Gas detection method, system and equipment based on odor array sensor, medium and product

Abstract

The invention discloses a gas detection method, system and equipment based on an odor array sensor, a medium and a product, and relates to the field of gas detection.The method comprises the steps that odor data collection is conducted on multiple types of sample gas in a sampling box through the odor array sensor; the smell array sensor is composed of 32 differentially sensitive oxide semiconductor elements; preprocessing the collected smell data to generate a sample standardization matrix of each type of sample gas; based on the standardized matrix, adopting a support vector machine to generate a sample identification feature matrix of each type of sample gas; and detecting to-be-detected gas based on the sample identification feature matrix. According to the invention, the gas detection speed and precision can be improved.

Description

Technical Field

[0001] This application relates to the field of gas detection, and in particular to a gas detection method, system, device, medium and product based on an odor array sensor. Background Technology

[0002] With the needs of social development and the advancement of science and technology, human research on the mechanisms of biological organs has become increasingly sophisticated. The imitation of biological sensory functions such as vision, hearing, taste, touch, and smell has been extensively studied by scientists worldwide. Human research on smell has evolved from early chemical analysis methods to instrumental analysis methods over nearly a century. Biomimetic olfactory technology has become increasingly capable of identifying substances, and its recognition rate has gradually improved.

[0003] Odor recognition technology detects and classifies odors by simulating the human olfactory system, but its progress is affected by the dimensionality of feature data. Traditional technologies often use 8-16 dimensional feature data, which results in insufficient recognition accuracy. Summary of the Invention

[0004] The purpose of this application is to provide a gas detection method, system, device, medium, and product based on an odor array sensor, which can improve the speed and accuracy of gas detection.

[0005] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a gas detection method based on an odor array sensor, comprising: Odor data is collected from multiple categories of sample gases in the sampling chamber using an odor array sensor; the odor array sensor consists of 32 differentially sensitive oxide semiconductor elements. The collected odor data is preprocessed to generate a sample normalization matrix for each category of sample gas; Based on the standardized matrix, a support vector machine is used to generate a sample identification feature matrix for each category of sample gas; The gas to be tested is detected based on the sample identification feature matrix.

[0006] Secondly, this application provides a gas detection system based on an odor array sensor, comprising: The acquisition module is used to acquire odor data of multiple categories of sample gases in the sampling chamber through an odor array sensor; the odor array sensor consists of 32 differentially sensitive oxide semiconductor elements; The preprocessing module is used to preprocess the collected odor data and generate a sample normalization matrix for each category of sample gas. The sample identification feature matrix generation module is used to generate a sample identification feature matrix for each category of sample gas based on the standardized matrix using a support vector machine. The detection module is used to detect the gas to be tested based on the sample identification feature matrix.

[0007] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described gas detection method based on an odor array sensor.

[0008] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described gas detection method based on an odor array sensor.

[0009] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described gas detection method based on an odor array sensor.

[0010] According to the specific embodiments provided in this application, this application has the following technical effects: This application employs an odor array sensor composed of 32 differentially sensitive oxide semiconductor elements, significantly enhancing the dimensionality and information richness of odor data. This effectively overcomes the problem of insufficient recognition accuracy in traditional odor recognition technologies that rely solely on 8–16 dimensional feature data. Furthermore, by standardizing and preprocessing the collected odor data and constructing a highly discriminative sample recognition feature matrix using a Support Vector Machine (SVM), not only is the ability to distinguish between multiple gas categories enhanced, but the generalization performance and stability of the model under complex or interfering environments are also improved. This application establishes a complete and repeatable gas detection process from high-dimensional data acquisition and standardization to intelligent classification and recognition, breaking through the dimensional bottleneck of traditional bionic olfactory systems and significantly improving the accuracy, reliability, and practicality of odor recognition. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of a gas detection method based on an odor array sensor, provided as an embodiment of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] In one exemplary embodiment, such as Figure 1 As shown, a gas detection method based on an odor array sensor is provided. This method is executed by a computer device, specifically by a computer device such as a terminal or a server alone, or by both a terminal and a server. In this embodiment, the method is described using a server as an example, and includes the following steps S1 to S4.

[0016] S1: Odor data is collected from multiple categories of sample gases in the sampling chamber using an odor array sensor; the odor array sensor consists of 32 differentially sensitive oxide semiconductor elements.

[0017] Multiple types of sample gases are released into the sampling chamber, which is then kept at a constant temperature and humidity. An odor array sensor is placed at the sampling port of the chamber; the sensor is then activated to collect odor data.

[0018] The cross-sectional area of ​​the odor array sensor is a square with a side length of 19 mm, and the sampling time is 100 s.

