Unmanned aerial vehicle and electronic nose combined smell recognition method and system

Abstract

The invention relates to the technical field of smell recognition, and discloses a smell recognition method and system combining an unmanned aerial vehicle and an electronic nose, and the method comprises the steps: obtaining the detection data of each gas sensor in the electronic nose for gas samples with different concentrations; processing the detection data, determining odor characteristics of each gas sample, enabling the odor characteristics of the gas samples to correspond to odor types, and generating an odor characteristic type comparison table; controlling the unmanned aerial vehicle to perform flight detection on the to-be-detected area according to a preset path, obtaining real-time detection data of each gas sensor in an electronic nose carried by the unmanned aerial vehicle, and determining odor characteristics of the to-be-detected area according to the real-time detection data; determining the similarity between the odor characteristics of the to-be-detected area and the odor characteristics of the gas sample, and determining the odor type of the to-be-detected area according to the similarity and an odor characteristic type comparison table. According to the invention, the odor type can be accurately determined, manual intervention is reduced, and the detection efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of odor recognition, and in particular to an odor recognition method and system combining an unmanned aerial vehicle with an electronic nose. Background Art

[0002] Odor recognition technology has broad application prospects in many fields, such as environmental monitoring, food safety, and medical diagnosis. Traditional odor recognition methods mainly rely on artificial olfactory detection, which is not only inefficient, but also easily affected by subjective factors, making it difficult to achieve accurate and rapid detection. With the development of science and technology, electronic nose technology has emerged. The electronic nose is a sensor system that simulates the human olfactory system and detects and identifies odors through multiple gas sensor arrays. However, the electronic nose also has certain limitations in practical applications, such as limited odor detection capabilities in large areas and complex environments. Therefore, there is an urgent need for an odor recognition method and system that combines a drone with an electronic nose to achieve large-scale odor detection in a specified area. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for odor recognition combining a drone and an electronic nose, so as to solve the problem that the traditional electronic nose has limited ability in odor detection in a large range and complex environment.

[0004] The present invention provides a method for odor recognition combining a drone and an electronic nose, comprising:

[0005] Obtaining detection data of gas samples of different concentrations by each gas sensor in the electronic nose;

[0006] Processing the detection data to determine the odor characteristics of each gas sample, making a one-to-one correspondence between the odor characteristics of each gas sample and the odor type of the gas sample, and generating an odor characteristic type comparison table;

[0007] Control the drone to perform flight inspection on the inspection area according to a preset path, obtain real-time detection data of each gas sensor in the electronic nose carried by the drone, and determine the odor characteristics of the inspection area according to the real-time detection data;

[0008] The similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample is determined, and the odor type of the area to be detected is determined according to the similarity and the odor characteristic type comparison table.

[0009] Preferably, the detection data is processed to determine the odor characteristics of each gas sample, including:

[0010] Preprocessing the detection data, wherein the preprocessing includes denoising, baseline correction and normalization;

[0011] Use chemometric methods to extract features from preprocessed detection data;

[0012] Based on the extracted features, the odor characteristics of each gas sample are determined using statistical analysis methods.

[0013] Preferably, the odor characteristics of each gas sample are matched one by one with the odor type of the gas sample, and an odor characteristic type comparison table is generated, including:

[0014] Determine the odor type of each gas sample;

[0015] Add the odor characteristics of each gas sample and the odor type of the gas sample to the comparison table template, and correspond the odor characteristics of each gas sample to the odor type to obtain an odor characteristic type comparison table;

[0016] Wherein, the comparison table template includes the gas sample number, odor characteristics and odor type.

[0017] Preferably, when determining the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, the similarity is determined by the following formula:

[0018]

[0019] Among them, Sk represents the similarity between the odor characteristics of the area to be detected and the odor characteristics of the kth gas sample, C i represents the odor feature of the i-th area to be detected, Q i represents the i-th odor feature of the k-th gas sample, n represents the data of the odor feature, and A represents the normalization constant.

