Natural gas concentration safety detection system

Abstract

The invention provides a natural gas concentration safety detection system, and particularly relates to the technical field of natural gas concentration detection, which comprises a detection module, a data transmission module, a processing module, an alarm module, a power supply module and a user terminal interaction module, and the detection module adopts an intermediate infrared spectrum sensor based on a quantum cascade laser. By adopting the mid-infrared spectrum sensor based on the quantum cascade laser, ppb-level high-precision detection of the natural gas concentration can be realized, the integrated environmental parameter monitoring unit can master environmental temperature, humidity and air pressure parameters in real time, and through a self-adaptive environmental compensation algorithm and by utilizing temperature, humidity and air pressure compensation formulas, the natural gas concentration can be accurately detected. The method comprehensively considers the influence of environmental factors on the detection result, effectively corrects the detection data, greatly improves the detection precision and environmental interference resistance, enables the detection result to be more suitable for the actual natural gas concentration condition, and reduces the misjudgment risk caused by environmental changes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of natural gas concentration detection, in particular to a natural gas concentration safety detection system. BACKGROUND

[0002] Natural gas refers to all gases naturally existing in nature, including gases formed by various natural processes in the atmosphere, hydrosphere and lithosphere. In petroleum geology, it usually refers to oilfield gas and gas field gas, which is mainly composed of hydrocarbons and contains non-hydrocarbon gases. Natural gas has been widely used in people's daily life, but the safe use of natural gas during use cannot be ignored. In the production, transportation and use of natural gas, natural gas leakage may cause explosions, fires and poisoning accidents, so it is very important to detect the concentration of natural gas.

[0003] The existing natural gas detection technology mainly uses catalytic combustion, semiconductor or electrochemical sensor, which has insufficient detection accuracy and cannot meet the early warning demand of micro-leakage. Moreover, it does not integrate environmental parameter monitoring unit or compensate for temperature, humidity and air pressure changes. For example, the increase of temperature may cause the response of sensor to drift, the change of humidity may affect the gas diffusion rate, and the fluctuation of air pressure may change the gas concentration calculation benchmark. These factors will cause the detection result to be distorted, leading to false alarm or missed alarm, which is difficult to meet the demand of natural gas safety detection in actual application. SUMMARY

[0004] Therefore, the present application provides a natural gas concentration safety detection system to solve the problems of insufficient detection accuracy and environmental factor interference in the prior art, which can effectively reduce the safety risk in the use of natural gas and provide more reliable safety protection for users.

[0005] The embodiment of the present application provides a natural gas concentration safety detection system, which comprises a detection module, a data transmission module, a processing module, an alarm module, a power module and a user terminal interaction module; the detection module adopts a mid-infrared spectrum sensor based on a quantum cascade laser to acquire natural gas concentration data in real time, integrates an environmental parameter monitoring unit to acquire environmental parameter data in real time, and corrects the natural gas concentration data and the environmental parameter data through a self-adaptive environmental compensation algorithm; the data transmission module adopts LoRa wireless communication technology to transmit the corrected natural gas concentration data and environmental parameter data to the processing module in real time; the processing module is internally provided with big data analysis and machine learning algorithms, is used for analyzing and processing the received corrected natural gas concentration data and environmental parameter data, identifying a natural gas concentration change mode, judging whether natural gas leakage occurs and predicting a leakage risk, obtaining an analysis result, and controlling the alarm module to work according to the analysis result; the alarm module is used for emitting an audible and light alarm signal when the analysis result indicates that natural gas leakage occurs or high leakage risk is predicted, and sending alarm information to a user terminal through a wireless communication mode; the power module adopts a high-efficiency battery and is used for providing power support for the detection module, the data transmission module, the processing module and the alarm module; and the power module simultaneously integrates an energy recovery unit and is used for recovering energy to charge the battery during equipment movement.

[0006] Optionally, the mid-infrared spectrum sensor in the detection module adopts an array layout to expand the detection range of a single sensor, and the shell of the mid-infrared spectrum sensor has corrosion resistance, dustproofness and waterproofness.

[0007] Optionally, the data transmission module adopts an AES encryption algorithm to encrypt the transmitted corrected natural gas concentration data and environmental parameter data, so as to ensure the security of data transmission.

