Gas intelligent monitoring method and system

Abstract

The application discloses a kind of gas intelligent monitoring method and system, it is related to gas monitoring technical field.The method includes: by gas flow sensor, monitoring obtains the gas flow sequence of gas pipeline, and by gas concentration sensor, monitoring obtains the gas concentration of monitoring position, wherein, monitoring position is in target space;Air flow characteristic distribution in target space is obtained, according to the air flow characteristic distribution, compensate the gas concentration, obtain compensation gas concentration;The gas flow sequence and compensation gas concentration are verified to gas anomaly, obtain gas anomaly rate, according to the air flow characteristic distribution, carry out gas anomaly influence analysis and correction, obtain correction gas anomaly rate;According to the correction gas anomaly rate, carry out gas anomaly early warning discrimination, obtain gas monitoring result.The application effectively improves the accuracy of gas anomaly identification, improves the intelligentization and reliability of gas monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gas monitoring, in particular to a gas intelligent monitoring method and system. BACKGROUND

[0002] Gas leakage is a common safety hazard in home and industrial environments. If leakage occurs and is not handled in time, it may cause serious accidents such as fire, explosion or poisoning. Existing gas monitoring technologies usually use gas concentration sensors for concentration detection or use gas flow sensors to detect pipeline flow.

[0003] Using traditional methods, using a single sensor for monitoring often has data deviation. Air flow will affect the distribution of gas concentration, making the gas concentration monitoring data inaccurate, thereby causing false positives or false negatives. SUMMARY

[0004] The present application provides a gas intelligent monitoring method and system, aiming to solve the technical problems of false positives and false negatives in existing gas monitoring technologies.

[0005] In view of the above problems, the present application provides a gas intelligent monitoring method and system.

[0006] In a first aspect, the present application provides a gas intelligent monitoring method, comprising:

[0007] acquiring a gas flow sequence of a gas pipeline through a gas flow sensor, and acquiring a gas concentration at a monitoring position through a gas concentration sensor, wherein the monitoring position is in a target space;

[0008] obtaining an air flow feature distribution in the target space, compensating the gas concentration according to the air flow feature distribution, and obtaining a compensated gas concentration;

[0009] verifying gas anomalies based on the gas flow sequence and the compensated gas concentration, obtaining a gas anomaly rate, analyzing and correcting gas anomaly influences based on the air flow feature distribution, and obtaining a corrected gas anomaly rate;

[0010] discriminating gas anomaly early warning based on the corrected gas anomaly rate, and obtaining a gas monitoring result.

[0011] In a second aspect, the present application provides a gas intelligent monitoring system, comprising:

[0012] a gas concentration monitoring module, configured to acquire a gas flow sequence of a gas pipeline through a gas flow sensor, and acquire a gas concentration at a monitoring position through a gas concentration sensor, wherein the monitoring position is in a target space;

[0013] The gas concentration compensation module is configured to obtain an air flow characteristic distribution in a target space, compensate the gas concentration according to the air flow characteristic distribution, and obtain a compensated gas concentration;

[0014] The gas anomaly verification module is configured to perform gas anomaly verification on the gas flow sequence and the compensated gas concentration, obtain a gas anomaly rate, perform gas anomaly influence analysis and correction according to the air flow characteristic distribution, and obtain a corrected gas anomaly rate.

[0015] The gas anomaly early warning module is configured to perform gas anomaly early warning discrimination according to the corrected gas anomaly rate, and obtain a gas monitoring result.

[0016] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0017] The present application provides a gas intelligent monitoring method and system, which compensates the gas concentration according to the air flow characteristic distribution, can effectively reduce the interference of environmental factors such as ventilation and convection on the sensor monitoring result, makes the detected gas concentration more accurate, uses the gas flow and gas concentration double parameters for verification, no longer relies on single sensor data, avoids false positives and false negatives caused by single signal fluctuation, improves the reliability of gas anomaly identification, introduces the abnormal influence analysis under the air flow, calculates the gas anomaly influence coefficient, corrects the gas anomaly rate, and further improves the accuracy of early warning, and has strong universality and can be applied to central kitchen, commercial restaurant, industrial workshop and other air circulation complex environments. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 A flowchart of a gas intelligent monitoring method provided by an embodiment of the present application is shown in the figure.

[0020] Figure 2 A structure diagram of a gas intelligent monitoring system provided by an embodiment of the present application is shown in the figure.

[0021] In the drawings, the components represented by the numbers are described as follows:

[0022] The gas concentration monitoring module 11, the gas concentration compensation module 12, the gas anomaly verification module 13, and the gas anomaly early warning module 14. DETAILED DESCRIPTION

[0023] The application provides a gas intelligent monitoring method and system, which are used for solving the technical problems of false positives and false negatives in the existing gas monitoring technology.

[0024] The technical solutions in the embodiments of the application will be clearly and completely described in connection with the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0025] It should be noted that the terms "comprising" and "having" are intended to cover the inclusions that are not exclusive, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to the clearly listed steps or units, but can include other steps or modules that are not clearly listed or inherent to the process, method, product or device.

[0026] Embodiment one, as shown in the application provides a gas intelligent monitoring method, the method comprises: Figure 1

[0027] S100: monitoring and acquiring a gas flow sequence of a gas pipeline through a gas flow sensor, and monitoring and acquiring a gas concentration of a monitoring position through a gas concentration sensor, wherein the monitoring position is in a target space.

[0028] In the embodiments of the application, the flow information in the gas pipeline and the gas concentration information in the target space are acquired, thereby providing basic data for subsequent leakage risk determination. For example, when the gas flow is greater than 0 and the gas concentration in the monitoring space appears an upward trend, it is determined that there may be a gas leakage problem; if the gas flow is 0, it indicates that there is no gas flow in the monitoring space, and at this time, even if there is a small amount of concentration change, it may be historical residual gas or other external factors, rather than pipeline leakage.

[0029] Specifically, the step S100 comprises the following sub-steps:

[0030] When the gas pipeline has gas flow, the gas flow sequence of the gas pipeline is monitored and acquired through the gas flow sensor;

[0031] The gas concentration of the monitoring position is monitored and acquired through the gas concentration sensor, wherein the gas concentration sensor comprises a methane concentration sensor, and the monitoring position is in the target space.

[0032] ​In this embodiment, when gas flow occurs in the gas pipeline, a gas flow sensor is used to monitor and acquire the gas flow sequence. For example, a gas flow sensor, such as an ultrasonic flow meter or a diaphragm flow meter, is installed on the main gas pipeline entering the user's home to continuously monitor the volume or velocity of the gas flowing through the pipeline and record it at a fixed high-frequency sampling interval, such as once or ten times per second. These instantaneous flow data points arranged in chronological order constitute the gas flow sequence. The gas flow sequence can reflect the gas consumption and flow state per unit time and is used to determine whether gas usage is abnormal.

[0033] Gas concentration sensors, including methane concentration sensors, are used to monitor and obtain the gas concentration at a monitoring location within the target space. For example, a high-precision, interference-resistant methane concentration sensor can be placed in areas where gas leaks may accumulate in the kitchen, such as above the stove or near the ceiling, to ensure timely detection of changes in the concentration of leaked gas.

[0034] S200: Obtain the airflow characteristic distribution in the target space, and compensate the gas concentration according to the airflow characteristic distribution to obtain the compensated gas concentration.

[0035] In this embodiment, the airflow characteristic distribution within the target space is obtained. Based on this airflow characteristic distribution, the gas concentration is compensated to obtain a compensated gas concentration. This solves the problem of false alarms caused by environmental ventilation interference in traditional gas monitoring. By constructing the airflow characteristic distribution of the target space and using a trained gas concentration change analyzer, the impact of current ventilation conditions on the gas concentration readings at the monitoring point is quantitatively evaluated. This compensates the original value obtained by the concentration sensor, resulting in a compensated gas concentration that more closely approximates the actual leakage situation and eliminates ventilation interference.

[0036] Specifically, step S200 includes the following sub-steps:

[0037] An array of air flow sensors deployed within the target space is used to collect air flow characteristics from multiple air monitoring locations. These air flow characteristics include air velocity and air flow direction.

[0038] An airflow feature distribution is generated based on multiple airflow characteristics and the spatial coordinates of multiple air detection locations.

[0039] Based on the airflow characteristic distribution, the gas concentration is compensated to obtain a compensated gas concentration.

[0040] In the embodiments of the present application, an array of air flow sensors arranged in the target space is used to collect air flow characteristics at multiple air monitoring locations, wherein the air flow characteristics include air flow speed and air flow direction. The air flow sensors can be used to detect air flow speed and air flow direction, such as thermal anemometers, ultrasonic anemometers, etc. For example, in the target space, an array composed of multiple micro air flow sensor nodes is deployed, and each node integrates a sensor capable of measuring air flow speed and air flow direction.

[0041] According to the multiple air flow characteristics and the spatial coordinates of the multiple air detection locations, an air flow characteristic distribution is generated. For example, a three-dimensional spatial coordinate system is constructed in the target space, such as a kitchen, to form spatial coordinates. Using the data of multiple sensors, an air flow characteristic distribution of all spatial coordinates in the target space is formed by interpolation. Interpolation is an important method for approximating discrete functions, which can estimate the approximate value of a function at other points by using the value of the function at a limited number of points. Interpolation can be used to fill the gaps between pixels during image transformation. For example, in a target space such as a kitchen, there are two air monitoring locations A and B, and the unmonitored midpoint coordinate between A and B is C. According to the interpolation method, the wind speed and direction of the midpoint coordinate C are the average of the wind speed and direction of the two air monitoring locations A and B, so C = (A + B) / 2. Single-point wind speed and direction cannot reflect the air movement of the entire space. After generating the distribution by interpolation, the air flow environment around any location can be inferred, so that the concentration value can be more accurately compensated.

[0042] According to the air flow characteristic distribution, the gas concentration is compensated to obtain a compensated gas concentration. The data measured by the gas concentration sensor is a local concentration, and air flow dilution or enrichment may cause the local concentration to deviate from the actual leakage concentration. By compensating the gas concentration, the reading can be corrected to a value closer to the actual leakage level.

[0043] According to the air flow characteristic distribution, the gas concentration is compensated to obtain a compensated gas concentration, including:

[0044] In the air flow feature distribution, a neighboring air flow feature set within a preset range near the monitoring position is indexed. The neighboring air flow feature set refers to a local air flow speed and direction data set close to the gas concentration sensor position. The local features of the air flow have a greater impact on the sensor readings. For example, the wind speed and direction within 1 meter of the sensor will directly affect the diffusion of gas around the sensor, thereby affecting the sensor reading results. For example, taking the coordinates of the gas concentration sensor as the center point, a virtual sphere with a radius of 1 meter is divided, and the data of all interpolation points within the sphere is extracted from the air flow feature distribution to form a neighboring air flow feature set. The air flow is represented by wind speed and wind direction. The air flow direction is generally represented by the horizontal azimuth angle and the vertical elevation angle. A reference coordinate system is defined: the X-axis points to the east; the Y-axis points to the north; and the Z-axis is vertically upward. The horizontal azimuth angle refers to the angle between the projection of the wind speed vector on the horizontal plane (XY plane) and the north direction (Y-axis), ranging from 0° to 360° in the clockwise rotation direction; the vertical elevation angle refers to the angle between the wind speed vector itself and the horizontal plane (XY plane), ranging from -90° to +90° in the clockwise rotation direction. For example, the neighboring air flow feature set may include: {point 1: (1.7 m / s, 95°, 0°), point 2: (1.9 m / s, 105°, -10°), point 3: (1.8 m / s, 100°, +15°),...}.

[0045] The neighboring air flow feature set is input into the gas concentration change analyzer to output a gas concentration change coefficient. The gas concentration change analyzer is a calculation module trained based on a machine learning model, used to predict the influence of air flow on gas concentration. The gas concentration change coefficient can represent the concentration deviation caused by air flow. Training the gas concentration change analyzer using machine learning methods can continuously optimize the compensation coefficient and abnormality discrimination model to adapt to different environments, such as open kitchens, closed workshops, and outdoor work areas.

[0046] The training steps of the gas concentration change analyzer include:

[0047] According to the test data of the gas concentration change, a plurality of sample neighboring air flow feature sets are collected, and the amplitude of the gas concentration change under each sample neighboring air flow feature set is obtained to label a sample gas concentration change coefficient set; based on machine learning, a gas concentration change analyzer is constructed, and the plurality of sample neighboring air flow feature sets and the sample gas concentration change coefficient set are trained to convergence to complete the training.

[0048] The air flow characteristics of different environments are different, and must be applied to different scenes such as kitchens or workshops in a data-driven manner. For example, three different environments are simulated in the laboratory: low wind speed 0.1 m / s, medium wind speed 0.5 m / s, and high wind speed 2.0 m / s. The corresponding methane data is collected by sensors, and the actual diffusion concentration is detected and recorded. The difference between the two is calculated to obtain a sample gas concentration variation coefficient set, such as +0.05, +0.2, and +0.4. The neural network model is trained using these sample data, and finally a gas concentration variation analyzer that can be generalized to actual scenarios is obtained.

[0049] The gas concentration variation coefficient is used to compensate for the gas concentration to obtain a compensated gas concentration. The compensated concentration obtained after correction can be closer to the actual gas leakage concentration, thereby avoiding false positives or false negatives caused by air flow interference. For example, the methane concentration detected by a kitchen gas concentration sensor is 0.18%, and the air flow characteristics show that there is a wind speed of 0.5 m / s at this location, and the air flow direction will quickly carry away the gas. The calculated concentration variation coefficient is -0.2, indicating that the concentration is affected and reduced by 20%. The detected concentration is lower, so reverse compensation is required. Therefore, the methane concentration is corrected to 0.18% x (1+0.2) = 0.216%, which is closer to the actual concentration without wind.

[0050] S300: verifying gas anomaly based on the gas flow sequence and the compensated gas concentration, obtaining a gas anomaly rate, analyzing and correcting the gas anomaly based on the air flow characteristic distribution, and obtaining a corrected gas anomaly rate.

[0051] In the embodiments of the present application, by introducing the air flow characteristic distribution, the concentration data of the sensor is compensated, the errors caused by wind speed, wind direction, ventilation conditions and other factors are eliminated, the gas leakage detection result is closer to the actual situation, and false positives or false negatives are avoided.

[0052] Specifically, the step S300 includes the following sub-steps:

[0053] According to the gas flow sequence, the predicted gas concentration of the monitoring position is calculated and obtained;

[0054] The similarity between the compensated gas concentration and the predicted gas concentration is calculated as a gas anomaly rate;

[0055] According to the air flow characteristic distribution, the gas anomaly influence analysis is performed to obtain a gas anomaly influence coefficient;

[0056] The gas anomaly rate is corrected and calculated using the gas anomaly influence coefficient to obtain a corrected gas anomaly rate.

[0057] In the embodiments of the present application, a predicted gas concentration at the monitoring position is obtained according to the gas flow sequence. The gas flow sequence refers to the flow value of the gas in the pipeline changing over time. The predicted gas concentration is a theoretical concentration value calculated according to the pipeline flow, the gas diffusion model, and the like. For example, in a kitchen, a gas flow sensor detects that the gas flow is 1 L / min, the target space volume is 20 m 3 According to the diffusion model, it is predicted that the indoor gas concentration is (5x1) / 20=0.25% in 5 minutes, which is the predicted gas concentration.

[0058] The similarity between the compensated gas concentration and the predicted gas concentration is calculated as a gas anomaly rate. The similarity is usually calculated by using a difference value or correlation. Assuming that the predicted gas concentration in the target space of the kitchen is 0.25% and the compensated gas concentration is 0.23%, the similarity is 1-(|0.25-0.23|) / 0.25=0.92, that is, the gas anomaly rate is 92%, indicating that the possibility of gas leakage is very high.

[0059] According to the air flow feature distribution, gas anomaly influence analysis is performed to obtain a gas anomaly influence coefficient. For example, in a high-ventilation environment, rapid air flow can dilute the gas and reduce the probability of a dangerous event, so the gas anomaly influence coefficient needs to be used to correct the data, otherwise false positives may be caused.

[0060] The gas anomaly influence coefficient includes:

[0061] According to the air flow feature distribution, an average air flow rate is calculated. The air flows irregularly and unevenly in the space, and the value of a single sensor cannot represent the overall situation of the air flow. The average air flow rate can reflect the overall level of the entire space. For example, in a kitchen, four air flow sensors are arranged at different positions, and the detection results are 0.8 m / s, 0.6 m / s, 0.2 m / s, and 0.4 m / s, respectively. Then the average air flow rate is (0.8+0.6+0.2+0.4) / 4=0.5 m / s.

[0062] According to the gas monitoring historical data, the ratio of the proportion of gas anomalies at the average air flow rate to the historical average gas anomaly warning ratio is obtained as a gas anomaly influence coefficient. By using historical monitoring data, the proportion of gas anomalies at a certain average air flow rate is counted and compared with the overall anomaly ratio to obtain a correction coefficient. For example, when the average air flow rate is less than 0.2 m / s, the gas anomaly triggering ratio is 20%; when the average air flow rate is 2.0 m / s, the gas anomaly triggering ratio is 5%; the historical average anomaly ratio is 10%; and if the target space average air flow rate is 2.0 m / s, the gas anomaly influence coefficient is 5% / 10%=0.5.

[0063] The gas anomaly rate is corrected and calculated by using the gas anomaly influence coefficient to obtain a corrected gas anomaly rate. For example, the gas anomaly rate in the target space is 92%, and the gas anomaly influence coefficient is 0.5, so the corrected gas anomaly rate is: 92%*0.5=46%. The corrected gas anomaly rate is more in line with the actual risk level, and false positives or false negatives caused by air flow can be avoided.

[0064] S400: According to the corrected gas anomaly rate, a gas anomaly warning discrimination is performed to obtain a gas monitoring result.

[0065] In the embodiments of the present application, according to the corrected gas anomaly rate, a gas anomaly warning discrimination is performed to obtain a gas monitoring result, which can reduce false positives and improve safety. For example, when the target space, for example, the kitchen, has gas diffusion at the moment of using gas, but the air flow is fast and the risk is not large, after correction, the gas anomaly rate is lower than the threshold value, so the alarm will not be triggered; if the gas continues to leak, the corrected anomaly rate exceeds the threshold value, and the warning is triggered immediately.

[0066] Specifically, the step S400 includes the following sub-steps:

[0067] It is judged whether the corrected gas anomaly rate is greater than or equal to a gas anomaly rate threshold value;

[0068] If yes, a gas anomaly result is obtained, a gas anomaly warning is performed, and if no, a gas normal result is obtained, no gas anomaly warning is performed, and the gas monitoring result is obtained.

[0069] In the embodiments of the present application, it is judged whether the corrected gas anomaly rate is greater than or equal to a gas anomaly rate threshold value; if yes, a gas anomaly result is obtained, and a gas anomaly warning is performed; if no, a gas normal result is obtained, and no gas anomaly warning is performed, as a gas monitoring result. The gas anomaly rate threshold value is set and determined according to experiments, historical data statistics or industry safety standards. For example, the gas anomaly rate threshold value is 70%, when the corrected gas anomaly rate in the space is greater than or equal to 70%, it can be basically determined that gas leakage occurs, and the gas anomaly is determined, and the warning is triggered immediately; when the corrected gas anomaly rate is less than 70%, the gas is determined to be normal, and the warning is not triggered, only data is recorded. Long-term flow and concentration change data are recorded, combined with air flow characteristics, a historical database is formed, and leakage risk prediction can be realized. Through multi-dimensional detection and abnormal correction mechanism, the accident risk can be effectively reduced, and the gas monitoring accuracy and intelligence level are improved.

[0070] In the embodiments of the present application, a gas intelligent monitoring system is provided, as shown in Figure 2 The system comprises:

[0071] A gas concentration monitoring module 11 is configured to monitor and obtain a gas flow sequence of a gas pipeline through a gas flow sensor, and monitor and obtain a gas concentration at a monitoring position through a gas concentration sensor, wherein the monitoring position is in a target space.

[0072] A gas concentration compensation module 12 is configured to obtain an air flow characteristic distribution in the target space, compensate the gas concentration according to the air flow characteristic distribution, and obtain a compensated gas concentration.

[0073] A gas anomaly verification module 13 is configured to perform gas anomaly verification on the gas flow sequence and the compensated gas concentration, obtain a gas anomaly rate, perform gas anomaly influence analysis and correction according to the air flow characteristic distribution, and obtain a corrected gas anomaly rate.

[0074] A gas anomaly warning module 14 is configured to perform gas anomaly warning discrimination according to the corrected gas anomaly rate, and obtain a gas monitoring result.

[0075] In one embodiment, the gas concentration monitoring module 11 is further configured to:

[0076] When the gas pipeline has a gas flow, the gas flow sequence of the gas pipeline is monitored and obtained through the gas flow sensor;

[0077] The gas concentration at the monitoring position is monitored and obtained through the gas concentration sensor, wherein the gas concentration sensor comprises a methane concentration sensor, and the monitoring position is in the target space.

[0078] In one embodiment, the gas concentration compensation module 12 is further configured to:

[0079] collecting air flow features of a plurality of air monitoring positions through an air flow sensor array arranged in the target space, wherein the air flow features include air flow speed and air flow direction;

[0080] generating an air flow feature distribution according to the plurality of air flow features and spatial coordinates of the plurality of air monitoring positions;

[0081] compensating the gas concentration according to the air flow feature distribution to obtain a compensated gas concentration.

[0082] wherein the compensating the gas concentration according to the air flow feature distribution to obtain a compensated gas concentration comprises:

[0083] indexing a neighboring air flow feature set within a preset range near the monitoring position in the air flow feature distribution;

[0084] inputting the neighboring air flow feature set into a gas concentration change analyzer to output a gas concentration change coefficient;

[0085] compensating the gas concentration using the gas concentration change coefficient to obtain a compensated gas concentration.

[0086] wherein the training step of the gas concentration change analyzer comprises:

[0087] collecting a plurality of sets of sample neighboring air flow feature sets according to test data of gas concentration changes, and obtaining an amplitude of gas concentration change under each set of sample neighboring air flow feature sets to label a set of sample gas concentration change coefficients;

[0088] constructing a gas concentration change analyzer based on machine learning, and training the plurality of sets of sample neighboring air flow feature sets and the set of sample gas concentration change coefficients to convergence to complete the training.

[0089] In one embodiment, the gas anomaly verification module 13 is further configured to:

[0090] calculating a predicted gas concentration of the monitoring position according to the gas flow sequence;

[0091] calculating a similarity between the compensated gas concentration and the predicted gas concentration as a gas anomaly rate;

[0092] performing gas anomaly impact analysis according to the air flow feature distribution to obtain a gas anomaly impact coefficient;

[0093] correcting the gas anomaly rate using the gas anomaly impact coefficient to obtain a corrected gas anomaly rate.

[0094] The gas abnormality influence analysis is performed according to the air flow characteristic distribution, and a gas abnormality influence coefficient is obtained, including:

[0095] The average air flow rate is calculated according to the air flow characteristic distribution;

[0096] According to the gas monitoring historical data, the ratio of the proportion of gas abnormality under the average air flow rate to the historical average gas abnormality early warning ratio is obtained as the gas abnormality influence coefficient.

[0097] In one embodiment, the gas abnormality early warning module 14 is further configured to:

[0098] determine whether the corrected gas abnormality rate is greater than or equal to a gas abnormality rate threshold value;

[0099] if yes, obtain a gas abnormality result and perform gas abnormality early warning, and if no, obtain a gas normal result and do not perform gas abnormality early warning, as the gas monitoring result.

[0100] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above description is made for specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0101] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0102] The present application is only an exemplary description of the present application, and should be considered as covering any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalents, the present application intends to include these modifications and changes.

Claims

1. A method of intelligent monitoring of gas, characterized in that, The method comprises: monitoring the gas flow sequence of the gas pipeline through a gas flow sensor, and monitoring the gas concentration at the monitoring position through a gas concentration sensor, wherein the monitoring position is in the target space; obtaining the air flow feature distribution in the target space, and compensating the gas concentration according to the air flow feature distribution to obtain a compensated gas concentration; verifying the gas anomaly according to the gas flow sequence and the compensated gas concentration to obtain a gas anomaly rate, and performing gas anomaly influence analysis and correction according to the air flow feature distribution to obtain a corrected gas anomaly rate, wherein verifying the gas anomaly according to the gas flow sequence and the compensated gas concentration to obtain a gas anomaly rate comprises: calculating the predicted gas concentration at the monitoring position according to the gas flow sequence, wherein the predicted gas concentration is a theoretical concentration value calculated according to the pipeline flow and a gas diffusion model; calculating the similarity between the compensated gas concentration and the predicted gas concentration as the gas anomaly rate; performing gas anomaly early warning discrimination according to the corrected gas anomaly rate to obtain a gas monitoring result.

2. The method of claim 1, wherein, monitoring the gas flow sequence of the gas pipeline through a gas flow sensor, and monitoring the gas concentration at the monitoring position through a gas concentration sensor, comprising: monitoring the gas flow sequence of the gas pipeline through a gas flow sensor when the gas flow appears in the gas pipeline; monitoring the gas concentration at the monitoring position through a gas concentration sensor, wherein the gas concentration sensor comprises a methane concentration sensor, and the monitoring position is in the target space.

3. The gas intelligent monitoring method of claim 1, wherein, obtaining the air flow feature distribution in the target space, and compensating the gas concentration according to the air flow feature distribution to obtain a compensated gas concentration, comprising: collecting air flow features of multiple air monitoring positions through an air flow sensor array arranged in the target space, wherein the air flow features include air flow speed and air flow direction; generating an air flow feature distribution according to the multiple air flow features and the spatial coordinates of the multiple air monitoring positions; compensating the gas concentration according to the air flow feature distribution to obtain a compensated gas concentration.

4. The gas intelligent monitoring method according to claim 3, characterized in that, compensating the gas concentration according to the air flow feature distribution to obtain a compensated gas concentration, comprising: indexing a set of adjacent air flow features within a preset range near the monitoring position in the air flow feature distribution; inputting the set of adjacent air flow features into a gas concentration change analyzer to output a gas concentration change coefficient; compensating the gas concentration using the gas concentration change coefficient to obtain a compensated gas concentration.

5. The method of intelligent gas monitoring of claim 4, wherein, The training steps of the gas concentration change analyzer comprise: collecting multiple sets of sample adjacent air flow feature sets according to the test data of gas concentration change, and obtaining the amplitude of gas concentration change under each set of sample adjacent air flow feature sets to label a set of sample gas concentration change coefficients; based on machine learning, constructing a gas concentration change analyzer, and training the multiple sets of sample adjacent air flow feature sets and the set of sample gas concentration change coefficients to convergence to complete the training.

6. The intelligent gas monitoring method of claim 1, wherein, According to the air flow characteristic distribution, the gas abnormality influence analysis is performed to obtain a gas abnormality influence coefficient. According to the air flow characteristic distribution, the gas abnormality influence analysis is performed to obtain a gas abnormality influence coefficient. The gas abnormality rate is corrected by using the gas abnormality influence coefficient to obtain a corrected gas abnormality rate.

7. The gas smart monitoring method of claim 6, wherein, According to the air flow characteristic distribution, the gas abnormality influence analysis is performed to obtain a gas abnormality influence coefficient. According to the air flow characteristic distribution, the average air flow rate is calculated and obtained. According to the gas monitoring historical data, the ratio of the proportion of gas abnormality under the average air flow rate to the historical average gas abnormality early warning ratio is obtained as the gas abnormality influence coefficient.

8. The intelligent gas monitoring method of claim 1, wherein, According to the corrected gas abnormality rate, the gas abnormality early warning discrimination is performed to obtain a gas monitoring result, including: It is judged whether the corrected gas abnormality rate is greater than or equal to a gas abnormality rate threshold value. If yes, the gas abnormality result is obtained, and the gas abnormality early warning is performed, and if no, the gas normal result is obtained, and the gas abnormality early warning is not performed, as the gas monitoring result.

9. A gas intelligent monitoring system characterized in that, The system for implementing the gas intelligent monitoring method of any one of claims 1-8, the system comprising: A gas concentration monitoring module for monitoring and obtaining a gas flow sequence of a gas pipeline by a gas flow sensor, and monitoring and obtaining a gas concentration at a monitoring position by a gas concentration sensor, wherein the monitoring position is in a target space; A gas concentration compensation module for obtaining an air flow characteristic distribution in the target space, and compensating the gas concentration according to the air flow characteristic distribution to obtain a compensated gas concentration; A gas abnormality verification module for performing gas abnormality verification on the gas flow sequence and the compensated gas concentration to obtain a gas abnormality rate, and performing gas abnormality influence analysis and correction according to the air flow characteristic distribution to obtain a corrected gas abnormality rate, wherein the gas abnormality verification on the gas flow sequence and the compensated gas concentration to obtain the gas abnormality rate comprises: According to the gas flow sequence, a predicted gas concentration at the monitoring position is calculated and obtained, wherein the predicted gas concentration is a theoretical concentration value calculated according to the pipeline flow and a gas diffusion model; The similarity between the compensated gas concentration and the predicted gas concentration is calculated as the gas abnormality rate; A gas abnormality early warning module for performing gas abnormality early warning discrimination according to the corrected gas abnormality rate to obtain a gas monitoring result.

Images