[0020] Preferably, determining the odor type of the area to be detected according to the similarity and odor feature type comparison table includes:

[0021] Comparing the similarity with a similarity threshold, if the similarity is less than the similarity threshold, determining that the odor type of the area to be detected is not in the odor feature type comparison table;

[0022] If the similarity is greater than or equal to the similarity threshold, it is determined that the odor type of the area to be detected is in the odor feature type comparison table, and the corresponding odor feature when the similarity is greater than or equal to the similarity threshold is determined, and the odor feature type comparison table is screened according to the corresponding odor feature to obtain the odor type of the area to be detected.

[0023] The present invention also discloses an odor recognition system combining a drone and an electronic nose, which is used to apply the above-mentioned odor recognition method combining a drone and an electronic nose, and comprises:

[0024] A data acquisition module is configured to acquire detection data of gas samples of different concentrations by each gas sensor in the electronic nose;

[0025] a type comparison generation module configured to process the detection data, determine the odor characteristics of each gas sample, match the odor characteristics of each gas sample with the odor type of the gas sample one by one, and generate an odor characteristic type comparison table;

[0026] The flight detection module is configured to control the drone to perform flight detection on the detection area according to a preset path, obtain real-time detection data of each gas sensor in the electronic nose carried by the drone, and determine the odor characteristics of the detection area according to the real-time detection data;

[0027] The odor determination module is configured to determine the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, and determine the odor type of the area to be detected based on the similarity and the odor characteristic type comparison table.

[0028] Preferably, when the type comparison generation module processes the detection data to determine the odor characteristics of each gas sample, it includes:

[0029] Preprocessing the detection data, wherein the preprocessing includes denoising, baseline correction and normalization;

[0030] Use chemometric methods to extract features from preprocessed detection data;

[0031] Based on the extracted features, the odor characteristics of each gas sample are determined using statistical analysis methods.

[0032] Preferably, when the type comparison generation module matches the odor characteristics of each gas sample with the odor type of the gas sample one by one and generates an odor characteristic type comparison table, it includes:

[0033] Determine the odor type of each gas sample;

[0034] Add the odor characteristics of each gas sample and the odor type of the gas sample to the comparison table template, and correspond the odor characteristics of each gas sample to the odor type to obtain an odor characteristic type comparison table;

[0035] Wherein, the comparison table template includes the gas sample number, odor characteristics and odor type.

[0036] Preferably, when the odor determination module determines the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, the similarity is determined by the following formula:

[0037]

[0038] Among them, Sk represents the similarity between the odor characteristics of the area to be detected and the odor characteristics of the kth gas sample, C i represents the odor feature of the i-th area to be detected, Q i represents the i-th odor feature of the k-th gas sample, n represents the data of the odor feature, and A represents the normalization constant.

[0039] Preferably, when the odor determination module determines the odor type of the area to be detected according to the similarity and odor feature type comparison table, it includes:

[0040] Comparing the similarity with a similarity threshold, if the similarity is less than the similarity threshold, determining that the odor type of the area to be detected is not in the odor feature type comparison table;

[0041] If the similarity is greater than or equal to the similarity threshold, it is determined that the odor type of the area to be detected is in the odor feature type comparison table, and the corresponding odor feature when the similarity is greater than or equal to the similarity threshold is determined, and the odor feature type comparison table is screened according to the corresponding odor feature to obtain the odor type of the area to be detected.

[0042] Compared with the prior art, the beneficial effect of the present invention is that the present invention combines the maneuverability of the drone and the high sensitivity of the electronic nose, and can quickly and accurately detect and identify odors in large areas, making up for the shortcomings of the traditional electronic nose in spatial coverage, and by controlling the drone to fly along a preset path, it can conduct comprehensive detection of different areas to avoid omissions. The detection data of the gas sensor is obtained in real time, and odor changes and abnormal conditions can be discovered in time. Using the odor feature type comparison table and similarity calculation, the odor type of the area to be detected can be accurately determined, reducing manual intervention and improving detection efficiency and accuracy. It can be used in many fields such as environmental monitoring, safety testing, industrial production, etc., and has high practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 The present invention is a schematic flow chart of an odor recognition method combining a drone and an electronic nose.

