Mixed gas identification method and system based on gas sensor array

Abstract

The invention belongs to the technical field of intelligent gas detection, and provides a mixed gas identification method and system based on a gas sensor array, and the method and system reduce the influence of an interference signal through the anti-interference processing of an initial voltage signal, and improve the gas identification accuracy. According to the method, feature extraction is carried out on the initial voltage signals of the gas sensors to obtain feature data, and a target dimension reduction algorithm is used for carrying out dimension reduction on the feature data, so that the calculated amount of the method is remarkably reduced while the feature information of the initial voltage signals is reserved; and the mixed gas is identified by matching the KNN algorithm with the dimensionality-reduced target feature data, so that the data demand and the calculation amount are further reduced, and meanwhile, the accurate identification of the mixed gas is realized.

Description

Technical Field

[0001] The present application belongs to the field of gas intelligent detection technology, and more specifically, relates to a mixed gas identification method and system based on a gas sensor array. Background Art

[0002] With the rapid development of new energy vehicles, energy storage power stations, and other fields, thermal runaway of lithium batteries has become a major concern. In the early stages of thermal runaway, lithium batteries produce a series of gases, including H2, CO, and various volatile organic compounds. Rapidly identifying the composition and concentration of these gases can effectively reduce accidents caused by thermal runaway.

[0003] Because thermal runaway requires detection, a sensor array composed of multiple gas sensors is used for gas detection. While this can yield more accurate gas data, the problem of cross-interference between gases when measuring a mixture of multiple gases persists, reducing gas identification accuracy. Furthermore, existing gas sensor array-based identification methods that can address cross-interference often require large amounts of data, are computationally intensive, and are difficult to deploy on low-computing-power devices. Summary of the Invention

[0004] In response to the above-mentioned defects in the prior art, the present application provides a mixed gas identification method and system based on a gas sensor array, aiming to solve the problems of low accuracy in mixed gas identification and high computing power consumption in the existing methods.

[0005] In a first aspect, the present application provides a mixed gas identification method based on a gas sensor array, comprising: Obtaining the initial voltage signal corresponding to each gas sensor, and performing anti-interference processing on the initial voltage signal to obtain the target voltage signal; Performing feature extraction processing on each target voltage signal to obtain feature data corresponding to the target voltage signal, the feature data including response integral feature, response amplitude feature, response speed feature, and response stability feature corresponding to each target voltage signal; Based on the target dimensionality reduction algorithm, each feature data is subjected to dimensionality reduction processing to obtain the target feature data corresponding to each feature data; Based on the target gas recognition algorithm, the characteristic data of each target is recognized and processed to obtain the recognition result of the gas sensor array.

[0006] Furthermore, the initial voltage signal is subjected to anti-interference processing to obtain a target voltage signal, including: Amplifying the initial voltage signal; Performing impedance matching on the amplified initial voltage signal, and obtaining a voltage bias signal corresponding to the initial voltage signal based on the impedance matching result; The initial voltage signal is adjusted based on the voltage bias signal to obtain a target voltage signal, and the target voltage signal is amplified.

[0007] Because the gas sensor arrays used to measure lithium batteries utilize weak current, the initial voltage signal must be amplified using a low-noise, high-input impedance operational amplifier before processing. Since the deployment of gas sensor arrays often involves a large number of electronic circuits for signal processing, which introduces significant interference from factors such as impedance and ambient temperature, the initial voltage signal must be impedance-matched to generate a voltage bias signal, which is then used to adjust the initial voltage signal. However, the impedance matching process causes a certain amount of attenuation in the voltage signal, necessitating further amplification to obtain an easily measurable initial voltage signal.

[0008] Furthermore, feature extraction processing is performed on each target voltage signal, including: Performing a moving smoothing process on the target voltage signal, and obtaining a response amplitude characteristic corresponding to the target voltage signal based on the moving smoothing process result; The target voltage signal after the motion smoothing process is subjected to extreme value normalization processing, and based on the extreme value normalization processing result, the response integral characteristic, response speed characteristic and response stability characteristic corresponding to the target voltage signal are obtained.

