Multi-gas data monitoring and intelligent management system and method based on NDIR

Abstract

The invention discloses a multi-gas data monitoring and intelligent management system and method based on NDIR, and relates to the technical field of gas data management, and the system comprises a gas data acquisition module, a gas data optimization module, a gas feature extraction module, a gas feature evaluation module, a gas database construction module and a gas monitoring alarm module. The method comprises the steps of collecting gas absorption intensity data and environmental data, optimizing the gas absorption intensity data, performing data preprocessing on gas, extracting gas characteristics from the processed data in combination with the environmental data, calculating influence coefficients of the characteristics on gas concentration, setting threshold screening characteristics, and changing the gas concentration in a monitoring environment. The method comprises the following steps: acquiring multiple groups of feature and concentration data, establishing a database, monitoring the difference degree between environment features and database features in real time, and judging and alarming according to the difference degree. According to the method, key features are screened according to a fixed and dynamic threshold value, accurate data support is provided, environmental gas safety is guaranteed, and potential risks are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of gas data management, and particularly to a multi-gas data monitoring and intelligent management system and method based on NDIR. Background Art

[0002] In the past, gas monitoring relied on basic sensors, and the data acquisition accuracy was poor. For example, in urban air monitoring, ordinary sensors had a narrow data acquisition range and low accuracy for the absorption intensity data of various pollutant gases, and it was difficult to distinguish the subtle differences in similar concentrations. At the same time, traditional monitoring basically only focused on the gas itself and ignored the surrounding environmental factors. For example, in a chemical industrial park, the particulate matter concentration, temperature and humidity in the environment affected the gas characteristics at all times, but these data were not included in the previous monitoring, resulting in the collected data being unable to truly reflect the actual state of the gas in a complex environment. Naturally, the analysis results based on these data were difficult to meet the requirements of accurate judgment and scientific decision-making; traditional gas characteristic analysis work relied on manual experience and simple algorithms. Staff manually calculated the correlation between each characteristic and the gas concentration, with low efficiency and being easily interfered by subjective factors. When analyzing the gases emitted by factories, in the face of complex absorption peak characteristics and changing environmental factors, it was difficult for manual analysis to quickly identify the key influencing factors. Due to the lack of an intelligent screening mechanism, a large number of invalid characteristics irrelevant to the gas concentration were included in the analysis, which not only consumed a lot of time but also reduced the reliability of the analysis results. This made it difficult for us to master the gas concentration change law in the first time and unable to provide strong data support for subsequent gas concentration prediction and control, restricting the effective treatment of gas pollution; traditional gas monitoring systems lacked the ability to compare and analyze the difference degree between the environment and the database characteristics in real time. In indoor air quality monitoring, even if there were records of gas concentration data, it was impossible to detect abnormal changes in real time. When harmful gases such as formaldehyde in the room slowly exceeded the standard, it was difficult for the system to discover in time. In industrial production scenarios, this lack of early warning was even more dangerous. Once toxic and harmful gases leaked and the concentration increased abnormally, due to the inability to give an early warning in time, safety accidents would occur. Summary of the Invention

[0003] The purpose of the present invention is to provide a multi-gas data monitoring and intelligent management system and method based on NDIR to solve the problems mentioned in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solutions: A multi-gas data monitoring and intelligent management method based on NDIR, including the following steps:

[0005] S1. In the monitoring environment, collect the absorption intensity data of the gas and the environmental data;

[0006] S2. Optimize the gas absorption intensity data and perform data preprocessing on the gas;

[0007] S3. Extract gas characteristics from the processed data in combination with environmental data;

[0008] S4. Calculate the influence coefficients of each characteristic on the gas concentration, and set a threshold to screen the characteristics that have an impact on the gas concentration;

[0009] S5. Change the gas concentration in the monitoring environment, obtain the characteristic and concentration data of the gas, and establish a database;

[0010] S6. Real-time monitor the difference degree between the characteristics in the environment and the characteristics in the database, and judge whether the environment is safe according to the difference degree.