[0008] Optionally, the processing module is further connected with a storage unit, and the storage unit is used for storing historical detection data and the analysis result, so as to be subsequently inquired and optimized and trained on the machine learning algorithm.

[0009] Optionally, the audible and light alarm signal emitted by the alarm module has multiple alarm modes, different alarm modes are switched according to the severity of natural gas leakage and the risk level, and the different alarm modes correspond to different alarm sound intensities and light flicker frequencies.

[0010] Optionally, the energy recovery unit in the power module adopts a vibration energy collection technology, and the vibration energy collection technology collects energy through vibration generated by equipment movement and converts the energy into electric energy to be stored in the battery.

[0011] Optionally, the detection system further comprises a user terminal interaction module for user to interact with the detection system through mobile phone APP or computer client, including real-time viewing of natural gas concentration data, alarm information and setting of the detection system parameters.

[0012] Optionally, the adaptive environmental compensation algorithm corrects the natural gas concentration data and the environmental parameter data detection data through the following formula:

[0013] Temperature compensation formula:

[0014] C corrected-T =C measured ×(1+α T ×(T-T0))

[0015] Wherein, C corrected-T is the natural gas concentration value after temperature compensation, unit: ppb, C measured is the natural gas concentration original data directly measured by the mid-infrared spectrum sensor, unit: ppb, α T is the temperature compensation coefficient, T is the real-time monitored environmental temperature, unit: ℃, T0 is the standard reference temperature, unit: ℃;

[0016] Humidity compensation formula:

[0017] C corrected-H =C corrected-T ×(1-α H )×(H-H0))

[0018] Wherein, C corrected-H is the natural gas concentration value after humidity compensation, unit: ppb, C corrected-T is the natural gas concentration value after temperature compensation, unit: ppb, α H is the humidity compensation coefficient, H is the real-time monitored environmental humidity, unit: %RH, H0 is the standard reference humidity, unit: %RH;

[0019] Atmospheric pressure compensation formula:

[0020]

[0021] Wherein, C corrected-P is the final natural gas concentration value after atmospheric pressure compensation, unit: ppb; C corrected-H is the natural gas concentration value after humidity compensation, unit: ppb, P0 is the standard reference atmospheric pressure, unit: kPa; P is the real-time monitored environmental atmospheric pressure, unit: kPa.

[0022] Optionally, the machine learning algorithm comprises a support vector machine-based leakage identification algorithm and an ARIMA-based leakage risk prediction algorithm; the support vector machine-based leakage identification algorithm determines the class to which the input data x belongs in the linearly separable case by the following decision function:

[0023] f(x)=sign(omega T x+b)

[0024] Wherein, f(x) is the output value of the decision function, x is the input feature vector, containing the natural gas concentration value after environmental compensation, real-time environmental temperature, humidity, air pressure, omega is the weight vector, and b is the bias term;

[0025] The following decision function is used to determine the class to which x belongs in the non-linearly separable case:

[0026]

[0027] Wherein, alpha i is the Lagrange multiplier, y i is the class label of the training sample x i , K(x i , x) is the kernel function, the radial basis function K(x i , x)=exp(-gamma||x-x i || 2 ), n is the number of training samples;

[0028] The ARIMA-based leakage risk prediction algorithm predicts the future natural gas concentration by the following formula:

[0029]

[0030] Wherein, y t is the natural gas concentration observation value at time t, unit: ppb, mu is the mean of the time series, p is the order of the autoregressive term, is the autoregressive coefficient, q is the order of the moving average term, theta j is the moving average coefficient, epsilon t is the white noise error term at time t.

[0031] Optionally, the support vector machine-based leakage identification algorithm optimizes the weight vector and the bias term by gradient descent method, and the ARIMA-based leakage risk prediction algorithm estimates the autoregressive coefficient and the moving average coefficient by least square method.

[0032] Compared with the prior art, the present application has the following beneficial effects:

[0033] (1) The detection module of the present application adopts a mid-infrared spectrum sensor based on a quantum cascade laser, which can realize high-precision detection of natural gas concentration at the ppb level. The integrated environmental parameter monitoring unit can monitor the environmental temperature, humidity and air pressure parameters in real time. Through the self-adaptive environmental compensation algorithm and the temperature, humidity and air pressure compensation formula, the influence of environmental factors on the detection results is comprehensively considered, the detection data is effectively corrected, the detection precision and the anti-environmental interference ability are greatly improved, the detection results are more in line with the actual natural gas concentration situation, and the risk of misjudgment caused by environmental changes is reduced.