[0045] Figure 2The present invention is a functional block diagram of an odor recognition system combining a drone and an electronic nose. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] like Figure 1 As shown, the present invention provides a method for odor recognition combining a drone and an electronic nose, comprising:

[0048] Obtaining detection data of gas samples of different concentrations by each gas sensor in the electronic nose;

[0049] Processing the detection data to determine the odor characteristics of each gas sample, making a one-to-one correspondence between the odor characteristics of each gas sample and the odor type of the gas sample, and generating an odor characteristic type comparison table;

[0050] Control the drone to perform flight inspection on the inspection area according to a preset path, obtain real-time detection data of each gas sensor in the electronic nose carried by the drone, and determine the odor characteristics of the inspection area according to the real-time detection data;

[0051] The similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample is determined, and the odor type of the area to be detected is determined according to the similarity and the odor characteristic type comparison table.

[0052] In some embodiments of the present application, the detection data is processed to determine the odor characteristics of each gas sample, including: preprocessing the detection data, the preprocessing including denoising, baseline correction and normalization; using chemometric methods to extract features from the preprocessed detection data; and using statistical analysis methods to determine the odor characteristics of each gas sample based on the extracted features.

[0053] In this embodiment, in order to accurately analyze and identify the odor characteristics of each gas sample, it is first necessary to perform a series of processing steps on the collected detection data. These steps include preprocessing the data to ensure the quality and accuracy of the data. The preprocessing process mainly includes the following aspects: First, denoising is performed to eliminate random noise and interference signals in the data. The presence of noise may have a negative impact on the subsequent analysis results, so removing noise is a crucial step. By applying various filtering algorithms, such as low-pass filtering, median filtering, etc., we can effectively reduce the impact of noise on the data. Secondly, baseline correction is performed. The baseline refers to the output signal of the detection device when there is no gas sample. Due to factors such as equipment aging and environmental changes, the baseline may drift, thereby affecting the accuracy of the detection results. Through baseline correction, the detection data can be adjusted to a unified baseline to ensure the consistency and comparability of the data. Next, normalization is performed. Normalization is to scale the data to a specific range, usually between 0 and 1. This can eliminate the impact of different dimensions and magnitudes on data analysis, making the detection data of different gas samples comparable. Commonly used normalization methods include minimum-maximum normalization and z-score normalization.

[0054] After preprocessing, chemometric methods are used to extract features from the preprocessed detection data. Chemometric methods include principal component analysis (PCA), partial least squares (PLS), and linear discriminant analysis (LDA). These methods can extract the most representative features from high-dimensional data, thereby simplifying the data structure and facilitating subsequent analysis. Finally, based on the extracted features, statistical analysis methods are used to determine the odor characteristics of each gas sample. Statistical analysis methods include cluster analysis, discriminant analysis, and regression analysis. Through these methods, the similarities and differences between different gas samples can be revealed, thereby accurately describing and distinguishing their odor characteristics. The odor characteristics in this application can be represented by feature vectors.

[0055] In some embodiments of the present application, the odor characteristics of each gas sample are matched one-to-one with the odor type of the gas sample, and an odor characteristic type comparison table is generated, including: determining the odor type of each gas sample; adding the odor characteristics of each gas sample and the odor type of the gas sample to a comparison table template, and matching the odor characteristics of each gas sample with the odor type to obtain an odor characteristic type comparison table; wherein the comparison table template includes the gas sample number, odor characteristics and odor type.

[0056] In this embodiment, in order to ensure that the odor characteristics of the gas samples can be accurately identified and classified, it is necessary to match the odor characteristics of each gas sample with its corresponding odor type in detail. This process involves creating an odor characteristic type comparison table, which will list the odor type of each gas sample in detail and correspond the odor characteristics of each gas sample to the corresponding odor type one by one. The specific steps are as follows: First, the odor type of each gas sample needs to be determined. Next, the odor characteristics of each gas sample are matched with the odor type of the gas sample, and this information is added to a pre-designed comparison table template. This template will contain three main columns: gas sample number, odor characteristics, and odor type. The gas sample number is used to identify each specific gas sample; the odor characteristic column describes the unique odor characteristics of each gas sample in detail; and the odor type column classifies these odor characteristics into corresponding odor types. In this way, a complete odor characteristic type comparison table can be generated, which not only lists the odor characteristics of each gas sample in detail, but also accurately corresponds to the corresponding odor type.

[0057] In some embodiments of the present application, when determining the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, the similarity is determined by the following formula:

[0058]

[0059] Among them, Sk represents the similarity between the odor characteristics of the area to be detected and the odor characteristics of the kth gas sample, C i represents the odor feature of the i-th area to be detected, Q i represents the i-th odor feature of the k-th gas sample, n represents the data of the odor feature, and A represents the normalization constant.

[0060] In some embodiments of the present application, the odor type of the area to be detected is determined according to the similarity and the odor feature type comparison table, including: comparing the similarity with the similarity threshold, if the similarity is less than the similarity threshold, determining that the odor type of the area to be detected is not in the odor feature type comparison table; if the similarity is greater than or equal to the similarity threshold, determining that the odor type of the area to be detected is in the odor feature type comparison table, and determining the corresponding odor feature when the similarity is greater than or equal to the similarity threshold, screening the odor feature type comparison table according to the corresponding odor feature to obtain the odor type of the area to be detected.

[0061] In this embodiment, the odor type of the area to be detected is determined based on the similarity and the odor feature type comparison table. The specific steps are as follows: First, the similarity is compared with a preset similarity threshold. If the calculated similarity is less than the similarity threshold, it can be determined that the odor type of the area to be detected is not in the odor feature type comparison table. On the contrary, if the calculated similarity is greater than or equal to the similarity threshold, it can be determined that the odor type of the area to be detected is in the odor feature type comparison table. In this case, it is necessary to further determine the odor features corresponding to the similarity greater than or equal to the similarity threshold. Finally, the odor feature type comparison table is screened according to these corresponding odor features to obtain the odor type of the area to be detected. Through this series of steps, the odor type of the area to be detected can be effectively identified and classified.

[0062] like Figure 2 As shown, the present invention also discloses an odor recognition system combining a drone and an electronic nose, which is used to apply the above-mentioned odor recognition method combining a drone and an electronic nose, including:

[0063] The data acquisition module is configured to acquire detection data of gas samples of different concentrations by each gas sensor in the electronic nose.

[0064] The type comparison generation module is configured to process the detection data, determine the odor characteristics of each gas sample, match the odor characteristics of each gas sample with the odor type of the gas sample one by one, and generate an odor characteristic type comparison table.

[0065] The flight detection module is configured to control the drone to perform flight detection on the area to be detected along a preset path, obtain real-time detection data of each gas sensor in the electronic nose carried by the drone, and determine the odor characteristics of the area to be detected based on the real-time detection data.

[0066] The odor determination module is configured to determine the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, and determine the odor type of the area to be detected based on the similarity and the odor characteristic type comparison table.

[0067] The present invention uses an unmanned aerial vehicle equipped with an electronic nose for flight detection, which can quickly cover a large area and significantly improve detection efficiency. It is particularly suitable for areas that are difficult to reach manually. The flight detection module can obtain the detection data of each gas sensor in the electronic nose in real time, ensure the timeliness of the odor information, and help to respond to and handle abnormal odor situations in a timely manner. The type comparison generation module generates an odor feature type comparison table by processing the detection data, so that the odor determination module can accurately match the odor characteristics of the area to be detected with the known odor type, thereby determining the odor type. The system of the present invention can adjust the flight path and detection strategy of the unmanned aerial vehicle according to different detection requirements, and adapt to various complex and changeable detection environments. The automated detection using unmanned aerial vehicles and electronic noses reduces the human resources required for traditional manual detection and reduces operating costs.

[0068] In some embodiments of the present application, when the type control generation module processes the detection data to determine the odor characteristics of each gas sample, it includes: preprocessing the detection data, the preprocessing including denoising, baseline correction and normalization; using chemometric methods to extract features from the preprocessed detection data; and using statistical analysis methods to determine the odor characteristics of each gas sample based on the extracted features.

[0069] In some embodiments of the present application, when the type comparison generation module matches the odor characteristics of each gas sample with the odor type of the gas sample one-to-one and generates an odor characteristic type comparison table, it includes: determining the odor type of each gas sample; adding the odor characteristics of each gas sample and the odor type of the gas sample to a comparison table template, and matching the odor characteristics of each gas sample with the odor type to obtain an odor characteristic type comparison table; wherein the comparison table template includes the gas sample number, odor characteristics and odor type.

[0070] In this embodiment, feature extraction is performed on the detection data to obtain the odor feature vector of the gas sample, and the odor feature is matched with the odor type to obtain an odor feature type comparison table. Each odor type in the odor feature type comparison table corresponds to an odor feature, which facilitates the subsequent determination of the odor type corresponding to the odor feature based on the odor feature.

[0071] In some embodiments of the present application, when the odor determination module determines the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, the similarity is determined by the following formula:

[0072]

[0073] Among them, Sk represents the similarity between the odor characteristics of the area to be detected and the odor characteristics of the kth gas sample, Ci represents the odor feature of the i-th area to be detected, Q i represents the i-th odor feature of the k-th gas sample, n represents the data of the odor feature, and A represents the normalization constant.

[0074] In some embodiments of the present application, when the odor determination module determines the odor type of the area to be detected according to the similarity and the odor feature type comparison table, it includes: comparing the similarity with the similarity threshold; if the similarity is less than the similarity threshold, determining that the odor type of the area to be detected is not in the odor feature type comparison table; if the similarity is greater than or equal to the similarity threshold, determining that the odor type of the area to be detected is in the odor feature type comparison table, and determining the corresponding odor feature when the similarity is greater than or equal to the similarity threshold, screening the odor feature type comparison table according to the corresponding odor feature to obtain the odor type of the area to be detected.

[0075] In this embodiment, when calculating the similarity, the similarity between the odor feature of the area to be detected and the odor feature of each gas sample is calculated, and the odor type of the area to be detected is determined according to the comparison result of the similarity and the similarity threshold. If the similarity between the odor feature of the area to be detected and the odor feature of the third gas sample is greater than the similarity threshold, the odor feature of the area to be detected is the odor feature of the third gas sample, and then the odor type corresponding to the odor feature of the third gas sample is determined to be the odor type of the area to be detected.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

[0077] The system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0078] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. A method for odor recognition combining a drone and an electronic nose, characterized in that: include: Obtaining detection data of gas samples of different concentrations by each gas sensor in the electronic nose; Processing the detection data to determine the odor characteristics of each gas sample, making a one-to-one correspondence between the odor characteristics of each gas sample and the odor type of the gas sample, and generating an odor characteristic type comparison table; Control the drone to perform flight inspection on the inspection area according to a preset path, obtain real-time detection data of each gas sensor in the electronic nose carried by the drone, and determine the odor characteristics of the inspection area according to the real-time detection data; The similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample is determined, and the odor type of the area to be detected is determined according to the similarity and the odor characteristic type comparison table.

2. The odor recognition method combining a drone and an electronic nose according to claim 1, characterized in that: The detection data is processed to determine the odor characteristics of each gas sample, including: Preprocessing the detection data, wherein the preprocessing includes denoising, baseline correction and normalization; Use chemometric methods to extract features from preprocessed detection data; Based on the extracted features, the odor characteristics of each gas sample are determined using statistical analysis methods.

3. The odor recognition method combining a drone and an electronic nose according to claim 1, characterized in that: The odor characteristics of each gas sample are matched one by one with the odor type of the gas sample, and an odor characteristic type comparison table is generated, including: Determine the odor type of each gas sample; Add the odor characteristics of each gas sample and the odor type of the gas sample to the comparison table template, and correspond the odor characteristics of each gas sample to the odor type to obtain an odor characteristic type comparison table; Wherein, the comparison table template includes the gas sample number, odor characteristics and odor type.