[0011] Further, in step S1, in the monitoring environment, use the NDIR sensor to collect data on J gases at the monitoring time interval to obtain the absorption intensity data of J gases. The J gases include: {G1, G2, …, G j , …, G J}, record the absorption intensity data {I j at M wavelength points in the wavelength range [λ max , λ min for the gas G j1 , I j2 , …, I jm , …, I jM}, where m represents the m-th wavelength point; in the monitoring environment, use the particle size sensor and the temperature and humidity sensor to collect environmental data. The environmental data includes the particulate matter concentration data P J , the temperature data W J and the humidity data H J ; in the data collection stage of this monitoring method, multiple sensors work together to comprehensively obtain gas and environmental information. The NDIR sensor is responsible for collecting gas absorption intensity data, and the particle size and temperature and humidity sensors collect environmental data, avoiding the one-sidedness of monitoring information and providing a more complete information basis for subsequent analysis. Multi-dimensional data collection can more truly reflect the actual situation of gases in a complex environment. Whether it is industrial waste gas emission monitoring or indoor air quality control, it can effectively make up for the deficiencies of traditional single monitoring, enabling people to have a more comprehensive and accurate understanding of the environmental gas state and providing a reliable basis for environmental assessment and safety guarantee.

[0012] Further, in step S2, perform data preprocessing on the gas G j , and calculate the optimized absorption intensity data I’ j1 , I j2 , …, I jm , …, I jM} at the m-th wavelength point based on the absorption intensity data {I jm :

[0013]

[0014] where I jα represents the α-th absorption intensity data, and the optimized absorption intensity data at M wavelength points are calculated one by one to obtain the gas G j in the wavelength range [λ max , λ min , the optimized absorption intensity data {I' j1 , I' j2 , …, I' jm , …, I' jM} at M wavelength points, and then the optimized absorption intensity data are converted into standardized absorption intensity data {i' j1 , i' j2 , …, i' jm , …, i' jM} through standardization processing. By performing optimized calculations on the absorption intensity data of the gas G j using a specific formula, the noise and interference in the original data can be effectively removed, enabling the data to more accurately reflect the gas characteristics. The subsequent standardization processing unifies the scale of the data, making the data at different wavelength points comparable. This series of operations greatly improves the data quality, providing a solid and reliable data foundation for subsequent gas feature extraction. It allows analysts to more accurately grasp the gas characteristics based on high-quality data, improving the reliability and accuracy of the analysis results and effectively enhancing the effectiveness of the entire monitoring and management system.

[0015] Furthermore, in step S3, the gas G j is subjected to feature extraction to obtain the intensity data i' (j，max) of the absorption peak, the position data λ (j，max) and the full width at half maximum data Δλ j of the absorption peak are extracted from the infrared absorption spectrum. At the same time, in combination with the particulate matter concentration data P J , the temperature data W J and the humidity data H J , the change rates of particulate matter, temperature, and humidity in the monitoring environment within a monitoring period are calculated. For example, the calculation method of the change rate of particulate matter is as follows: assuming the monitoring period is t j , the particulate matter concentration data recorded at the start of the monitoring period is P J0 , and the particulate matter concentration data recorded at the end of the monitoring period is P J1 , then the change rate of particulate matter concentration within a monitoring period is (P J1 - P J0 ) / t j, The calculation methods of the temperature change rate data and the humidity change rate data are the same as those of the particle size change rate. By obtaining the intensity, position, and full width at half maximum data of the absorption peak, the key characteristics of the gas in the infrared absorption spectrum can be accurately located from the aspect of the gas's own characteristics, providing a core basis for gas component and concentration analysis. At the same time, by combining environmental data such as particulate matter concentration, temperature, and humidity, calculating their change rates, and taking environmental factors into consideration. This can not only reveal the dynamic impact of environmental changes on the gas but also help analysts grasp the evolution law of the gas in a complex environment from a more macroscopic perspective, improving the accuracy and comprehensiveness of gas monitoring and analysis, and providing solid data support for subsequent gas concentration assessment and early warning.

