阅读说明：本技术 一种基于自制电子鼻系统的酱油分类方法 (Soy sauce classification method based on self-made electronic nose system ) 是由 钮永莉 刘青 武斌 刘东旭 于 2020-06-09 设计创作，主要内容包括：本发明公开了一种基于自制电子鼻系统的酱油分类方法。将该方法运用于五种酱油电子鼻数据的聚类分析并与传统GK模糊算法和FCM算法进行对比。聚类结果表明,M_GK算法具有更少的迭代次数和更高的聚类准确率；电子鼻技术结合PCA,LDA算法和M_GK聚类可以实现酱油品种的准确分类,提供了实现酱油分类鉴别的一种有效模型。(The invention discloses a soy sauce classification method based on a self-made electronic nose system. The method is applied to the cluster analysis of the data of the electronic nose of the five soy sauce types and is compared with the traditional GK fuzzy algorithm and the FCM algorithm. The clustering result shows that the M _ GK algorithm has fewer iteration times and higher clustering accuracy; the electronic nose technology is combined with PCA, LDA algorithm and M _ GK clustering, so that accurate classification of soy sauce varieties can be realized, and an effective model for realizing soy sauce classification and identification is provided.)

1. A soy sauce classification method based on a self-made electronic nose system is characterized by comprising the following steps:

s1, opening the bottle cover of the sample, and electrifying the electronic nose for 10 minutes for preheating;

s2, putting a 15 ml soy sauce sample into a sample bottle, connecting an air pipe of the sample bottle with an air chamber, placing the sample bottle in the center of the air chamber, and standing the sensor for 60 minutes until the gas is completely volatilized;

s3, collecting and recording data by using an upper computer program compiled by NI LabVIEW 2018, collecting the data once every 5 minutes for three times in total, and taking the average value of the three collection results as stable data of a soy sauce sample;

and S4, after the soy sauce sample is collected once, opening the box cover and standing for 10 minutes to enable each sensor to recover the initial state, and then repeatedly collecting other soy sauce samples. The state of the air chamber can be observed through a LabVIEW response curve, and after the air chamber is completely emptied, data of another soy sauce sample is collected;

steps S2-S4 are repeated until all data acquisitions are complete.

2. The soy sauce classification method based on the homemade electronic nose system according to claim 1, characterized in that: the electronic nose system for soy sauce mainly comprises a gas chamber (where a sensor array is arranged), a sample bottle, a gas sensor array, a data acquisition card, a computer and the like.

3. The soy sauce classification method based on the homemade electronic nose system according to claim 2, characterized in that: the gas sensor for selecting the self-made electronic nose aiming at the characteristic aroma of the soy sauce is required to be sensitive to the odor components and the concentration of a soy sauce sample, and eight semiconductor gas sensors of MQ135, MQ3, TGS2600, TGS2620, TGS2602, TGS2610, TGS2611 and TGS813 are selected for sample identification.

Technical Field

The invention relates to the technical field of information, in particular to a soy sauce classification method based on a self-made electronic nose system.

Background

The soy sauce originates from China, has unique fragrance and various nutritional ingredients, such as amino acids, saccharides, organic acids, minerals, esters, vitamins and the like, is very beneficial to human bodies, and is popular in daily life of people. The taste of soy sauce is an important index of soy sauce quality and quality, and is generally judged by depending on the sense of a quality control expert, but the taste of soy sauce is greatly influenced by subjective factors, and a modern instrument is required to replace or assist the work of the quality control expert. The electronic nose technology is a simple, rapid and objective smell detection technology, comprises knowledge of a plurality of subjects such as sensors, mode recognition, signal processing and the like, and is widely used for analyzing various gas components containing organic volatile matters. The electronic nose has the advantages of high speed, high sensitivity and nondestructive detection, thereby being applied to the fields of food classification and identification and food safety and becoming a research hotspot. For example, the method is widely applied to tea classification detection, meat detection, wine detection and fruit and vegetable detection.

Most of the current electronic nose application research adopts finished electronic nose systems, such as PEN3, INose and the like, which are expensive and have limited market popularization. The invention researches and designs an electronic nose system for soy sauce detection, which firstly uses Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) to reduce the dimension of data, then uses an improved GK clustering algorithm to process an electronic nose signal, and carries out a comparative test with an FCM algorithm and a traditional GK algorithm to realize the detection and classification of soy sauce varieties.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides a soy sauce classification method based on a self-made electronic nose system.

Electronic nose system connection

The data acquisition card uses NI USB 6002, manufactured by National Instruments (NI) Inc., which provides eight analog input channels, and interacts with the PC using NI's configuration management software NIMax. The devices of each part of the electronic nose are orderly connected, the sensor array is connected with a data acquisition card, the output end of the data acquisition card is connected with a PC through a USB line, and the power supply is switched on.

In order to achieve the purpose, the invention adopts the following technical scheme:

a soy sauce classification method based on a homemade electronic nose system comprises the following steps:

s1, opening the bottle cover of the sample, and electrifying the electronic nose for 10 minutes for preheating;

s2, putting a 15 ml soy sauce sample into a sample bottle, connecting an air pipe of the sample bottle with an air chamber, placing the sample bottle in the center of the air chamber, and standing the sensor for 60 minutes until the gas is completely volatilized;

s3, collecting and recording data by using an upper computer program compiled by NI LabVIEW 2018, collecting the data once every 5 minutes for three times in total, and taking the average value of the three collection results as stable data of a soy sauce sample;

and S4, after the soy sauce sample is collected once, opening the box cover and standing for 10 minutes to enable each sensor to recover the initial state, and then repeatedly collecting other soy sauce samples. The state of the air chamber can be observed through a LabVIEW response curve, and after the air chamber is completely emptied, data of another soy sauce sample is collected;

steps S2-S4 are repeated until all data acquisitions are complete.

The invention has the beneficial effects that:

1. improvement to GK clustering (M _ GK)

The GK clustering is a fuzzy clustering algorithm, and the algorithm can detect clusters with different shapes in a data set and realize effective classification of the data set. However, the algorithm also has certain disadvantages, such as sensitivity to initial clustering centers and clustering numbers, easy falling into local optimum and the like. The invention uses a method based on density function to determine the initial clustering center, namely, the data area of each sample point is fully considered, firstly, the point with the highest density index is selected as the first clustering center, then the density index values of other sample points are correspondingly adjusted according to the distance between the other sample points and the clustering center, so that the closer points in the sample are, the faster the density is reduced, the cycle is carried out in sequence until enough clustering centers are found.

2. Faster speed and higher precision

The method is applied to the cluster analysis of the data of the electronic nose of the five soy sauce types and is compared with the traditional GK fuzzy algorithm and the FCM algorithm. The clustering result shows that the M _ GK algorithm has fewer iteration times and higher clustering accuracy; the electronic nose technology is combined with PCA, LDA algorithm and M _ GK clustering, so that accurate classification of soy sauce varieties can be realized, and an effective model for realizing soy sauce classification and identification is provided.

Drawings

FIG. 1 is a flow chart of the operation of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.