[0009] The purpose of feature extraction processing on the target voltage signal is to enable accurate quantitative analysis of the target voltage signal, rather than simply summarizing the single calculation results of several groups of gas sensors, which is conducive to reducing cross-interference between gases when measuring mixed gases.

[0010] Furthermore, based on the target dimensionality reduction algorithm, each feature data is subjected to dimensionality reduction processing to obtain target feature data corresponding to each feature data, including: Based on the characteristic data corresponding to each gas sensor, an initial characteristic vector corresponding to each characteristic data is obtained, and an initial characteristic matrix is ​​established based on each initial characteristic vector; The initial feature matrix is ​​reduced in dimension based on a target dimensionality reduction algorithm to obtain a target feature matrix, and target feature data corresponding to each gas sensor is obtained based on the target feature matrix. The target feature data includes a target feature vector corresponding to the gas sensor.

[0011] Furthermore, the initial feature matrix is ​​subjected to dimensionality reduction processing based on the target dimensionality reduction algorithm, including: Calculate the class mean vector and global mean vector of the initial feature matrix; Based on the class mean vector and the global mean vector, an inter-class scatter matrix is ​​established, and based on the class mean vector, an intra-class scatter matrix is ​​established; Based on the inter-class scatter matrix and the intra-class scatter matrix, the generalized characteristic equation corresponding to the initial characteristic matrix is ​​solved, and the projection direction of the initial characteristic matrix is ​​determined based on the solution; A projection matrix corresponding to the initial feature matrix is ​​established, and based on the projection matrix and projection direction, the dimension of the initial feature matrix is ​​compressed to the same dimension as the projection matrix to obtain the target feature matrix.

[0012] Furthermore, the target characteristic data is identified and processed based on the target gas identification algorithm, including: Inputting target characteristic data into a gas sample database, the gas sample database including prediction characteristic vectors of multiple groups of gases, and the target characteristic data including target characteristic vectors of each gas sensor; The Euclidean distance between each target vector and the prediction feature vector is calculated, and based on the Euclidean distance calculation result, the gas type corresponding to each target vector is determined.

[0013] The target gas identification algorithm used in this embodiment is the KNN (K-Nearest Neighbors) algorithm. Since the target feature matrix of the reduced target feature data is relatively simple, and KNN is a typical lazy learning algorithm that only stores raw data during the training phase and does not involve model parameter optimization or complex mathematical derivation, using a non-deep learning algorithm like the KNN algorithm significantly reduces the computational complexity of the method in this embodiment while also accurately matching the reduced target feature matrix to accurately identify mixed gases.

[0014] Furthermore, the target dimensionality reduction algorithm is the LDA (Linear Discriminant Analysis) algorithm.

[0015] Among them, the purpose of the target dimensionality reduction algorithm to reduce the dimensionality of the initial feature matrix is ​​to retain the feature information of the initial feature matrix while reducing the dimension of the initial feature matrix to reduce the amount of calculation, which is conducive to the target gas identification algorithm to quickly identify each target feature data, thereby facilitating the deployment of the method of this embodiment on a low-power microprocessor.

[0016] In a second aspect, the present application further provides a mixed gas identification system based on a gas sensor array, for implementing any method of the first aspect, including: The signal receiving module is used to obtain the initial voltage signal corresponding to each gas sensor and perform anti-interference processing on the initial voltage signal to obtain the target voltage signal; A data extraction module is used to perform feature extraction processing on each target voltage signal to obtain feature data corresponding to the target voltage signal; The data dimension reduction module is used to perform dimension reduction processing on each feature data to obtain the target feature data corresponding to each feature data; The recognition module is used to identify and process the characteristic data of each target to obtain the recognition result of the gas sensor array; The display module is used to display the target voltage signal, target characteristic data and the recognition result of the gas sensor array.

[0017] In a third aspect, the present application also provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the programs stored in the memory are executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.

[0018] In a fourth aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0019] In general, the above technical solutions conceived by the present invention have the following beneficial effects compared with the prior art: the present application provides a mixed gas identification method and system based on a gas sensor array, which obtains feature data by extracting features from the initial voltage signals of each gas sensor, and uses a target dimensionality reduction algorithm to reduce the dimension of the feature data, thereby retaining the feature information of the initial voltage signal while effectively reducing the computational complexity of the method of the present application; the mixed gas is identified by using the KNN algorithm in combination with the target feature data after dimensionality reduction, and the low computational complexity of KNN itself can be used to further reduce the data requirement and computational complexity; by extracting features from the initial voltage signal, reducing the dimension of the feature data and combining it with the KNN algorithm, while accurately identifying the mixed gas, the computing power required for identifying the mixed gas can be significantly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in this application or related technologies, the following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 This is a flow chart of a mixed gas identification method based on a gas sensor array provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a mixed gas identification system based on a gas sensor array provided in an embodiment of the present application; Figure 3 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0023] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application. Different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, even though the embodiment may not be clearly described in the following text.

[0024] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the elements described without departing from the scope of the present application. Various examples may appropriately omit, replace, or add various processes or components. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted, or combined. In addition, features described in some examples may be combined in other examples.

[0025] Figure 1 is a flow chart of a mixed gas identification method based on a gas sensor array provided in an embodiment of the present application, such as Figure 1 As shown, the method comprises at least the following steps: S1. Obtain the initial voltage signal corresponding to each gas sensor, and perform anti-interference processing on the initial voltage signal to obtain the target voltage signal.

[0026] In the embodiments of the present application, the method of this embodiment is intended to achieve accurate and rapid analysis of multi-component mixed gases in complex environments while reducing the latency, cost, and security risks associated with cloud-based processing or deep learning networks. The method may be executed by an MCU (Microcontroller Unit) integrated with an onboard power supply or a fixed power supply.

[0027] Most existing gas sensors rely on the resistance changes of composite sensitive materials in different gas environments. For example, MXene / NiO (two-dimensional carbon nitride / nickel oxide) composite sensitive materials have good response characteristics and response recovery performance to hydrogen, and multiferroic materials of different polarities, such as BiFeO3, have different adsorption properties for different gases such as H2, CH4, and CO. Therefore, the characteristics of the gas being measured by the gas sensor can be accurately obtained by the changes in the voltage signal.

[0028] In one possible implementation, performing anti-interference processing on the initial voltage signal to obtain the target voltage signal includes: Amplifying the initial voltage signal; Performing impedance matching on the amplified initial voltage signal, and obtaining a voltage bias signal corresponding to the initial voltage signal based on the impedance matching result; The initial voltage signal is adjusted based on the voltage bias signal to obtain a target voltage signal, and the target voltage signal is amplified.

[0029] In the embodiments of the present application, the method of this embodiment is applicable to weak-current circuits. Due to the presence of various impedance-carrying components, the initial voltage signal needs to be appropriately amplified using a low-noise, high-input impedance operational amplifier. To achieve impedance matching and obtain a voltage bias signal, a voltage follower circuit can be used to follow the initial voltage signal, thereby obtaining impedance data and a voltage bias signal corresponding to the impedance data. The corresponding amplifier circuit can then be used to appropriately adjust the initial voltage signal according to the voltage bias signal. This approach effectively eliminates interference caused by gas sensor baseline drift and ambient temperature, improving the method's anti-interference capability and gas identification accuracy.

[0030] S2. Perform feature extraction processing on each target voltage signal to obtain feature data corresponding to the target voltage signal, where the feature data includes response integral feature, response amplitude feature, response speed feature, and response stability feature corresponding to each target voltage signal.

[0031] In the embodiment of the present application, the purpose of feature extraction processing on the target voltage signal is to enable accurate quantitative analysis of the target voltage signal, and the response integral feature, response amplitude feature, response speed feature and response stability feature in the feature data can reflect the characteristic differences of the target voltage signal.

[0032] In one possible implementation, performing feature extraction processing on each target voltage signal includes: Performing a moving smoothing process on the voltage value of the target voltage signal, and obtaining a response amplitude characteristic corresponding to the target voltage signal based on the moving smoothing process result; The target voltage signal after the motion smoothing process is subjected to extreme value normalization processing, and based on the extreme value normalization processing result, the response integral characteristic, response speed characteristic and response stability characteristic corresponding to the target voltage signal are obtained.

[0033] In the embodiment of the present application, the response speed characteristics include the maximum response speed characteristics and the minimum response speed characteristics. The calculation formulas for the response amplitude characteristics, the response integral characteristics, the response speed characteristics, and the response stability characteristics are as follows:

[0034] Among them, F1 and A represent the response integral characteristics, F2 and S represent the response amplitude characteristics, F3 represents the maximum response speed characteristics, F4 represents the minimum response speed characteristics, and F5 represents the response stability characteristics.

[0035] Indicates the j The normalized signal of a sensor at time t is j Indicates the j sensors, represents the mean value during the response period, Indicates the j The global minimum value of the target voltage signal corresponding to each sensor, Indicates the j The global minimum value of the target voltage signal corresponding to each sensor.

[0036] S3. Perform dimensionality reduction processing on each feature data based on the target dimensionality reduction algorithm to obtain target feature data corresponding to each feature data.

[0037] In the embodiment of the present application, since this method needs to be deployed on a microprocessor with low power consumption and low computing power, it is necessary to reduce the parameters required for calculation as much as possible. The method of dimensionality reduction of feature data can retain the feature information of the initial feature matrix while reducing the dimension of the initial feature matrix to reduce the amount of calculation.

[0038] In one possible implementation, each feature data is subjected to dimensionality reduction processing based on a target dimensionality reduction algorithm to obtain target feature data corresponding to each feature data, including: Based on the characteristic data corresponding to each gas sensor, an initial characteristic vector corresponding to each characteristic data is obtained, and an initial characteristic matrix is ​​established based on each initial characteristic vector; The initial feature matrix is ​​reduced in dimension based on a target dimensionality reduction algorithm to obtain a target feature matrix, and target feature data corresponding to each gas sensor is obtained based on the target feature matrix. The target feature data includes a target feature vector corresponding to the gas sensor.

[0039] In the embodiments of the present application, the dimensionality reduction process for feature data primarily involves aggregating the feature data into a feature matrix. For example, in this embodiment, there are six gas sensors, each corresponding to five feature groups, resulting in an initial 5×6 feature matrix. Dimensionality reduction can convert the matrix to a lower-dimensional matrix, such as a 2×6 matrix. While the feature information of the five feature groups is retained during the dimensionality reduction process, the number of parameters required for identification of the target feature vector is reduced from five to three or two. The target dimensionality reduction algorithm in this embodiment can be PCA (Principal Component Analysis), t-SNE (t-Distributed Stochastic Neighbor Embedding), or LDA. LDA is selected as the target dimensionality reduction algorithm in this embodiment because it leverages categorical information to enhance discriminability, making it more straightforward for classification tasks such as gas types. It also preserves the discriminant type during the dimensionality reduction process, thereby preserving as much feature information from the feature matrix as possible.

[0040] In one possible implementation, the dimensionality reduction process of the initial feature matrix is ​​performed based on a target dimensionality reduction algorithm, including: Calculate the class mean vector and global mean vector of the initial feature matrix; Based on the class mean vector and the global mean vector, an inter-class scatter matrix is ​​established, and based on the class mean vector, an intra-class scatter matrix is ​​established; Based on the inter-class scatter matrix and the intra-class scatter matrix, the generalized characteristic equation corresponding to the initial characteristic matrix is ​​solved, and the projection direction of the initial characteristic matrix is ​​determined based on the solution; A projection matrix corresponding to the initial feature matrix is ​​established, and based on the projection matrix and projection direction, the dimension of the initial feature matrix is ​​compressed to the same dimension as the projection matrix to obtain the target feature matrix.

[0041] S4. Perform identification processing on each target feature data based on the target gas identification algorithm to obtain the identification result of the gas sensor array.

[0042] In the present embodiment, after dimensionality reduction to obtain the target feature matrix, target feature data, including the target feature vectors corresponding to each gas sensor after dimensionality reduction, can be obtained. The target gas identification algorithm can then use this data to identify the gas type in the mixed gas, thereby obtaining the identification result of the gas sensor array.

[0043] In one embodiment, identifying and processing each target characteristic data based on a target gas identification algorithm includes: Inputting target characteristic data into a gas sample database, the gas sample database including prediction characteristic vectors of multiple groups of gases, and the target characteristic data including target characteristic vectors of each gas sensor; The Euclidean distance between each target vector and the prediction feature vector is calculated, and based on the Euclidean distance calculation result, the gas type corresponding to each target vector is determined.

[0044] In the present embodiment, the target gas identification algorithm can be a deep learning method using an MLP (Multilayer Perceptron). However, this type of deep learning method has high training data requirements and consumes relatively high computing power. Because the target feature vectors in the reduced dimensionality target feature data have few parameter samples, and the KNN (K-Nearest Neighbors) algorithm is fast, highly resistant to interference, and highly accurate when processing low-dimensional data, the KNN algorithm, which uses distance calculation for classification, is used as the target gas identification algorithm in this embodiment.

[0045] Figure 2 A schematic diagram of the structure of a mixed gas identification system based on a gas sensor array provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the system at least includes: The signal receiving module is used to obtain the initial voltage signal corresponding to each gas sensor and perform anti-interference processing on the initial voltage signal to obtain the target voltage signal; A data extraction module is used to perform feature extraction processing on each target voltage signal to obtain feature data corresponding to the target voltage signal; The data dimension reduction module is used to perform dimension reduction processing on each feature data to obtain the target feature data corresponding to each feature data; The recognition module is used to identify and process the characteristic data of each target to obtain the recognition result of the gas sensor array; The display module is used to display the target voltage signal, target characteristic data and the recognition result of the gas sensor array.

[0046] like Figure 3 As shown, Figure 3 3 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: a processor (Processor) 301, a communication interface (Communications Interface) 302, a memory (Memory) 303, and a communication bus 304. The processor 301, the communication interface 302, and the memory 303 communicate with each other via the communication bus 304. The processor 301 can call software instructions in the memory 303 to execute the methods described in the above embodiments.

[0047] In addition, the logic instructions in the aforementioned memory 303 can be implemented in the form of a software functional unit and, when sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application.

[0048] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0049] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0050] It is understood that the processor in the embodiments of the present application may be a CPU (Central Processing Unit), other general-purpose processors, DSPs (Digital Signal Processors), ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0051] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, ROM (Read-only Memory), PROM (Programmable ROM), EPROM (Erasable PROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), registers, hard disks, removable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC.

[0052] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. Available media can include magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0053] It will be understood that the various numerical numbers involved in the embodiments of the present application are merely distinctions for the convenience of description and are not intended to limit the scope of the embodiments of the present application.

[0054] It is easy for those skilled in the art to understand that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A mixed gas identification method based on a gas sensor array, characterized in that: include: Obtaining an initial voltage signal corresponding to each gas sensor, and performing anti-interference processing on the initial voltage signal to obtain a target voltage signal; performing feature extraction processing on each of the target voltage signals to obtain feature data corresponding to the target voltage signal, the feature data including a response integral feature, a response amplitude feature, a response speed feature, and a response stability feature corresponding to each of the target voltage signals; Performing dimensionality reduction processing on each of the feature data based on a target dimensionality reduction algorithm to obtain target feature data corresponding to each of the feature data; The target characteristic data are identified and processed based on a target gas identification algorithm to obtain an identification result of the gas sensor array.

2. The mixed gas identification method based on the gas sensor array according to claim 1, characterized in that: The performing anti-interference processing on the initial voltage signal to obtain a target voltage signal includes: amplifying the initial voltage signal; performing impedance matching on the amplified initial voltage signal, and acquiring a voltage bias signal corresponding to the initial voltage signal based on a result of the impedance matching; The initial voltage signal is adjusted based on the voltage bias signal to obtain a target voltage signal, and the target voltage signal is amplified.

3. The mixed gas identification method based on the gas sensor array according to claim 1, characterized in that: The performing feature extraction processing on each of the target voltage signals includes: performing a motion smoothing process on the target voltage signal, and obtaining a response amplitude characteristic corresponding to the target voltage signal based on a result of the motion smoothing process; An extreme value normalization process is performed on the target voltage signal after the motion smoothing process, and based on the extreme value normalization process result, a response integral characteristic, a response speed characteristic, and a response stability characteristic corresponding to the target voltage signal are obtained.

4. The mixed gas identification method based on a gas sensor array according to claim 1, characterized in that: The target dimensionality reduction algorithm is used to perform dimensionality reduction processing on each of the feature data to obtain target feature data corresponding to each of the feature data, including: Based on the characteristic data corresponding to each of the gas sensors, obtaining an initial characteristic vector corresponding to each of the characteristic data, and establishing an initial characteristic matrix based on each of the initial characteristic vectors; The initial feature matrix is ​​subjected to dimensionality reduction processing based on a target dimensionality reduction algorithm to obtain a target feature matrix, and target feature data corresponding to each gas sensor is obtained based on the target feature matrix, wherein the target feature data includes a target feature vector corresponding to the gas sensor.

5. The mixed gas identification method based on the gas sensor array according to claim 4, characterized in that: The target dimensionality reduction algorithm is used to reduce the dimensionality of the initial feature matrix, including: Calculating a class mean vector and a global mean vector of the initial feature matrix; Establishing an inter-class scatter matrix based on the class mean vector and the global mean vector, and establishing an intra-class scatter matrix based on the class mean vector; Solving the generalized characteristic equation corresponding to the initial characteristic matrix based on the between-class scatter matrix and the within-class scatter matrix, and determining the projection direction of the initial characteristic matrix based on the solution result; A projection matrix corresponding to the initial feature matrix is ​​established, and based on the projection matrix and the projection direction, the dimension of the initial feature matrix is ​​compressed to the same dimension as the projection matrix to obtain a target feature matrix.

6. The mixed gas identification method based on a gas sensor array according to claim 1, characterized in that: The identifying and processing of each target characteristic data based on the target gas identification algorithm includes: Inputting the target characteristic data into a gas sample database, wherein the gas sample database includes prediction characteristic vectors of multiple groups of gases, and the target characteristic data includes the target characteristic vector of each gas sensor; The Euclidean distance between each target vector and the prediction feature vector is calculated, and the gas type corresponding to each target vector is determined based on the Euclidean distance calculation result.

7. The mixed gas identification method based on a gas sensor array according to claim 1, characterized in that: The target dimensionality reduction algorithm is the LDA algorithm.

8. A mixed gas identification method based on a gas sensor array, used to implement the method according to any one of claims 1 to 7, characterized in that: include: A signal receiving module is used to obtain the initial voltage signal corresponding to each gas sensor and perform anti-interference processing on the initial voltage signal to obtain a target voltage signal; a data extraction module, configured to perform feature extraction processing on each of the target voltage signals to obtain feature data corresponding to the target voltage signal; A data dimensionality reduction module is used to perform dimensionality reduction processing on each of the feature data to obtain target feature data corresponding to each of the feature data; An identification module is used to perform identification processing on each target feature data to obtain an identification result of the gas sensor array; The display module is used to display the target voltage signal, target characteristic data and the recognition result of the gas sensor array.

9. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or processor to execute the steps of the method according to any one of claims 1 to 7.

Images