[0016] Further, in step S4, K monitoring samples are taken in the monitoring environment. In the k-th monitoring sample, for gas G j feature summarization is performed, and the feature set is {x (j,1k) , x (j,2k) , …, x (j,6k)}, where the position data of the absorption peak of gas G j is represented as x (j,1k) , and the position data of the absorption peak represents the wavelength corresponding to the maximum absorption intensity of gas G j . The intensity data of the absorption peak of gas G j is represented as x (j,2k) . The full width at half maximum data of gas G j is represented as x (j,3k) . The particle size change rate of gas G j is represented as x (j,4k) . The temperature change rate data of gas G j is represented as x (j,5k) . The humidity change rate data of gas G j is represented as x (j,6k) . Then, the influence coefficient ρ (j,yk) of feature x j on the concentration of gas G (j，y) is calculated:

[0017]

[0018] where x (j,yk) represents the y-th feature in the feature set {x (j,1k) , x (j,2k) , …, x (j,6k)} in the k-th monitoring sample, x (j,y) represents the mean value of the y-th feature in K samples, g (j,k) represents the concentration of gas G j in the k-th monitoring sample, and g j represents the concentration of gas G j in k monitoring samplesThe average concentration is substituted into y = 1, 2, 3, 4, 5, 6 one by one to calculate the characteristic pair gas G j The set of concentration influence coefficients of is {ρ (j，1) , ρ (j，2) , …, ρ (j，6)};

[0019] Calculate the concentration influence correlation threshold ρ j :

[0020]

[0021] where u is the influence tolerance set by the system. When ρ (j，y) > ρ j , the system determines that the y-th characteristic has an influence on the concentration of gas G j . When ρ (j，y) ≤ρ j , the system determines that the y-th characteristic has no influence on the concentration of gas G j . Thus, the final set of concentration influence coefficients {A (j，1) , A (j，2) , …, A (j，B)} is obtained, where B represents the number of characteristics determined by the system to have an influence on the concentration of gas G j . The set of characteristics is {C (j,1) , C (j,2) , …, C (j,B)}. At this time, the concentration of gas G j is g j . Thus, a set of data groups about the set of characteristics and the concentration of gas G j is obtained. By taking K samples in the monitoring environment and summarizing the characteristics of gas G j , its characteristics in different scenarios can be comprehensively captured. Calculating the influence coefficients of each characteristic on the concentration of gas G j can quantify the influence degree of each factor and clarify the key influencing factors. Setting the concentration influence correlation threshold can accurately screen out the characteristics that truly affect the gas concentration and exclude invalid interferences. The obtained set of characteristics and the gas concentration data groups provide an accurate data basis for in-depth analysis of the gas concentration change law, which helps to more efficiently and accurately predict and regulate the gas concentration in various application scenarios, ensuring environmental safety and production stability.

[0022] Furthermore, in step S5, on the premise of ensuring that the concentration of gas G j does not exceed the safety threshold, the concentration of gas G j in the monitoring environment is changed, and a total of R data groups about the set of characteristics and the concentration of gas G j are obtained, thereby establishing a database about the concentration of gas G j and the set of characteristics.

[0023] Furthermore, in step S6, during the monitoring process of any environment, the system calculates in real time the difference V between any environmental feature and the rth set of features in the database. (j_r) :

[0024]

[0025] Among them, M (j,b) is the bth feature monitored in real time, C (j_r,b) For the bth feature in the rth set of features in the database, substitute r=1,2,3,…,R one by one to obtain the difference set {1,2,…,V (j_r) ,…,V (j_R)}, the minimum difference value obtained by comparison is V (j_min) , set the maximum tolerance of difference V max , when V (j_min) >V max When the gas G is triggered j Concentration abnormal alarm, when V (j_min) ≤V max When the system determines V (j_min) Gas G in the data group j The concentration of the gas G in any of the above environments j Concentration; The system can dynamically track the change of gas concentration by calculating the difference between environmental characteristics and database feature sets in real time. Once the minimum difference V (j_min) Exceeding the maximum tolerance V max , immediately triggering an alarm. This allows relevant personnel to immediately detect abnormal gas concentrations and take timely measures to effectively prevent safety accidents and ensure the safety of production and life. When the difference is within the normal range, the system can quickly determine the current ambient gas concentration. This entire process greatly improves monitoring efficiency and accuracy, providing efficient and reliable technical support for ambient gas monitoring and reducing potential risks.

[0026] NDIR-based multi-gas data monitoring and intelligent management system, the system includes: a gas data acquisition module, a gas data optimization module, a gas feature extraction module, a gas feature evaluation module, a gas database construction module and a gas monitoring alarm module;

[0027] The gas data acquisition module collects gas absorption intensity data and environmental data in the monitoring environment;

[0028] The gas data optimization module optimizes the gas absorption intensity data and performs data preprocessing on the gas;

[0029] The gas feature extraction module extracts gas features from the processed data in combination with the environmental data;

[0030] The gas feature evaluation module calculates the influence coefficients of each feature on the gas concentration, and sets a threshold to screen the features that have an impact on the gas concentration;

[0031] The gas database construction module changes the gas concentration in the monitoring environment, obtains the feature and concentration data of the gas, and establishes a database;

[0032] The gas monitoring and alarm module monitors the difference degree between the features in the environment and the features in the database in real time, and judges whether the environment is safe according to the difference degree.

[0033] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: on the one hand, with the help of the NDIR sensor, the absorption intensity data of multiple gases is collected at specific time intervals, and at the same time, other sensors are used to obtain environmental data to ensure the comprehensiveness of the data. The absorption intensity data is optimized through a unique algorithm and then standardized to effectively filter out noise, convert the original data into high-quality analysis data, improve the data accuracy, provide a solid and reliable data basis for subsequent analysis, and greatly reduce the data error compared with the traditional method, and can accurately present the actual state of the gas;

[0034] On the one hand, the system automatically calculates the influence coefficients of each feature on the gas concentration, and sets a dynamic threshold to screen key features. In a complex environment, key influencing factors such as the characteristics of gas absorption peaks and changes in environmental factors can be quickly identified, interference from invalid features can be excluded, the analysis efficiency can be greatly improved, allowing analysts to quickly grasp the key points of gas concentration changes, providing accurate data support for database construction and real-time monitoring, significantly shortening the analysis time, and enhancing the reliability of the analysis.

[0035] On the other hand, the system calculates the difference degree between the environment and the database features in real time. Once it exceeds the maximum tolerance, an alarm is immediately triggered. In scenarios such as industrial production and indoor air monitoring, abnormal gas concentrations can be detected in the first time, providing time for personnel to handle, effectively preventing safety accidents, ensuring environmental safety, and reducing potential risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0037] Figure 1 is the structural diagram of the multi-gas data monitoring and intelligent management system based on NDIR of the present invention;

[0038] Figure 2 is the flowchart of the multi-gas data monitoring and intelligent management method based on NDIR of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Please refer to Figure 1 and Figure 2 , the present invention provides a technical solution: a multi-gas data monitoring and intelligent management method based on NDIR, including the following steps:

[0041] S1. In the monitoring environment, collect the absorption intensity data of the gas and the environmental data;

[0042] S2. Optimize the gas absorption intensity data and perform data preprocessing on the gas;

[0043] S3. Extract gas characteristics from the processed data in combination with the environmental data;

[0044] S4. Calculate the influence coefficient of each characteristic on the gas concentration, and set a threshold to screen the characteristics that have an impact on the gas concentration;

[0045] S5. Change the gas concentration in the monitoring environment, obtain the characteristic and concentration data of the gas, and establish a database;

[0046] S6. Real-time monitor the difference degree between the characteristics in the environment and the characteristics in the database, and judge whether the environment is safe according to the difference degree.

[0047] In step S1, in the monitoring environment, use the NDIR sensor to collect data on J kinds of gases at the monitoring time interval to obtain the absorption intensity data of J kinds of gases, and the J kinds of gases include: {G1, G2,..., G j ,..., G J}, record the absorption intensity data {I j at M wavelength points in the wavelength range [λ max , λ min of gas G j1 , I j2 ,..., I jm ,..., I jM}, where m represents the mth wavelength point; in the monitoring environment, use a particle size sensor and a temperature and humidity sensor to collect environmental data, and the environmental data includes particulate matter concentration data P J , temperature data W J and humidity data H J; In the data acquisition stage of this monitoring method, multiple sensors work together to comprehensively obtain gas and environmental information. The NDIR sensor is responsible for collecting gas absorption intensity data, and the particle size and temperature-humidity sensors collect environmental data, avoiding one-sidedness of monitoring information and providing a more complete information basis for subsequent analysis. Multi-dimensional data acquisition can more truly reflect the actual situation of gases in complex environments. Whether it is industrial waste gas emission monitoring or indoor air quality control, it can effectively make up for the deficiencies of traditional single monitoring, enabling people to have a more comprehensive and accurate understanding of the environmental gas state and providing a reliable basis for environmental assessment and safety guarantee.

