas species according to the magnitude of the similarity is performed, further comprising:
and sending out an early warning signal under the condition that the gas predicted concentration exceeds the corresponding early warning value.
7. A gas concentration prediction system, comprising:
the system comprises a first acquisition module, a second acquisition module and a first control module, wherein the first acquisition module is used for acquiring a first output sequence and a first output change rate sequence of a sensor array in a preparation stage aiming at the change of an output value of target gas along with time to obtain a first sensor dynamic output matrix, wherein the sensor array is subjected to testing of multiple target gases and concentrations to construct a test data set, and the test data set comprises the first sensor dynamic output matrix;
The second acquisition module is used for acquiring a second output sequence and a second output change rate sequence of the sensor array aiming at the change of the output value of the gas to be detected along with time in an actual measurement stage to obtain a second sensor dynamic output matrix;
the similarity calculation module is used for calculating the similarity between the dynamic output matrix of the second sensor and the dynamic output matrix of the first sensor at the moment of change trend;
the concentration prediction module is used for determining the gas prediction concentration of the suspected gas type according to the similarity, wherein the gas concentration of the suspected gas type in the actual measurement stage is taken as the gas prediction concentration of the suspected gas type in the preliminary stage test data set when the difference of the two dynamic output matrixes is the minimum;
the first output sequence comprises a sequence obtained by periodically collecting output values of the sensor array in a preparation stage;
the first output change rate sequence is a sequence obtained by calculating a change rate of the first output sequence;
the second output sequence comprises a sequence obtained by periodically collecting output values of the sensor array in an actual measurement stage;
the second output change rate sequence is a sequence obtained by calculating a change rate of the second output sequence;
The first sensor dynamic output matrix comprises a matrix formed by taking the first output sequence and the first output change rate sequence as column vectors;
the second sensor dynamic output matrix comprises a matrix formed by taking the second output sequence and the second output change rate sequence as column vectors;
the change trend time includes: and starting from the sampling starting time, the continuous multiple output values in the second output sequence have the time of monotonically increasing trend.
8. The gas concentration prediction system of claim 7, wherein the similarity of the second sensor dynamic output matrix to the first sensor dynamic output matrix comprises:
the first Euclidean distance weighted sum of the second sensor dynamic output matrix and the first sensor dynamic output matrix has the following calculation formula:
wherein L is un (i, j) is a first Euclidean distance weighted sum, i is a target gas type number, j is a target gas concentration number, M is the number of sensors of the sensor array, z represents each sensor number in the sensor array, θ z Weight coefficient for Euclidean distance of each sensor, E z (t) is the second output sequence, E ijz (t) is the first output sequence, F z (t) is the second output rate of change sequence, F ijz (t) is the first output rate of change sequence.
9. The gas concentration prediction system of claim 8, wherein the concentration prediction module is specifically configured to:
and taking the gas concentration of the gas type corresponding to the minimum value obtained by the weighted sum of the first Euclidean distances as the gas prediction concentration of the suspected gas type.
10. The gas concentration prediction system of claim 8, wherein the concentration prediction module is specifically configured to:
judging whether the minimum value of the first Euclidean distance weighted sum exceeds an accuracy threshold value;
when the minimum value of the first euclidean distance weighted sum exceeds the accuracy threshold, performing approximate calculation on the gas type corresponding to the minimum value obtained by the first euclidean distance weighted sum, wherein the method comprises the following steps:
calculating a second Euclidean distance weighted sum of a first sensor dynamic output matrix and a second sensor dynamic output matrix, which are exclusive to the first Euclidean distance weighted sum and correspond to the gas type when the minimum value is obtained;
taking the gas concentration of the gas species corresponding to the second Euclidean distance weighted sum as the next-smallest value for approximately calculating the gas predicted concentration, wherein the calculation formula is as follows:
Wherein C is un For the gas to be predicted a concentration of the gas,the gas concentration of the corresponding gas species when taking the minimum value for the first Euclidean distance weighted sum, the +.>And weighting and taking the gas concentration of the corresponding gas type when the second Euclidean distance is small, wherein,
wherein M is the number of sensors in the sensor array, z is the number of each sensor in the sensor array, E z (t) is said second output sequence,for the output sequence corresponding to the gas type and gas concentration, which is exclusive of the first Euclidean distance weighted sum and takes the minimum value, F z (t) is said second output rate of change sequence,>for the->Determining the sequence of the change rate, < >>Weighting and taking the next small value for the exclusive second Euclidean distance in the first output sequenceOutput sequence corresponding to body concentration,/->For the->The sequence obtained from the rate of change was obtained.
11. The gas concentration prediction system of claim 10, wherein the concentration prediction module is further configured to: and when the minimum value of the first Euclidean distance weighted sum does not exceed the accuracy threshold value, taking the gas concentration of the gas type corresponding to the minimum value obtained by the first Euclidean distance weighted sum as the gas prediction concentration of the suspected gas type.
12. The gas concentration prediction system according to claim 7, further comprising:
and the early warning module is configured to send out an early warning signal under the condition that the gas predicted concentration exceeds a corresponding early warning value.
13. A machine-readable storage medium having instructions stored thereon for causing a machine to perform the gas concentration prediction method according to any one of claims 1-6.