[0019] S2: Preprocess the collected odor data to generate a sample normalization matrix for each category of sample gas. Specifically, this includes: summarizing the collected odor data into a total sample matrix; calculating the mean and standard deviation of the total sample matrix; and standardizing the total sample matrix based on the mean and standard deviation to generate a sample normalization matrix for each category of sample gas.

[0020] If there are K categories, and each category has N samples of sample gas, the collected and measured samples (i.e., odor data) are labeled and summarized into a total sample matrix. , It has K×N rows and 32 columns. This embodiment uses 4... The odor gases produced by heating a 25cm low-smoke halogen-free cross-linked polyethylene rare earth high-speed iron aluminum alloy core power cable (WDZ-YJ(XG)LHV) and the odor gases from burnt fur were the measurement and identification objects, totaling 2 categories, with 32 samples measured for each category.

[0021] calculate The arithmetic mean matrix μ for each column of data; calculate The average value M for each column of data: calculate Standard deviation of each column of data : Through mean M and standard deviation ,right The sample standardization matrix is ​​obtained by standardization. : S3: Based on the standardized matrix, a support vector machine is used to generate a sample identification feature matrix for each category of sample gas. Specifically, this includes: using a support vector machine to construct an objective function with the goal of maximizing the sum of the distances from the hyperplane to the two types of sample gases; solving the objective function using the Lagrange multiplier method to obtain the optimal hyperplane; and converting the sample standardized matrix into a sample identification feature matrix based on the optimal hyperplane.

[0022] (1) Construction of the objective function.

[0023] Define a hyperplane (w, b) in a 32-dimensional feature space, where w is the hyperplane coefficient and b is the hyperplane intercept; let the standardized data of the two types of sample gases be positive examples (labeled) and negative examples (labeled). ) and negative examples (marked) ).

[0024] Hyperplane to any positive sample data point The distance is: Hyperplane to any negative sample data point The distance is: The objective is to maximize the sum of distances from the hyperplane to all sample data points of the two types of sample gases, combined with classification constraints. Construct the objective function: Transform it into a minimization problem: (2) Solving for the optimal hyperplane.

[0025] Transform the problem into a multivariate extremum problem using the Lagrange multiplier method, and find the maximum and minimum values: in, It is a Lagrange multiplier.

[0026] By taking the partial derivatives with respect to w and b, and setting the partial derivatives to zero, the optimal hyperplane coefficients can be obtained. and optimal hyperplane intercept Thus, the optimal hyperplane is obtained. , ).

[0027] (3) Sample recognition feature matrix generation.

[0028] Standardize the sample matrix Each 32-dimensional feature vector Substitute (k=1,2,...,K×N) into the decision function of the optimal hyperplane : in, Let `sign` be the mapping function from a 32-dimensional feature vector to a high-dimensional feature space, and `sign` be the sign function; each feature vector is calculated... Corresponding decision value The decision value is +1 or -1, corresponding to the category identifiers of the two types of sample gases, respectively; With the corresponding decision value The samples are bound together and arranged in order to form a K×N row, 33 column sample recognition feature matrix. (The first 32 columns are feature vectors, and the 33rd column is the category identifier).

[0029] S4: Detect the gas to be tested based on the sample identification feature matrix. Specifically, this includes: collecting odor data of the gas to be tested using an odor array sensor and generating a standardized matrix; generating a feature matrix of the gas to be tested using a support vector machine based on the standardized matrix; calculating the hyperplane distance between the feature matrix of the gas to be tested and the sample identification feature matrix of each category of sample gas; and determining the category of the sample gas with the closest hyperplane distance as the category of the gas to be tested.

[0030] For the gas to be tested, repeat steps S2 to S3 to obtain the feature matrix of the gas to be tested. .calculate Each feature vector in The hyperplane distance between the feature vectors of various gases is used to determine the category of the sample gas with the closest hyperplane distance.

[0031] This application analyzes gas odor data by using a solution to the linearly inseparable problem of Support Vector Machine (SVM) to ultimately identify various categories of gases.

[0032] Based on the same inventive concept, this application also provides a system for implementing the gas detection method based on an odor array sensor as described above. The solution provided by this system is similar to the implementation described in the above method; therefore, the specific limitations of one or more embodiments of the gas detection system based on an odor array sensor provided below can be found in the limitations of the gas detection method based on an odor array sensor described above, and will not be repeated here.

[0033] In one exemplary embodiment, a gas detection system based on an odor array sensor is provided, including the following modules.

[0034] The acquisition module is used to acquire odor data of multiple categories of sample gases in the sampling chamber through an odor array sensor; the odor array sensor consists of 32 differentially sensitive oxide semiconductor elements.

[0035] The preprocessing module is used to preprocess the collected odor data and generate a sample normalization matrix for each category of sample gas.

[0036] The sample identification feature matrix generation module is used to generate a sample identification feature matrix for each category of sample gas based on the standardized matrix using a support vector machine.

[0037] The detection module is used to detect the gas to be tested based on the sample identification feature matrix.

[0038] Furthermore, the detection module includes the following units.

[0039] The test normalization matrix generation unit is used to collect odor data of the test gas through an odor array sensor and generate the test normalization matrix.

[0040] The gas to be tested feature matrix generation unit is used to generate the gas to be tested feature matrix using a support vector machine based on the normalized matrix to be tested.

[0041] The hyperplane distance calculation unit is used to calculate the hyperplane distance between the feature matrix of the gas to be tested and the sample identification feature matrix of each category of sample gas.

[0042] The detection unit is used to determine the category of the sample gas closest to the hyperplane as the category of the gas to be tested.

[0043] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments. The computer device may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, memory, and I / O are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device stores data to be processed. The I / O interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with an external terminal via a network connection. When the computer program is executed by the processor, it implements the steps in the above-described method embodiments.

[0044] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0045] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0046] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0047] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0048] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0049] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A gas detection method based on an odor array sensor, characterized in that, include: Odor data of multiple categories of sample gases in the sampling chamber are collected using an odor array sensor. The odor array sensor consists of 32 differentially sensitive oxide semiconductor elements; The collected odor data is preprocessed to generate a sample normalization matrix for each category of sample gas; Based on the standardized matrix, a support vector machine is used to generate a sample identification feature matrix for each category of sample gas; The gas to be tested is detected based on the sample identification feature matrix.

2. The gas detection method based on an odor array sensor according to claim 1, characterized in that, The collected odor data is preprocessed to generate a sample normalization matrix for each category of sample gas, specifically including: The collected odor data are summarized into a total sample matrix; Calculate the mean and standard deviation of the population sample matrix; The overall sample matrix is ​​standardized based on the mean and the standard deviation to generate a sample standardized matrix for each category of sample gas.

3. The gas detection method based on an odor array sensor according to claim 1, characterized in that, Calculating the mean and standard deviation of the population sample matrix specifically includes: Calculate the arithmetic mean matrix of the total sample matrix; The mean of the population sample matrix is ​​calculated based on the arithmetic mean matrix; The standard deviation is calculated based on the mean and the overall sample matrix.

4. The gas detection method based on an odor array sensor according to claim 1, characterized in that, Based on the aforementioned sample standardization matrix, a support vector machine is used to generate a sample recognition feature matrix, specifically including: A support vector machine is used to construct an objective function with the goal of maximizing the sum of the distances from the hyperplane to the two types of sample gases. The objective function is solved using the Lagrange multiplier method to obtain the optimal hyperplane. Based on the optimal hyperplane, the sample normalization matrix is ​​converted into a sample recognition feature matrix.

5. The gas detection method based on an odor array sensor according to claim 1, characterized in that, The gas to be tested is detected based on the sample identification feature matrix, specifically including: Odor data of the gas to be tested is collected using an odor array sensor, and a standardized matrix of the gas to be tested is generated. Based on the standardized matrix to be tested, a support vector machine is used to generate the feature matrix of the gas to be tested. Calculate the hyperplane distance between the feature matrix of the gas to be tested and the sample identification feature matrix of each category of sample gas; The category of the sample gas closest to the hyperplane is determined as the category of the gas to be tested.

6. A gas detection system based on an odor array sensor, characterized in that, include: The acquisition module is used to acquire odor data of multiple categories of sample gases in the sampling chamber through an odor array sensor; The odor array sensor consists of 32 differentially sensitive oxide semiconductor elements; The preprocessing module is used to preprocess the collected odor data and generate a sample normalization matrix for each category of sample gas. The sample identification feature matrix generation module is used to generate a sample identification feature matrix for each category of sample gas based on the standardized matrix using a support vector machine. The detection module is used to detect the gas to be tested based on the sample identification feature matrix.

7. The gas detection system based on an odor array sensor according to claim 6, characterized in that, The detection module includes: The test normalization matrix generation unit is used to collect odor data of the test gas through an odor array sensor and generate the test normalization matrix. The gas to be tested feature matrix generation unit is used to generate the gas to be tested feature matrix based on the normalized matrix to be tested using a support vector machine. The hyperplane distance calculation unit is used to calculate the hyperplane distance between the feature matrix of the gas to be tested and the sample identification feature matrix of each category of sample gas; The detection unit is used to determine the category of the sample gas closest to the hyperplane as the category of the gas to be tested.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the gas detection method based on an odor array sensor according to any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the gas detection method based on an odor array sensor as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the gas detection method based on an odor array sensor as described in any one of claims 1-5.

Images