[0048] In step S2, for gas G j perform data preprocessing, and calculate the optimized absorption intensity data I' at the m-th wavelength point based on the absorption intensity data {I j1 , I j2 , …, I j m , …, I jM}: jm :

[0049]

[0050] where I jα represents the α-th absorption intensity data - calculate the optimized absorption intensity data at M wavelength points one by one to obtain the optimized absorption intensity data {I' j of gas G at M wavelength points within the wavelength range [λ max , λ min , and then convert the optimized absorption intensity data into standardized absorption intensity data {i' j1 , i' j2 , …, i' jm , …, i' jM} through standardization processing. Then, convert the optimized absorption intensity data into standardized absorption intensity data {i' j1 , i' j2 , …, i' jm , …, i' jM} through standardization processing. Through a specific formula for gas G j1 , i' j2 , …, i' jm , …, i' jM}, and through a specific formula for gas G jOptimizing the calculation of the absorption intensity data can effectively eliminate the noise and interference in the original data, enabling the data to more accurately reflect the gas characteristics. The subsequent standardization process unifies the scale of the data, making the data at different wavelength points comparable. This series of operations greatly improves the data quality, providing a solid and reliable data foundation for subsequent gas feature extraction. It allows analysts to more accurately grasp the gas characteristics based on high-quality data, improving the reliability and accuracy of the analysis results and effectively enhancing the efficiency of the entire monitoring and management system.

[0051] In step S3, for gas G j perform feature extraction to obtain the intensity data i' of the absorption peak (j，max) , extract the position data λ of the absorption peak from the infrared absorption spectrum (j，max) and the full width at half maximum data Δλ of the absorption peak j . At the same time, combine the particulate matter concentration data P J , temperature data W J and humidity data H J , calculate the change rates of particulate matter, temperature, and humidity in the monitoring environment within a monitoring period. The calculation method of the particulate matter change rate is as follows: Set the monitoring period as t j . Record the particulate matter concentration data as P at the start of the monitoring period J0 . Record the particulate matter concentration data as P at the end of the monitoring period J1 . Then the change rate of particulate matter concentration within a monitoring period is (P J1 - P J0 ) / t j . The calculation methods of the temperature change rate data and humidity change rate data are the same as that of the particulate matter change rate. Obtaining the intensity, position, and full width at half maximum data of the absorption peak can accurately locate the key features of the gas in the infrared absorption spectrum from the aspect of the gas's own characteristics, providing a core basis for gas component and concentration analysis. At the same time, by combining environmental data such as particulate matter concentration, temperature, and humidity and calculating their change rates, environmental factors are taken into consideration. This can not only reveal the dynamic impact of environmental changes on the gas but also help analysts grasp the evolution law of the gas in a complex environment from a more macroscopic perspective, improving the accuracy and comprehensiveness of gas monitoring and analysis and providing solid data support for subsequent gas concentration assessment and early warning.

[0052] In step S4, take K monitoring samples in the monitoring environment. In the kth monitoring sample, summarize the features of gas G j . The feature set is {x (j,1k) , x (j,2k) , …, x (j,6k)}, where the position data of the absorption peak of gas G j is represented as x (j,1k), the position data of the absorption peak represents the gas G j when the absorption intensity data is the largest, and the intensity data of the absorption peak of the gas G j is represented as x (j,2k) , the gas G j the full width at half maximum data is represented as x (j,3k) , the gas G j the particle size change rate is represented as x (j,4k) , the gas G j the temperature change rate data is represented as x (j,5k) , the gas G j the humidity change rate data is represented as x (j,6k) , and then calculate the characteristic x (j,yk) for the influence coefficient ρ j of the gas G (j，y) :

[0053]

[0054] [[ID=3�]], where x (j,yk) represents the y-th characteristic in the characteristic set {x (j,1k) , x (j,2k) , …, x (j,6k)} in the k-th monitoring sample, x (j,y) represents the mean value of the y-th characteristic in K samples, g (j,k) represents the concentration of the gas G j in the k-th monitoring sample, g j represents the average concentration of the gas G j in k monitoring samples. Substitute y = 1, 2, 3, 4, 5, 6 one by one to calculate the influence coefficient set of the characteristic on the gas G j as {ρ (j，1) , ρ (j，2) , …, ρ (j，6)};

[0055] Calculate the correlation threshold ρ j of the concentration influence:

[0056]

[0057] where u is the influence tolerance set by the system. When ρ (j，y) > ρ j , the system judges that the y-th characteristic has an influence on the concentration of the gas G j . When ρ (j，y) ≤ ρ j , the system judges that the y-th characteristic has no influence on the concentration of the gas G j , so as to obtain the final concentration influence coefficient set {A (j，1) , A (j，2) , …, A(j，B)}, where B represents the number of features that the system determines have an impact on the concentration of gas G j , and the feature set is {C (j,1) , C (j,2) , …, C (j,B)}. At this time, the concentration of gas G j is g j , thus obtaining a data set about the feature set and the concentration of gas G j . By taking K samples in the monitoring environment and summarizing the features of gas G j , its characteristics in different scenarios can be comprehensively captured. Calculating the influence coefficient of each feature on the concentration of gas G j can quantify the influence degree of each factor and identify the key influencing factors. Setting the threshold for the relevance of concentration influence can accurately screen out the features that truly affect the gas concentration and exclude invalid interferences. The obtained feature set and the gas concentration data set provide an accurate data basis for in-depth analysis of the gas concentration change law, which helps to more efficiently and accurately predict and regulate the gas concentration in various application scenarios, ensuring environmental safety and production stability.

[0058] In step S5, on the premise of ensuring that the concentration of gas G j does not exceed the safety threshold, change the concentration of gas G j in the monitoring environment, and a total of R data sets about the feature set and the concentration of gas G j are obtained, thus establishing a database about the concentration of gas G j and the feature set.

[0059] In step S6, during the monitoring of any environment, the system calculates the difference degree V (j_r) between the features of any environment and the r-th group of feature sets in the database in real time:

[0060]

[0061] where M (j,b) is the b-th feature monitored in real time, and C (j_r,b) is the b-th feature in the r-th group of features in the database. Substituting r = 1, 2, 3, …, R one by one, a difference degree set {1, 2, …, V (j_r) , …, V (j_R)} is obtained. By comparing, the minimum value of the difference degree is V (j_min) . Set the maximum tolerance V max of the difference degree. When V (j_min) > V max , trigger an alarm for abnormal concentration of gas G j . When V (j_min) ≤ V max , the system determines V (j_min)Gas G in the data group where it is located j Gas G with the concentration in any of the said environments j Concentration; by calculating the difference degree between the environmental characteristics and the database characteristic set in real time, the system can dynamically track the change of gas concentration. Once the minimum value V of the difference degree (j_min) exceeds the maximum tolerance V max , an alarm will be triggered immediately, which enables relevant personnel to detect the abnormal gas concentration in the first time, take measures in time, effectively prevent the occurrence of safety accidents, and ensure the safety of production and life. When the difference degree is within the normal range, the system can quickly judge the current environmental gas concentration. The whole process greatly improves the monitoring efficiency and accuracy, provides efficient and reliable technical support for environmental gas monitoring, and reduces potential risks.

[0062] Multi-gas data monitoring and intelligent management system based on NDIR, the system includes: gas data acquisition module, gas data optimization module, gas feature extraction module, gas feature evaluation module, gas database construction module and gas monitoring and alarm module;

[0063] The gas data acquisition module collects the absorption intensity data of the gas and environmental data in the monitoring environment;

[0064] The gas data optimization module optimizes the gas absorption intensity data and preprocesses the gas data;

[0065] The gas feature extraction module extracts gas features from the processed data in combination with environmental data;

[0066] The gas feature evaluation module calculates the influence coefficient of each feature on the gas concentration and sets a threshold to screen the features that have an impact on the gas concentration;

[0067] The gas database construction module changes the gas concentration in the monitoring environment, obtains the feature and concentration data of the gas, and establishes a database;

[0068] The gas monitoring and alarm module monitors the difference degree between the features in the environment and the database features in real time, and judges whether the environment is safe according to the difference degree.

[0069] Example 1: In step S1, there are various harmful gases in the chemical industrial park, such as sulfur dioxide, nitrogen oxides, etc. According to the set monitoring time interval, we use NDIR sensors to collect the absorption intensity data of these gases. At the same time, particulate sensors and temperature and humidity sensors are deployed at different positions in the park to collect the environment.

[0070] Enter step S2, the original gas absorption intensity data collected will be affected by various interferences. Through specific optimization algorithms and standardization processing, the data is purified so that it can more accurately reflect the gas characteristics and lay a solid foundation for subsequent analysis.

[0071] In step S3, gas characteristics are extracted from the processed data, such as the intensity, position, and full width at half maximum of the absorption peak. At the same time, in combination with the change rate of the environmental data, the characteristics of the gas in a complex environment are comprehensively analyzed, enabling analysts to deeply understand the gas behavior.

[0072] In step S4, multiple monitoring samples are selected in different areas of the park, the characteristics of each gas are summarized, the influence coefficients of each characteristic on the gas concentration are calculated, and thresholds are set to screen key characteristics, so as to clarify which factors play a key role in the change of the gas concentration.

[0073] In step S5, on the premise of safety and controllability, the gas concentration in a local area is changed to obtain multiple sets of characteristic and concentration data, and a database of gas concentration and characteristic sets exclusive to the park is established.

[0074] Finally, in step S6, the system calculates the difference degree between the real-time environmental characteristics in the park and the characteristic set in the database in real time. Once the difference degree exceeds the maximum tolerance, an alarm is immediately triggered, and the park management personnel can take timely measures to ensure the production safety and environmental stability of the park.

[0075] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. An NDIR-based multi-gas data monitoring and intelligent management method, characterized in that: The method includes the following steps: S1. In the monitoring environment, collect the absorption intensity data of the gas and the environmental data; S2. Optimize the gas absorption intensity data and perform data preprocessing on the gas; S3. Extract gas characteristics from the processed data in combination with the environmental data; S4. Calculate the influence coefficient of each characteristic on the gas concentration, and set a threshold to screen the characteristics that have an impact on the gas concentration; S5. Change the gas concentration in the monitoring environment, obtain the characteristic and concentration data of the gas, and establish a database; S6. Real-time monitor the difference degree between the characteristics in the environment and the database characteristics, and judge whether the environment is safe according to the difference degree.

2. The method for multi-gas data monitoring and intelligent management based on NDIR according to claim 1, wherein: In step S1, in the monitoring environment, data of J kinds of gases are collected using an NDIR sensor at monitoring time intervals to obtain absorption intensity data of the J kinds of gases. The J kinds of gases include: {G1, G2, …, G j , …, G J}, and the absorption intensity data {I j at M wavelength points in the wavelength range [λ max , λ min of gas G j1 , I j2 , …, I jm , …, I jM} is recorded, where m represents the m-th wavelength point. In the monitoring environment, environmental data are collected using a particle size sensor and a temperature and humidity sensor. The environmental data include particulate matter concentration data P J , temperature data W J , and humidity data H J .

3. The multi-gas data monitoring and intelligent management method based on NDIR according to claim 2, wherein: In step S2, for the gas G j perform data preprocessing, and based on the absorption intensity data {I j1 , I j2 , …, I jm , …, I jM} calculate the optimized absorption intensity data I’ jm ; Calculate the optimized absorption intensity data at M wavelength points one by one to obtain gas G j In the wavelength range [λ max , λ min , the optimized absorption intensity data {I’ j1 , I’ j2 , …, I’ jm , …, I’ jM} at M wavelength points are obtained. Then, the optimized absorption intensity data is transformed into standardized absorption intensity data {i’ j1 , i’ j2 , …, i’ jm , …, i’ jM} through Z-score normalization processing.

4. The method for multi-gas data monitoring and intelligent management based on NDIR according to claim 3, wherein: In step S3, for gas G j feature extraction is performed to obtain the intensity data i' of the absorption peak (j，max) , the position data λ of the absorption peak is extracted from the infrared absorption spectrum (j，max) and the full width at half maximum data Δλ of the absorption peak j . Meanwhile, combining the particulate matter concentration data P J , the temperature data W J and the humidity data H J , the change rate of particle size, the change rate data of temperature, and the change rate data of humidity of the particulate matter concentration within a monitoring period are calculated.

5. The method for multi-gas data monitoring and intelligent management based on NDIR according to claim 4, characterized in that: In step S4, K monitoring samples are taken in the monitoring environment. In the k-th monitoring sample, for gas G j feature summarization is performed, and the feature set is {x (j,1k) , x (j,2k) , …, x (j,6k)}, where the position data of the absorption peak of gas G j is represented as x (j,1k) , and the position data of the absorption peak represents the wavelength corresponding to the maximum absorption intensity data of gas G j . The intensity data of the absorption peak of gas G j is represented as x (j,2k) , the full width at half maximum data of gas G j is represented as x (j,3k) , the granularity change rate of gas G j is represented as x (j,4k) , the temperature change rate data of gas G j is represented as x (j,5k) , the humidity change rate data of gas G j is represented as x (j,6k) . Furthermore, the influence coefficient ρ (j,yk) of feature x j on the concentration of gas G (j，y) is calculated; Substitute y = 1, 2, 3, 4, 5, 6 one by one, and calculate to obtain the set of concentration influence coefficients of the characteristic pair gas G j is {ρ (j，1) , ρ (j，2) , …, ρ (j，6)}.

6. The method for multi-gas data monitoring and intelligent management based on NDIR according to claim 5, wherein: Calculate the relevance threshold ρ for concentration influence j : where u is the influence tolerance set by the system. When ρ (j，y) > ρ j , the system determines that the y-th feature has an impact on the concentration of gas G j . When ρ (j，y) ≤ ρ j , the system determines that the y-th feature has no impact on the concentration of gas G j . Thus, the final set of concentration influence coefficients {A (j，1) , A (j，2) , …, A (j，B)} is obtained, where B represents the number of features determined by the system to have an impact on the concentration of gas G j . The feature set is {C (j,1) , C (j,2) , …, C (j,B)}. At this time, the concentration of gas G j in the monitored environment is g j . Thus, a data set regarding the feature set and the concentration of gas G j is obtained.

7. The method for multi-gas data monitoring and intelligent management based on NDIR according to claim 6, characterized in that: In step S5, on the premise of ensuring that the concentration of gas G j does not exceed the safety threshold, change the concentration of gas G j in the monitoring environment, and a total of R sets of data groups regarding the feature set and the concentration of gas G j are obtained, so as to establish a database regarding the concentration of gas G j and the feature set.

8. The method for multi-gas data monitoring and intelligent management based on NDIR according to claim 7, characterized in that: In step S6, during the monitoring of any environment, the system calculates the difference degree V between any environmental feature and the r-th group of feature sets in the database in real time (j_r) ; Substitute r = 1, 2, 3, …, R one by one to obtain the difference degree set {1, 2, …, V (j_r) , …, V (j_R)}, compare to obtain the minimum difference degree as V (j_min) , set the maximum tolerance of the difference degree as V max , when V (j_min) > V max , trigger the abnormal alarm of the gas G j concentration. When V (j_min) ≤ V max , judge that the gas G (j_min) concentration in the data group where V j is located is the gas G j concentration of any of the environments.

9. An NDIR-based multi-gas data monitoring and intelligent management system, which is applied to the NDIR-based multi-gas data monitoring and intelligent management method according to any one of claims 1-8, and is characterized in that: The system includes: a gas data acquisition module, a gas data optimization module, a gas characteristic extraction module, a gas characteristic evaluation module, a gas database construction module, and a gas monitoring and alarm module; The gas data acquisition module collects the absorption intensity data of the gas and the environmental data in the monitoring environment; The gas data optimization module optimizes the gas absorption intensity data and performs data preprocessing on the gas; The gas characteristic extraction module extracts gas characteristics from the processed data in combination with the environmental data; The gas characteristic evaluation module calculates the influence coefficient of each characteristic on the gas concentration, and sets a threshold to screen the characteristics that have an impact on the gas concentration; The gas database construction module changes the gas concentration in the monitoring environment, obtains the characteristic and concentration data of the gas, and establishes a database; The gas monitoring and alarm module real-time monitors the difference degree between the characteristics in the environment and the database characteristics, and judges whether the environment is safe according to the difference degree.

Images