4. The odor recognition method combining a drone and an electronic nose according to claim 1, characterized in that: When determining the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, the similarity is determined by the following formula: Among them, Sk represents the similarity between the odor characteristics of the area to be detected and the odor characteristics of the kth gas sample, C i represents the odor feature of the i-th area to be detected, Q i represents the i-th odor feature of the k-th gas sample, n represents the data of the odor feature, and A represents the normalization constant.

5. The odor recognition method combining a drone and an electronic nose according to claim 1, characterized in that: Determining the odor type of the area to be detected according to the similarity and the odor feature type comparison table includes: Comparing the similarity with a similarity threshold, if the similarity is less than the similarity threshold, determining that the odor type of the area to be detected is not in the odor feature type comparison table; If the similarity is greater than or equal to the similarity threshold, it is determined that the odor type of the area to be detected is in the odor feature type comparison table, and the corresponding odor feature when the similarity is greater than or equal to the similarity threshold is determined, and the odor feature type comparison table is screened according to the corresponding odor feature to obtain the odor type of the area to be detected.

6. An odor recognition system combining a drone and an electronic nose, used for applying the odor recognition method combining a drone and an electronic nose as described in any one of claims 1 to 5, characterized in that: include: A data acquisition module is configured to acquire detection data of gas samples of different concentrations by each gas sensor in the electronic nose; a type comparison generation module configured to process the detection data, determine the odor characteristics of each gas sample, match the odor characteristics of each gas sample with the odor type of the gas sample one by one, and generate an odor characteristic type comparison table; The flight detection module is configured to control the drone to perform flight detection on the detection area according to a preset path, obtain real-time detection data of each gas sensor in the electronic nose carried by the drone, and determine the odor characteristics of the detection area according to the real-time detection data; The odor determination module is configured to determine the similarity between the odor characteristics of the area to be detected and the odor characteristics of the gas sample, and determine the odor type of the area to be detected based on the similarity and the odor characteristic type comparison table.

7. The odor recognition system combining a drone and an electronic nose according to claim 6, characterized in that: When the type comparison generation module processes the detection data to determine the odor characteristics of each gas sample, it includes: Preprocessing the detection data, wherein the preprocessing includes denoising, baseline correction and normalization; Use chemometric methods to extract features from preprocessed detection data; Based on the extracted features, the odor characteristics of each gas sample are determined using statistical analysis methods.

8. The odor recognition system combining a drone and an electronic nose according to claim 6, characterized in that: When the type comparison generation module matches the odor characteristics of each gas sample with the odor type of the gas sample one by one and generates an odor characteristic type comparison table, it includes: Determine the odor type of each gas sample; Add the odor characteristics of each gas sample and the odor type of the gas sample to the comparison table template, and correspond the odor characteristics of each gas sample to the odor type to obtain an odor characteristic type comparison table; Wherein, the comparison table template includes the gas sample number, odor characteristics and odor type.

9. The odor recognition system combining a drone and an electronic nose according to claim 6, characterized in that: When the odor determination module determines the similarity between the odor feature of the area to be detected and the odor feature of the gas sample, the similarity is determined by the following formula: Among them, Sk represents the similarity between the odor characteristics of the area to be detected and the odor characteristics of the kth gas sample, C i represents the odor feature of the i-th area to be detected, Q i represents the i-th odor feature of the k-th gas sample, n represents the data of the odor feature, and A represents the normalization constant.

10. The odor recognition system combining a drone and an electronic nose according to claim 6, characterized in that: When the odor determination module determines the odor type of the area to be detected according to the similarity and the odor feature type comparison table, it includes: Comparing the similarity with a similarity threshold, if the similarity is less than the similarity threshold, determining that the odor type of the area to be detected is not in the odor feature type comparison table; If the similarity is greater than or equal to the similarity threshold, it is determined that the odor type of the area to be detected is in the odor feature type comparison table, and the corresponding odor feature when the similarity is greater than or equal to the similarity threshold is determined, and the odor feature type comparison table is screened according to the corresponding odor feature to obtain the odor type of the area to be detected.

Images