14. A processor, characterized by being configured to run a program, wherein the program is configured to perform the gas concentration prediction method according to any one of claims 1-6 when run.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011530289.XA CN114660231B (en) | 2020-12-22 | 2020-12-22 | Gas concentration prediction method, system, machine-readable storage medium and processor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011530289.XA CN114660231B (en) | 2020-12-22 | 2020-12-22 | Gas concentration prediction method, system, machine-readable storage medium and processor |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114660231A CN114660231A (en) | 2022-06-24 |
CN114660231B true CN114660231B (en) | 2023-11-24 |
Family
ID=82024891
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011530289.XA Active CN114660231B (en) | 2020-12-22 | 2020-12-22 | Gas concentration prediction method, system, machine-readable storage medium and processor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114660231B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105938116A (en) * | 2016-06-20 | 2016-09-14 | 吉林大学 | Gas sensor array concentration detection method based on fuzzy division and model integration |
CN109632891A (en) * | 2018-12-19 | 2019-04-16 | 江苏智闻智能传感科技有限公司 | A method of utilizing array gas sensor monitors gaseous species and concentration |
CN110175195A (en) * | 2019-04-23 | 2019-08-27 | 哈尔滨工业大学 | Mixed gas detection model construction method based on extreme random tree |
CN111126575A (en) * | 2020-01-09 | 2020-05-08 | 同济大学 | Gas sensor array mixed gas detection method and device based on machine learning |
CN111596006A (en) * | 2020-04-29 | 2020-08-28 | 北京雪迪龙科技股份有限公司 | Calibration method of atmosphere online monitor and monitor |
CN112098600A (en) * | 2020-09-14 | 2020-12-18 | 哈尔滨工业大学 | Fault detection and diagnosis method for chemical sensor array |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6338266B1 (en) * | 2000-04-05 | 2002-01-15 | Industrial Scientific Corporation | Method of identifying a gas and associated apparatus |
EP3736564A1 (en) * | 2019-05-09 | 2020-11-11 | Infineon Technologies AG | Gas sensing device and method for operating a gas sensing device |
-
2020
- 2020-12-22 CN CN202011530289.XA patent/CN114660231B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105938116A (en) * | 2016-06-20 | 2016-09-14 | 吉林大学 | Gas sensor array concentration detection method based on fuzzy division and model integration |
CN109632891A (en) * | 2018-12-19 | 2019-04-16 | 江苏智闻智能传感科技有限公司 | A method of utilizing array gas sensor monitors gaseous species and concentration |
CN110175195A (en) * | 2019-04-23 | 2019-08-27 | 哈尔滨工业大学 | Mixed gas detection model construction method based on extreme random tree |
CN111126575A (en) * | 2020-01-09 | 2020-05-08 | 同济大学 | Gas sensor array mixed gas detection method and device based on machine learning |
CN111596006A (en) * | 2020-04-29 | 2020-08-28 | 北京雪迪龙科技股份有限公司 | Calibration method of atmosphere online monitor and monitor |
CN112098600A (en) * | 2020-09-14 | 2020-12-18 | 哈尔滨工业大学 | Fault detection and diagnosis method for chemical sensor array |
Also Published As
Publication number | Publication date |
---|---|
CN114660231A (en) | 2022-06-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110134611B (en) | Memory leak analysis method, device, terminal and storage medium | |
CN110780347B (en) | Earthquake destructive power prediction device and method based on cyclic neural network | |
CN111080976B (en) | Method and device for monitoring natural gas leakage in real time under temperature change scene | |
US9807561B2 (en) | User settlement detection | |
CN114492629A (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium | |
CN114660231B (en) | Gas concentration prediction method, system, machine-readable storage medium and processor | |
CN109444060B (en) | Solution concentration detection method, device, equipment and storage medium | |
CN108152458A (en) | Gas detection method and device | |
CN113358582B (en) | Method, equipment and medium for detecting concrete structure defects | |
CN117220772A (en) | Method, device, equipment and storage medium for positioning optical cable fault point | |
CN113532384B (en) | Underground pipe network linear displacement settlement monitoring method based on wireless sensor technology and cloud monitoring platform | |
CN110765005A (en) | Software reliability evaluation method and device | |
JP3174188B2 (en) | Gas identification device | |
CN109642827A (en) | Temperature Estimation System, temperature projectional technique and record have the record media of temperature estimation program | |
CN114720165A (en) | Optical fiber hydrophone packaging detection method, device, system and computer equipment | |
CN109444061B (en) | Allergen solution concentration detection method, device, equipment and storage medium | |
CN113610344A (en) | Pollution early warning method and device, electronic equipment and storage medium | |
Conrad et al. | A hierarchical strategy for under-ground early fire detection based on a T-cycled semiconductor gas sensor | |
CN115420418B (en) | Air pressure measuring method and device, electronic equipment and readable storage medium | |
CN114783550B (en) | Artificial intelligence-based new material online evaluation method and system | |
CN117033983B (en) | Unmanned ship self-noise detection and identification method and system | |
CN116878728B (en) | Pressure sensor fault detection analysis processing system | |
CN116290150B (en) | On-line detection method and system for foundation of building engineering | |
CN117421551A (en) | Sensor detection method, device, computer equipment and storage medium | |
CN116307376A (en) | Method and device for obtaining carbon content of coal unit heat value |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20231027 Address after: 100728 No. 22 North Main Street, Chaoyang District, Beijing, Chaoyangmen Applicant after: CHINA PETROLEUM & CHEMICAL Corp. Applicant after: Sinopec Safety Engineering Research Institute Co.,Ltd. Address before: 100728 No. 22 North Main Street, Chaoyang District, Beijing, Chaoyangmen Applicant before: CHINA PETROLEUM & CHEMICAL Corp. Applicant before: SINOPEC Research Institute OF SAFETY ENGINEERING |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |