Gas detection system and method, electronic equipment and medium

Abstract

The invention provides a gas detection system and method, electronic equipment and a medium. The gas detection system comprises a sensor module and a data processing module. The sensor module comprises a sensor array and is used for detecting different gases in the environment and generating different detection signals; the data processing module is used for converting different detection signals into different digital signals; performing feature extraction and fusion on different digital signals by adopting a neural network model to obtain data features corresponding to each digital signal; identifying types and concentrations of different gases in the environment according to the data features; wherein the sensor array comprises MEMS sensors, an optical sensor, a temperature and humidity sensor and an air pressure sensor, and the number of the MEMS sensors is m * n. The system is used for providing a sensor array integrating various sensors, and feature extraction and intelligent processing are carried out on signals recognized by the sensor array through an artificial intelligence algorithm so as to improve the accuracy of measurement results.

Description

Technical Field

[0001] The present invention relates to the field of gas monitoring technology, and in particular to a gas detection system, method, electronic equipment and medium. Background Art

[0002] The changes in the air environment of conventional closed working environments present three characteristics: high mixing, complex composition, and local enrichment. In special closed working environments, a variety of toxic and harmful gases are released due to cooking, human breathing and metabolism, equipment operation, and material oxidation and aging, which constitute internal air pollution, thus affecting the air quality of the environment and the operating capacity of the equipment. Therefore, monitoring the air composition and air quality of closed working environments plays an important role in my country's work safety.

[0003] At present, spectral detection technology is widely used in the monitoring of water quality, air and soil in the field of environment in my country, especially for the detection of industrial pollutant gas concentration. This measurement method is not only fast and simple, but also has relatively accurate detection results. However, in actual applications, the gas discharged from the closed working environment contains not only the known pollutant gases that need to be measured, but also many unknown gases, which causes the overlap of absorption spectra and serious cross-interference, greatly affecting the accuracy of the measurement system.

[0004] Therefore, in order to solve the above problems, the present invention provides a sensor array that integrates various sensors, and uses artificial intelligence algorithms to extract features and intelligently process signals recognized by the sensor array to improve the accuracy of the above measurement results. Summary of the invention

[0005] The purpose of the present invention is to provide a gas detection system, method, electronic device and medium, which are used to provide a sensor array that integrates various sensors, and to extract features and intelligently process signals recognized by the sensor array through artificial intelligence algorithms to improve the accuracy of the above-mentioned measurement results.

[0006] In a first aspect, an embodiment of the present invention provides a gas detection system, including a sensor module and a data processing module.

[0007] The sensor module includes a sensor array for detecting different gases in the environment and generating different detection signals;

[0008] A data processing module, used to convert the different detection signals into different digital signals; use a neural network model to extract and fuse the different digital signals to obtain data features corresponding to each digital signal; and identify the types and concentrations of different gases in the environment according to the data features;

[0009] The sensor array includes MEMS sensors, optical sensors, temperature and humidity sensors, and air pressure sensors, wherein there are m×n MEMS sensors, m represents the number of MEMS sensors along the longitudinal direction of the sensor array, n represents the number of MEMS sensors along the transverse direction of the sensor array, and m and n are integers.

[0010] In a possible implementation, the data processing module is specifically used to: apply an autoencoder to perform data noise reduction and feature compression on the digital signal to obtain an intermediate digital signal;

[0011] Performing feature extraction and data processing on the intermediate digital signal to obtain a feature vector;

[0012] Gas classification is performed using a support vector machine in the neural network model, wherein the support vector machine includes u layers of fully connected layers connected in sequence, wherein the feature vector inputted by each layer is multiplied by a randomized weight matrix as the input of the next layer, and the last layer outputs the prediction result of the gas type;

[0013] The long short-term memory neural network in the neural network model is used for gas processing and concentration prediction. The long short-term memory neural network includes v layers of fully connected layers connected in sequence, and the last layer outputs the trend of gas concentration changes. u and v are positive integers.

[0014] In a possible implementation, the data processing module is further used to: apply an isolation forest or an autoencoder to perform anomaly detection on the gas concentration change trend to identify and mark abnormal data points.

[0015] In one possible implementation, the neural network model is deployed on a cloud platform, using cloud computing resources to perform large-scale data processing and model training.

[0016] In a possible implementation, the sensor module also includes a power interface, a memory, a communication interface and an alarm, wherein the power interface is used to connect the power; the memory is used to store the detection signal; the communication interface is used to realize communication transmission with the data processing module; and the alarm is used to sound an alarm when the sensor module operates abnormally.

[0017] In a second aspect, an embodiment of the present invention further provides a gas monitoring method, comprising: detecting different gases in an environment and generating different detection signals;

[0018] Convert the different detection signals into different digital signals; use a neural network model to extract and fuse the different digital signals to obtain data features corresponding to each digital signal; and identify the types and concentrations of different gases in the environment according to the data features;

[0019] The sensor array includes MEMS sensors, optical sensors, temperature and humidity sensors, and air pressure sensors, wherein there are m×n MEMS sensors, m represents the number of MEMS sensors along the longitudinal direction of the sensor array, n represents the number of MEMS sensors along the transverse direction of the sensor array, and m and n are integers.

[0020] In a possible embodiment, a neural network model is used to extract and fuse features of the different digital signals to obtain data features corresponding to each digital signal; and the types and concentrations of different gases in the environment are identified according to the data features, including:

[0021] Applying an autoencoder to perform data noise reduction and feature compression on the digital signal to obtain an intermediate digital signal;

[0022] Performing feature extraction and data processing on the intermediate digital signal to obtain a feature vector;

[0023] Gas classification is performed using a support vector machine in the neural network model, wherein the support vector machine includes u layers of fully connected layers connected in sequence, wherein the feature vector inputted by each layer is multiplied by a randomized weight matrix as the input of the next layer, and the last layer outputs the prediction result of the gas type;

[0024] The long short-term memory neural network in the neural network model is used for gas processing and concentration prediction. The long short-term memory neural network includes v layers of fully connected layers connected in sequence, and the last layer outputs the trend of gas concentration changes. u and v are positive integers.

[0025] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a program that can be run on the processor, and when the program is executed by the processor, the electronic device implements a method in any possible embodiment of the first aspect.

[0026] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a program, and when the program runs on an electronic device, the electronic device executes a method in any possible implementation of the first aspect.

[0027] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute a method of any possible implementation of the first aspect.

[0028] The present invention provides a gas detection system, device, equipment and medium. The beneficial effects of the technical solution are mainly reflected in the following aspects:

[0029] 1. High accuracy: By integrating a sensor array of multiple sensors, it is able to detect multiple gases in the environment, and perform feature extraction and intelligent processing of the detected signals through artificial intelligence algorithms, thereby improving the accuracy of gas monitoring.

[0030] 2. Real-time monitoring: The sensor array can monitor gas changes in the environment in real time, generate detection signals in a timely manner, and provide real-time data support for environmental safety.

[0031] 3. Data denoising and feature compression: Use autoencoders to perform data denoising and feature compression on digital signals to improve the efficiency and accuracy of data processing.

[0032] 4. Intelligent gas classification and concentration prediction: Use the support vector machine in the neural network model to classify gases, and use the long short-term memory neural network to predict gas concentration, so as to accurately identify gas types and accurately predict concentrations.

[0033] 5. Anomaly detection: Using isolation forests or autoencoders to detect anomalies in gas concentration trends can identify and mark abnormal data points, enhancing the safety and reliability of the system.

[0034] 6. Cloud platform support: The neural network model is deployed on the cloud platform, using cloud computing resources for large-scale data processing and model training, improving processing capabilities and reducing the computing burden of local devices.

[0035] 7. System integration: The sensor module integrates power interface, memory, communication interface and alarm, making the whole system more complete and easy to operate. At the same time, it can alarm in time when the sensor module works abnormally.

[0036] 8. Easy to expand and maintain: Due to the modular design, the system is easy to expand new sensor types and algorithms, and is easy to maintain and upgrade.

[0037] 9. Wide range of application scenarios: The gas detection system of the present invention is suitable for a variety of environments, such as industrial production, environmental monitoring, public safety and other fields, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 A schematic diagram of the composition structure of a gas detection system provided by an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of the structure of a sensor module provided by an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of a gas monitoring method provided by an embodiment of the present invention;

[0042] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In the description of the embodiments of the present invention, the terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to be used as limitations of the present invention. As used in the specification of the present invention and the appended claims, the singular expressions "a", "said", "above", "the" and "this" are intended to also include expressions such as "one or more", unless there is a clear contrary indication in the context. It should also be understood that in the following embodiments of the present invention, "at least one", "one or more" refer to one or more (including two). The term "and / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist; for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0044] References to "one embodiment" or "some embodiments" etc. described in this specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "include", "including", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways. The term "connection" includes direct connection and indirect connection, unless otherwise specified. "First" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated.

[0045] In the embodiments of the present invention, the words "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or implementation scheme described as "exemplarily" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or implementation schemes. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0046] Figure 1 This is a schematic diagram of the composition structure of a gas detection system provided by an embodiment of the present invention, which mainly includes: a sensor module 01 and a data processing module 02. Among them:

[0047] The sensor module 01 includes a sensor array for detecting different gases in the environment and generating different detection signals. Figure 2 As shown, the sensor array includes MEMS sensors, optical sensors, temperature and humidity sensors, and air pressure sensors, wherein there are m×n MEMS sensors, m represents the number of MEMS sensors in the longitudinal direction of the sensor array, n represents the number of MEMS sensors in the transverse direction of the sensor array, and m and n are integers. It should be understood that different gases in the environment mainly include life gases (such as oxygen, carbon dioxide, carbon monoxide, hydrogen, etc.), toxic gases (such as formaldehyde, acetone, chlorinated hydrocarbons, fluorinated hydrocarbons, etc.) and odorous gases.

[0048] The data processing module 02 is used to convert the different detection signals into different digital signals; use a neural network model to extract and fuse the features of the different digital signals to obtain data features corresponding to each digital signal; and identify the types and concentrations of different gases in the environment based on the data features.

[0049] It should be understood that a micro-electro-mechanical system (MEMS) is a micro device that integrates micro sensors, actuators, electronic circuits, and mechanical structures. These MEMS sensors are usually very small and can work on a scale of micrometers (millionths of a meter) or even nanometers (billionths of a meter). MEMS technology is widely used in many fields such as automobiles, medical treatment, and consumer electronics, and is used to manufacture various precision sensors and micro-mechanical devices. In this embodiment, in order to enhance the system's ability to detect specific gases, optical sensors and specific electrochemical sensors are also integrated to supplement the functions of MEMS sensors. Optical sensors use optical principles to detect gas components, and electrochemistry uses current signals combined with MEMS sensors to improve the system's detection accuracy for specific gases. In addition, the integration of temperature and humidity sensors and air pressure sensors is crucial for monitoring environmental parameters. These sensors can monitor changes in ambient temperature, humidity, and air pressure, and play an important role in adjusting the working state of the sensor and improving the measurement accuracy of the entire system. The basic circuit board of the above-mentioned sensor module 01 can be designed in four layers, with the top and bottom layers being signal layers, and the middle two layers being ground and power layers, respectively. This design helps reduce signal interference and improves signal integrity, thereby ensuring accurate collection of sensor data.

[0050] Optionally, for different types of sensors, this embodiment can also design dedicated sensor circuit boards. These circuit boards provide power management and signal conditioning circuits to ensure accurate collection of sensor data and provide a reliable basis for subsequent data transmission and processing.

[0051] Optionally, the sensor module 01 is also equipped with a plurality of other components to ensure its normal operation and data processing. Figure 2 As shown, the module includes a power interface, whose main function is to connect an external power source to provide the required power support for the sensor module. In addition, the module also has a built-in memory for saving and recording various signal data detected from the sensor. These data can be stored in the memory for further analysis and processing when necessary.

[0052] In order to realize data exchange with external devices, the sensor module 01 is also equipped with a communication interface. This interface can be wireless, such as Bluetooth or Wi-Fi, or wired, such as an Ethernet interface. Through this communication interface, the sensor module can transmit the detected data to the data processing module, or receive instructions and configuration information from the data processing module. This communication mechanism ensures the real-time transmission and processing of data, and improves the flexibility and response speed of the system. Data transmission can be carried out through the Ethernet port using the User Datagram Protocol (UDP). The UDP protocol is suitable for real-time data transmission, reduces delays and improves transmission efficiency, which is crucial for the real-time performance and response speed of the environmental gas detection system. To ensure the security and reliability of data, this embodiment can also transmit data through an internal network. The design of this internal network not only improves the security of data transmission, but also enhances the anti-interference ability of the system, ensuring the integrity and reliability of data during transmission.

[0053] Finally, the sensor module 01 is also equipped with an alarm, the main purpose of which is to sound an alarm when the sensor in the sensor module fails due to poisoning or the gas exceeds the standard. The alarm can notify the user or maintenance personnel through sound, light signal or other forms of prompts, so that timely measures can be taken to troubleshoot and repair the fault. This can ensure that the sensor module can work normally at critical moments and avoid data loss or false alarms caused by equipment failure.

[0054] In summary, the sensor module 01 ensures stable operation and data processing capabilities in various environments through the coordinated work of the power interface, memory, communication interface and alarm. The addition of these components not only improves the performance of the sensor module, but also enhances its reliability and user experience in practical applications.

[0055] Based on the above system, this embodiment provides a gas monitoring method, such as Figure 3 As shown, the method mainly includes the following steps:

[0056] S301, detecting different gases in the environment and generating different detection signals;

[0057] S302, converting the different detection signals into different digital signals; using a neural network model to extract and fuse the features of the different digital signals to obtain data features corresponding to each digital signal; and identifying the types and concentrations of different gases in the environment according to the data features.

[0058] In a feasible implementation scheme, the above S302 specifically includes: applying an autoencoder to perform data noise reduction and feature compression on the digital signal to obtain an intermediate digital signal, and exemplarily using an advanced electrical signal filtering algorithm to improve the signal-to-noise ratio of the sensor signal. The algorithm can effectively extract the information of each component in the mixture from the overlapping signals of a single gas sensor without pre-separation, and simply and quickly completes the detection of the mixture components. Afterwards, feature extraction and data processing are performed on the intermediate digital signal to obtain a feature vector. Exemplarily, a feature selection algorithm, such as principal component analysis (PCA) or recursive feature elimination (RFE), is used to identify the feature variables that have the greatest impact on the identification of chemical reaction paths. Using machine learning algorithms, such as random forests, support vector machines (SVMs) or artificial neural networks (ANNs), model training is performed on the selected features to identify different chemical reaction paths. Finally, the support vector machine in the neural network model is used for gas classification. The support vector machine includes u layers of fully connected layers connected in sequence. The feature vectors input in each layer are multiplied by the randomized weight matrix as the input of the next layer. The last layer outputs the prediction result of the gas type. The long short-term memory neural network in the neural network model is used for gas processing and concentration prediction. The long short-term memory neural network includes v layers of fully connected layers connected in sequence. The last layer outputs the trend of gas concentration changes. u and v are positive integers. In addition, isolation forests or autoencoders can also be used to detect anomalies in the trend of gas concentration changes to identify and mark abnormal data points.

[0059] In another feasible implementation, when processing sensor data, this embodiment can also use a (Gated Recurrent Unit, GRU) neural network machine learning method. GRU is a variant of a recurrent neural network (RNN) and is particularly suitable for processing time series data. Through the GRU model, the system can learn the time dependency of sensor data, thereby more accurately identifying and predicting gas components.

[0060] The neural network model mentioned above can be deployed not only on local computer devices, but also on cloud servers. In this way, the powerful computing power and storage capacity of cloud computing resources can be fully utilized to carry out large-scale data processing and model training. In this way, not only can the efficiency of data processing and model training be improved, but also the burden on local hardware devices can be reduced, making the entire system more flexible and scalable. In addition, by deploying neural network models on cloud platforms, cross-device and cross-platform collaboration can be achieved, further improving the availability and flexibility of the model.

[0061] All relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.

[0062] Next, an electronic device provided by an embodiment of the present application is introduced. Figure 4 , Figure 4 A schematic diagram of a structure of an electronic device provided in an embodiment of the present application, wherein the electronic device 400 implements Figure 1 Functions of the corresponding method embodiments. Specifically, the electronic device 400 includes: a receiver 401, a transmitter 402, a processor 403 and a memory 404 (wherein the number of processors 403 in the electronic device 400 can be one or more), wherein the processor 403 may include an application processor 4031 and a communication processor 4032. In some embodiments of the present application, the receiver 401, the transmitter 402, the processor 403 and the memory 404 may be connected via a bus or other means.

[0063] The memory 404 may include a read-only memory and a random access memory, and provides instructions and data to the processor 403. A portion of the memory 404 may also include a non-volatile random access memory (NVRAM). The memory 404 stores processor and operation instructions, executable modules or data structures, or subsets thereof, or extended sets thereof, wherein the operation instructions may include various operation instructions for implementing various operations.

[0064] The processor 403 controls the operation of the electronic device. In a specific application, the various components of the electronic device are coupled together through a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus, and a status signal bus, etc. However, for the sake of clarity, various buses are referred to as bus systems in the figure.

[0065] The method disclosed in the above embodiment of the present application can be applied to the processor 403, or implemented by the processor 403. The processor 403 can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware or software instructions in the processor 403. The above processor 403 can be a general-purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor or a microcontroller, and a vision processor (vision processing unit, VPU), a tensor processor (tensorprocessing unit, TPU) and other processors suitable for AI computing, and can further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The processor 403 can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 404, and the processor 403 reads the information in the memory 404, and completes the steps in the above method embodiment in combination with its hardware.

[0066] The receiver 401 can be used to receive input digital or character information and generate signal input related to the relevant settings and function control of the electronic device. The transmitter 402 can be used to output digital or character information through the first interface; the transmitter 402 can also be used to send instructions to the disk group through the first interface to modify the data in the disk group; the transmitter 402 can also include a display device such as a display screen.

[0067] A computer program product is also provided in an embodiment of the present application. When the computer program product is run on a computer, the computer executes the steps executed by the aforementioned device, or the computer executes the steps executed by the aforementioned device.

[0068] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a program for performing signal processing. When the program is run on a computer, the computer executes the steps executed by the aforementioned device, or the computer executes the steps executed by the aforementioned device.

[0069] The execution device, training device or electronic device provided in the embodiments of the present application may specifically be a chip, and the chip includes: a processing unit and a communication unit, wherein the processing unit may be, for example, a processor, and the communication unit may be, for example, an input / output interface, a pin or a circuit, etc. The processing unit may execute the computer execution instructions stored in the storage unit so that the chip in the execution device executes the data processing method described in the above embodiment, or so that the chip in the training device executes the data processing method described in the above embodiment. Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc. The storage unit may also be a storage unit located outside the chip in the wireless access device, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), etc.

[0070] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0071] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0072] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0073] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A gas detection system, characterized in that: The system comprises: The sensor module includes a sensor array for detecting different gases in the environment and generating different detection signals; A data processing module, used to convert the different detection signals into different digital signals; use a neural network model to extract and fuse the different digital signals to obtain data features corresponding to each digital signal; and identify the types and concentrations of different gases in the environment according to the data features; The sensor array includes MEMS sensors, optical sensors, temperature and humidity sensors, and air pressure sensors, wherein there are m×n MEMS sensors, m represents the number of MEMS sensors along the longitudinal direction of the sensor array, n represents the number of MEMS sensors along the transverse direction of the sensor array, and m and n are integers.

2. The system according to claim 1, characterized in that The data processing module is specifically used for: Applying an autoencoder to perform data noise reduction and feature compression on the digital signal to obtain an intermediate digital signal; Performing feature extraction and data processing on the intermediate digital signal to obtain a feature vector; Gas classification is performed using a support vector machine in the neural network model, wherein the support vector machine includes u layers of fully connected layers connected in sequence, wherein the feature vector inputted by each layer is multiplied by a randomized weight matrix as the input of the next layer, and the last layer outputs the prediction result of the gas type; The long short-term memory neural network in the neural network model is used for gas processing and concentration prediction. The long short-term memory neural network includes v layers of fully connected layers connected in sequence, and the last layer outputs the trend of gas concentration changes. u and v are positive integers.

3. The system according to claim 2, characterized in that The data processing module is also used to: apply isolation forest or autoencoder to perform anomaly detection on the gas concentration change trend to identify and mark abnormal data points.

4. The system according to any one of claims 1 to 3, characterized in that: The neural network model is deployed on a cloud platform, using cloud computing resources to perform large-scale data processing and model training.

5. The system according to any one of claims 1 to 3, characterized in that: The sensor module also includes a power interface, a memory, a communication interface and an alarm, wherein the power interface is used to connect the power supply; the memory is used to store the detection signal; the communication interface is used to realize communication transmission with the data processing module; and the alarm is used to sound an alarm when the sensor module is working abnormally.

6. A gas monitoring method, characterized in that: include: Detect different gases in the environment and generate different detection signals; Convert the different detection signals into different digital signals; use a neural network model to extract and fuse the different digital signals to obtain data features corresponding to each digital signal; and identify the types and concentrations of different gases in the environment according to the data features; The sensor array includes MEMS sensors, optical sensors, temperature and humidity sensors, and air pressure sensors, wherein there are m×n MEMS sensors, m represents the number of MEMS sensors along the longitudinal direction of the sensor array, n represents the number of MEMS sensors along the transverse direction of the sensor array, and m and n are integers.

7. The method according to claim 6, characterized in that A neural network model is used to extract and fuse the features of the different digital signals to obtain data features corresponding to each digital signal; and the types and concentrations of different gases in the environment are identified according to the data features, including: Applying an autoencoder to perform data noise reduction and feature compression on the digital signal to obtain an intermediate digital signal; Performing feature extraction and data processing on the intermediate digital signal to obtain a feature vector; Gas classification is performed using a support vector machine in the neural network model, wherein the support vector machine includes u layers of fully connected layers connected in sequence, wherein the feature vector inputted by each layer is multiplied by a randomized weight matrix as the input of the next layer, and the last layer outputs the prediction result of the gas type; The long short-term memory neural network in the neural network model is used for gas processing and concentration prediction. The long short-term memory neural network includes v layers of fully connected layers connected in sequence, and the last layer outputs the trend of gas concentration changes. u and v are positive integers.

8. An electronic device, characterized in that: include: At least one memory, at least one processor, the at least one processor is used to execute instructions stored in the at least one memory, so that the electronic device performs the method as described in any one of claims 6 or 7.

9. A computer-readable storage medium, wherein a program is stored in the computer-readable storage medium, characterized in that: When the program is executed by a processor, the method according to any one of claims 6 or 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to claim 6 or 7 is implemented.

Images