[0034] (2) The processing module of the present application is built-in big data analysis and machine learning algorithm, based on support vector machine (SVM) leakage identification algorithm, which can flexibly select decision function according to whether the data is linearly separable, accurately identify the natural gas leakage state, based on ARIMA leakage risk prediction algorithm, through in-depth analysis of historical concentration data, predict the future natural gas concentration trend, detect potential leakage risk in advance, gain valuable time for accident prevention, and effectively improve the safety of natural gas use. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments described in the embodiments of the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0036] Figure 1 It is a schematic diagram of the overall framework structure of the present application.

[0037] Figure 2 It is a flowchart of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0039] Referring to Figure 1 , Figure 2 The present application provides a natural gas concentration safety detection system, specifically comprising:

[0040] Detection module:

[0041] The detection module adopts a mid-infrared spectrum sensor based on a quantum cascade laser for high-precision detection of natural gas concentration in the environment, and real-time acquisition of natural gas concentration data, with a detection precision of ppb level.

[0042] The detection module is integrated with an environmental parameter monitoring unit for real-time acquisition of environmental parameter data, including environmental temperature, humidity and air pressure parameters.

[0043] It should be understood that the detection data of the present application includes the natural gas concentration data and the environmental parameter data.

[0044] The detection module also has a built-in adaptive environmental compensation algorithm, which compensates the detection data through the adaptive environmental compensation algorithm, effectively correcting the detection data.

[0045] The adaptive environmental compensation algorithm compensates the detection data through the following formula:

[0046] Temperature compensation formula:

[0047] C corrected-T =C measured ×(1+α T ×(T-T0))

[0048] Wherein, C corrected-T is the natural gas concentration value after temperature compensation, with unit of ppb, C measured is the natural gas concentration original data directly measured by the mid-infrared spectrum sensor, with unit of ppb, α T is the temperature compensation coefficient, T is the real-time monitored environmental temperature, with unit of ℃, T0 is the standard reference temperature, with unit of ℃;

[0049] Humidity compensation formula:

[0050] C corrected-H =C corrected -T×(1+α H ×(H-H0))

[0051] Wherein, C corrected-H is the natural gas concentration value after humidity compensation, with unit of ppb, C corrected-T is the natural gas concentration value after temperature compensation, with unit of ppb, α H is the humidity compensation coefficient, H is the real-time monitored environmental humidity, with unit of %RH, H0 is the standard reference humidity, with unit of %RH;

[0052] Air pressure compensation formula:

[0053]

[0054] Wherein, C corrected-PC is the final natural gas concentration value after pressure compensation, unit: ppb; C0 is the initial natural gas concentration value, unit: ppb; P0 is the standard reference air pressure, unit: kPa; P is the real-time monitored ambient air pressure, unit: kPa. corrected-H C is the natural gas concentration value after humidity compensation, unit: ppb; P0 is the standard reference air pressure, unit: kPa; P is the real-time monitored ambient air pressure, unit: kPa.

[0055] In addition, the mid-infrared spectrum sensor in the detection module adopts an array layout to expand the detection range of a single sensor, and the shell of the mid-infrared spectrum sensor is made of a material with corrosion resistance, dustproofness and waterproofness.

[0056] The data transmission module:

[0057] The data transmission module adopts LoRa wireless communication technology to transmit the corrected natural gas concentration data and environmental parameter data in real time to the processing module.

[0058] The data transmission module has a data encryption function, and uses the AES encryption algorithm to encrypt the transmitted corrected natural gas concentration data and environmental parameter data to ensure the security of data transmission.

[0059] For example, after the detection module completes data detection and compensation, it packages and arranges the compensated natural gas concentration data and environmental temperature, humidity, air pressure and other parameter data. Subsequently, the packaged data is encrypted using the AES encryption algorithm to convert the plaintext data into ciphertext, ensuring data security. After encryption is complete, the encrypted data is sent to the processing module using LoRa wireless communication technology through a specific frequency wireless signal.

