-
公开(公告)号：US20230141978A1
公开(公告)日：2023-05-11
申请号：US17794801
申请日：2020-07-18
发明人： Zejian Wang , Daqi Gao , Bo Li , Xiaoqin Zhang , Fang Cai , Jianhua Li , Mingjian Cheng
CPC分类号： G01N30/88 , G01N33/0032 , G01N33/0034 , G01N33/0062 , G06N3/045 , G01N2030/8804 , G01N2030/8809
摘要： Provided is a method for multi-information fusion of gas sensitivity and chromatography and on-site detection and analysis of flavor substances using an electronic nose instrument. The electronic nose instrument includes a gas sensor array module (I), a capillary gas chromatographic column module (II), an automatic headspace sampling module (III), a computer control and data analysis module (IV), an automatic lifter (V) for headspace sampling, a large-volume headspace vapor generation device (VI) and two auxiliary gas sources (VII-1, VII-2). The electronic nose instrument detects a large number of odorous samples to establish a big odor data. On this basis, the normalization fusion preprocessing is done, and the cascade machine learning model realizes both an on-site recognition of many foods, condiments, fragrances and flavors, and petroleum waxes and a real-time quantitative prediction of their odor quality grades and many key component concentrations.
-
公开(公告)号：US10948467B2
公开(公告)日：2021-03-16
申请号：US16642531
申请日：2018-05-30
发明人： Daqi Gao , Xiaoqin Zhang , Zejian Wang , Liming Zhao
摘要： Provided is an online centralized monitoring and analysis system using an electronic nose instrument for multi-point malodorous gases, and the system includes an electronic nose instrument, which connects with multiple monitoring points through pipes. On-site malodorous gases in the maximum range of 2.5 km are drawn into the electronic nose instrument within 1 min by the external vacuum pump, and forced to flow through an annular working chamber of a gas sensor array for 30 s by the internal vacuum pump periodically. The modular convolution neural networks online learn the recent time-series responses of the gas sensor array and predict their coming responses, and the modular deep neural networks offline set up the relationship between the responses and multiple concentration items according to odor big data. The electronic nose instrument monitors up to 10 pollution sites cyclically and uses the cascade machine learning model to online predict one dimensionless odor-unit (OU) concentration index value and 10 specified-component concentration index values of malodorous gases.
-
公开(公告)号：US20230152287A1
公开(公告)日：2023-05-18
申请号：US17794767
申请日：2020-07-18
发明人： Zejian Wang , Daqi Gao , Xiaoqin Zhang , Bo Li , Fang Cai , Jianhua Li , Mingjian Cheng
摘要： Provided is an electronic nose instrument based on gas sensitivity and gas chromatography and an online analysis method of multiple state parameters of fermentation and malodorous pollutant processes. The main constituent units of the instrument include a gas sensor array module, a capillary gas chromatographic column module, an automatic gas sampling module, and a computer control and analysis module. A single gas sampling period is T0=300-600s. Not only are two flow rates and two accumulative volumes of gas sampling unequal to each other, but also two starting time points are not synchronized to each other, between the gas sensor array module and the gas chromatography module. 3 pieces of sensitive information, i.e., a steady-state peak value, a corresponding peak time value and an area under a whole curve, are selected from a response curve of a single gas sensor with a 60s duration by the computer control and analysis module, or 48 pieces of gas sensitive information in total, and 21 pieces of sensitive information, i.e., 10 maximum peak values, 10 corresponding retention time values, and 1 area under the whole chromatographic curve, are selected from a semi-separation chromatogram with a duration T0−10 s. Furthermore, the cyclical online identification and intensity and quantitative estimation of multiple indices of odors for five fermentation or malodorous pollution processes with a maximum cyclical gas sampling period T=5T0 are realized by a modular deep convolutional neural network model according to a 69-dimensional normalized fused real-time sensitive pattern and an existing big odor data.
-
公开(公告)号：US10895560B2
公开(公告)日：2021-01-19
申请号：US16651722
申请日：2018-03-18
发明人： Daqi Gao , Zejian Wang , Xiaoqin Zhang , Jiamin Song
摘要： Provided is a sensory quality evaluation method for tobacco and tobacco products using an electronic nose instrument. The electronic nose instrument includes a gas sensor array module, an automatic smoke sampling system, a computer control and data analysis system, and an automatic ignition device. These components are integrated in a test box to make the instrument be structure miniaturization and work automation. The large tobacco data is established, in which the relationship between the responses of gas sensor array and the brand labels and sensory quality index scores by testing a large number of standard cigarette samples. A cascade type of modular neural networks is proposed with revised activation function and new decision-making and quantification rules to simulate the smoking and evaluating process of the professional panel. The electronic nose instrument and method realize on-site detection, discrimination and quality score estimation of a large number of tobacco and tobacco products.
-
-
-
搜索结果
4 条记录 (耗时 0.018 秒)