[0060] It should be understood that the LoRa technology has the characteristics of low power consumption and long distance transmission, and can meet the data transmission needs of the natural gas concentration safety detection system in different scenarios.

[0061] In summary, the data transmission module uses LoRa wireless communication technology to ensure that the natural gas concentration data and environmental parameter data obtained by the detection module can be transmitted to the processing module in real time. At the same time, the AES encryption algorithm is used to encrypt the transmitted data, building a security barrier for the data during transmission to prevent data from being stolen or tampered with, ensuring the integrity and security of the data and meeting the strict requirements of natural gas detection scenarios for reliable data transmission.

[0062] The processing module:

[0063] The processing module is built-in with big data analysis and machine learning algorithms for analyzing and processing the received corrected natural gas concentration data and environmental parameter data, identifying natural gas concentration change patterns, determining whether a natural gas leak has occurred and predicting leak risks, obtaining analysis results, and controlling the alarm module according to the analysis results.

[0064] The machine learning algorithm includes a leakage identification algorithm based on a support vector machine and a leakage risk prediction algorithm based on ARIMA.

[0065] It should be understood that the leakage identification algorithm based on a support vector machine is a leakage identification algorithm based on a support vector machine (SVM).

[0066] (1) The leakage identification algorithm based on a support vector machine determines the class to which the input data x belongs in the linearly separable case through the following decision function:

[0067] f(x) = sign(ω T x + b)

[0068] where f(x) is the output value of the decision function, x is the input feature vector, including the natural gas concentration value after environmental compensation, real-time environmental temperature, humidity, and air pressure, ω is the weight vector, and b is the bias term.

[0069] In the non-linearly separable case, the class to which x belongs is determined by the following decision function:

[0070]

[0071] where α i is the Lagrange multiplier, y i is the class label of the training sample x i , K(x i , x) is the kernel function, and the radial basis function K(x i , x) = exp(-γ||x-x i || 2 ) is used, n is the number of training samples.

[0072] In addition, the leakage identification algorithm based on a support vector machine optimizes the weight vector ω and the bias term b through the gradient descent method.

[0073] (2) The leakage risk prediction algorithm based on ARIMA predicts the future natural gas concentration through the following formula:

[0074]

[0075] where y t is the natural gas concentration observation value at time t, with units of ppb, μ is the mean of the time series, p is the order of the autoregressive term, is the autoregressive coefficient, q is the order of the moving average term, θ j is the moving average coefficient, and ∈ t is the white noise error term at time t.

[0076] In addition, the ARIMA-based leakage risk prediction algorithm estimates the autoregressive coefficients and the moving average coefficients θ j by least squares method.

[0077] The processing module is also connected with a storage unit for storing historical detection data and analysis results for subsequent query and optimized training of machine learning algorithms.

[0078] The alarm module:

[0079] The alarm module is used to issue an audible and visual alarm signal when the analysis result indicates that natural gas leakage has occurred or high leakage risk is predicted, and send alarm information to the user terminal through wireless communication.

[0080] The audible and visual alarm signal issued by the alarm module has multiple alarm modes, which are switched according to the severity of natural gas leakage and risk level, and the alarm sound intensity and light flicker frequency can be adjusted, different alarm modes correspond to different alarm sound intensity and light flicker frequency.

[0081] Illustratively, the alarm module starts the audible and visual alarm signal immediately after receiving the alarm instruction sent by the processing module. According to the severity of the leakage and the risk level, different alarm modes are switched. For example, low-risk leakage may use a relatively gentle light flicker frequency and a relatively low alarm sound intensity, while high-risk leakage may trigger intense light flicker and high-decibel alarm sound. At the same time, the alarm module sends alarm information to the user terminal through wireless communication, such as GSM, 4G, etc. The information content includes the location of the leakage (if the system has positioning function), the severity of the leakage, the risk level, etc., reminding the user to take appropriate measures in time to protect personnel and property safety;

[0082] In summary, the alarm module quickly issues diversified audible and visual alarm signals and sends alarm information to the user terminal through wireless communication when the processing module determines that natural gas leakage has occurred or high leakage risk is predicted. The alarm signal mode can be flexibly switched according to the severity of the leakage and the risk level, and the alarm sound intensity and light flicker frequency can also be adjusted to adapt to different scene requirements, ensuring that the user can receive the alarm information in time and clearly, take appropriate measures in time, and reduce accident losses.

[0083] The power module:

[0084] The power module uses high-performance batteries to provide power support for the detection module, data transmission module, processing module, and alarm module.

[0085] The power module is integrated with an energy recovery unit for recovering energy to charge the battery during the movement of the device. The energy recovery unit adopts a vibration energy collection technology to collect energy generated by the vibration of the device movement and convert the energy into electrical energy to be stored in the battery.

[0086] Exemplarily, the high-performance battery in the power module provides initial power support for the detection module, the data transmission module, the processing module and the alarm module, ensuring that the detection system can be normally started and operated. During the movement of the device, the vibration energy collection technology of the energy recovery unit starts to play a role. The vibration sensor inside it senses the vibration generated by the movement of the device, and through a specific energy conversion device such as a piezoelectric material or an electromagnetic induction device, the vibration energy is converted into electrical energy. After rectification, voltage stabilization and other treatments, the converted electrical energy is stored in the high-performance battery to continuously power the system, prolong the working time of the system and improve the stability and reliability of the system in the mobile scenario.

[0087] User terminal interaction module:

[0088] The user terminal interaction module is used for the user to interact with the detection system through a mobile phone APP or a computer client, including real-time viewing of natural gas concentration data, alarm information and setting of parameters of the detection system.

[0089] In summary, the detection system of the present application adopts modular design as a whole, and the modules are connected through standardized interfaces, which is convenient for disassembly, assembly and replacement. The array type layout is adopted for the mid-infrared spectrum sensor in the detection module, the shell of the detection system is made of light and high-strength material, and a handle or a strap is designed for easy carrying, which is convenient for moving use in different scenarios. The user terminal interaction module supports the user to interact with the detection system through a mobile phone APP or a computer client, and the user can real-time view natural gas concentration data and alarm information, and also can set parameters of the detection system, which is simple and easy to operate, so that non-professionals can easily master the natural gas detection situation and realize the self-management of the safety of natural gas use.

[0090] In addition, it should be noted that the present application can be a system, a method and / or a computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions loaded thereon for causing a processor to implement various aspects of the present application.

[0091] Computer readable storage media can be tangible storage media which can retain and store instructions for use by an instruction execution device. Computer readable storage media can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer readable storage media include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0092] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0093] Computer readable program instructions for carrying out operations of the present application can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present application.

[0094] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0095] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, 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 / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or nonvolatile memory, or a suitable combination of the different types of computer readable storage media. The computer readable program instructions can also be downloaded to a computer, other programmable data processing apparatus, or other device from a computer readable storage medium or to an external computer or external storage device via a data signal that can be transmitted for example via a wired medium or a wireless medium such as the Internet or wireless media.

[0096] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0097] The flow diagrams and the block diagrams in the drawings are presented to illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams and the block diagrams can represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logic functions. In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and

[0098] Embodiments of the application have been described above, and the description is intended to be illustrative of the embodiments of the application and not exhaustive. Numerous modifications and adaptations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The scope of the application is defined by the appended claims.

Claims

1. A natural gas concentration safety detection system, characterized by, The system comprises a detection module, a data transmission module, a processing module, an alarm module, a power module and a user terminal interaction module. The detection module uses a mid-infrared spectrum sensor based on a quantum cascade laser to obtain natural gas concentration data in real time, and integrates an environmental parameter monitoring unit to obtain environmental parameter data in real time, and corrects the natural gas concentration data and the environmental parameter data through a self-adaptive environmental compensation algorithm. The data transmission module uses LoRa wireless communication technology to transmit the corrected natural gas concentration data and environmental parameter data to the processing module in real time. The processing module is built-in with big data analysis and machine learning algorithms, which are used to analyze and process the received corrected natural gas concentration data and environmental parameter data, identify natural gas concentration change patterns, determine whether natural gas leakage occurs and predict leakage risk, obtain analysis results, and control the alarm module according to the analysis results. The alarm module is used to issue an audible and visual alarm signal when the analysis results indicate that natural gas leakage occurs or high leakage risk is predicted, and send alarm information to the user terminal through wireless communication. The power module uses a high-efficiency battery to provide power support for the detection module, the data transmission module, the processing module and the alarm module, and simultaneously integrates an energy recovery unit to recover energy for charging the battery during device movement. The mid-infrared spectrum sensor in the detection module adopts an array layout to expand the detection range of a single sensor, and the shell of the mid-infrared spectrum sensor has corrosion resistance, dustproof and waterproof functions.

2. The natural gas concentration safety detection system of claim 1, wherein, The data transmission module uses an AES encryption algorithm to encrypt the transmitted corrected natural gas concentration data and environmental parameter data to ensure the security of data transmission.

3. The natural gas concentration safety detection system of claim 1, wherein, The processing module is also connected to a storage unit, which is used to store historical detection data and analysis results for subsequent query and optimization training of the machine learning algorithm.

4. The natural gas concentration safety detection system of claim 1, wherein, The audible and visual alarm signal issued by the alarm module has multiple alarm modes, which are switched according to the severity of natural gas leakage and the risk level, and the different alarm modes correspond to different alarm sound intensity and light flashing frequency.

5. The natural gas concentration safety detection system of claim 1, wherein, The energy recovery unit in the power module uses vibration energy harvesting technology to collect energy generated by device movement and convert it into electrical energy stored in the battery.

6. The natural gas concentration safety detection system of claim 1, wherein, The detection system further comprises:

7. The natural gas concentration safety detection system of claim 1, wherein, A user terminal interaction module for users to interact with the detection system through a mobile phone APP or computer client, including real-time viewing of natural gas concentration data, alarm information and setting of detection system parameters. The self-adaptive environmental compensation algorithm corrects the natural gas concentration data and environmental parameter data detection data through the following formula:

8. The natural gas concentration safety detection system of claim 1, wherein, Temperature compensation formula: Humidity compensation formula: C corrected-T = C measured × (1 + α T × (T - T0)) Wherein, C corrected-T is the temperature-compensated natural gas concentration value, in ppb, C measured is the original data of natural gas concentration directly measured by the mid-infrared spectrum sensor, in ppb, a T is the temperature compensation coefficient, T is the real-time monitored ambient temperature, in ℃, and T0 is the standard reference temperature, in ℃. Atmospheric pressure compensation formula: C corrected-H = C corrected-T × (1 - α H ) × (H - H0)) wherein C corrected-H is the natural gas concentration value after humidity compensation, in ppb, C corrected-T is the natural gas concentration value after temperature compensation, in ppb, a H is the humidity compensation coefficient, H is the real-time monitored ambient humidity, in %RH, and H0 is the standard reference humidity, in %RH.

9. The natural gas concentration safety detection system according to claim 1, characterized in that, Wherein, C corrected-P is the final natural gas concentration value after air pressure compensation, unit: ppb; C corrected-H is the natural gas concentration value after humidity compensation, unit: ppb, P0 is the standard reference air pressure, unit: kPa; P is the real-time monitored environmental air pressure, unit: kPa. ​ The machine learning algorithm comprises a support vector machine-based leakage identification algorithm and an ARIMA-based leakage risk prediction algorithm; The support vector machine-based leakage identification algorithm determines the class to which input data x belongs in a linearly separable case through a decision function as follows: f(x) = sign(ω T x + b) wherein f(x) is an output value of the decision function, x is an input feature vector comprising an environment-compensated natural gas concentration value, real-time environment temperature, humidity, and air pressure, ω is a weight vector, and b is a bias term; The support vector machine-based leakage identification algorithm determines the class to which x belongs in a non-linearly separable case through a decision function as follows: Where, α i For Lagrange multipliers, y i For training sample x i Category labels, K(x) i The kernel function is K(x), and the radial basis function is used. i x)=exp(-γ||xx) i || 2 ), where n is the number of training samples; The ARIMA-based leakage risk prediction algorithm predicts future natural gas concentrations through a formula as follows: where y t is the natural gas concentration observation at time t, in ppb, μ is the mean of the time series, p is the order of the autoregressive term, is the autoregressive coefficient, q is the order of the moving average term, θ j is the moving average coefficient, ∈ t is the white noise error term at time t.

10. The natural gas concentration safety detection system of claim 9, wherein, The support vector machine-based leakage identification algorithm optimizes the weight vector and the bias term through a gradient descent method, and the ARIMA-based leakage risk prediction algorithm estimates the autoregressive coefficient and the moving average coefficient through a least square method.

Images