CN113267534A - Manufacturing method of intelligent gas identification system - Google Patents

Manufacturing method of intelligent gas identification system Download PDF

Info

Publication number
CN113267534A
CN113267534A CN202110826590.3A CN202110826590A CN113267534A CN 113267534 A CN113267534 A CN 113267534A CN 202110826590 A CN202110826590 A CN 202110826590A CN 113267534 A CN113267534 A CN 113267534A
Authority
CN
China
Prior art keywords
module
gas
gas identification
manufacturing
intelligent
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110826590.3A
Other languages
Chinese (zh)
Inventor
刘弘禹
潘宁
孟钢
方晓东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Shengfang Technology Co ltd
Original Assignee
Shenzhen Shengfang Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Shengfang Technology Co ltd filed Critical Shenzhen Shengfang Technology Co ltd
Priority to CN202110826590.3A priority Critical patent/CN113267534A/en
Publication of CN113267534A publication Critical patent/CN113267534A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K3/00—Apparatus or processes for manufacturing printed circuits
    • H05K3/0002—Apparatus or processes for manufacturing printed circuits for manufacturing artworks for printed circuits
    • H—ELECTRICITY
    • H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05K—PRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K3/00—Apparatus or processes for manufacturing printed circuits
    • H05K3/0005—Apparatus or processes for manufacturing printed circuits for designing circuits by computer

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Manufacturing & Machinery (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Optimization (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computational Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Biomedical Technology (AREA)
  • Electrochemistry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Operations Research (AREA)
  • Biophysics (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Computational Linguistics (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Computer Hardware Design (AREA)
  • Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)

Abstract

The invention discloses a manufacturing method of an intelligent gas identification system. The invention discloses a manufacturing method of an intelligent gas identification system, which comprises the following steps: dividing an intelligent gas identification system according to modules; designing a gas identification circuit schematic diagram according to each module; drawing a circuit diagram of the gas identification circuit board, and manufacturing the gas identification circuit board; and programming in the processor module so as to obtain the intelligent deep-learning gas identification model through the gas identification model building module. The manufacturing method of the intelligent gas identification system comprehensively plans the manufacturing of the system before manufacturing, reduces the technical difficulty for manufacturing the intelligent gas identification system in the later period, improves the manufacturing efficiency, has strong logicality on the whole, has reasonable and compact steps, can ensure the precision and high integration of the manufactured system, can manufacture the intelligent gas identification system by testing only a single gas sensor, and is simple and easy.

Description

Manufacturing method of intelligent gas identification system
Technical Field
The invention relates to the technical field of intelligent gas identification, in particular to a manufacturing method of an intelligent gas identification system.
Background
In addition, in food detection, whether food is deteriorated or not can be judged through the identification of specific gas, the eating safety is guaranteed, the quality states of tea leaves and wine can be judged, the quality levels of the tea leaves and the wine can be effectively distinguished, and therefore the gas detection and identification are necessary.
The existing gas detector generally determines the mass ratio of molecules or atoms in gas through spectral analysis so as to effectively identify the gas, but the gas detector is very complex in manufacture, very difficult in technology, extremely high in precision requirement and extremely expensive in manufacturing cost, the gas identification is realized through spectral analysis, no matter the labor cost or the equipment cost is high, the precise instrument is not required in all places, an electronic nose system based on a sensor array is also arranged on the market, a large number of gas sensors are required when the system is manufactured, and the problems of complex manufacturing process, poor sensor selectivity, complex operation, multiple redundancy characteristics, long-term drift, multiple consumables, large volume and low integration level exist.
Disclosure of Invention
Based on this, the invention aims to provide a manufacturing method of an intelligent gas identification system, which has been comprehensively planned before the intelligent gas identification system is manufactured, reduces the technical difficulty for manufacturing the intelligent gas identification system in the later period, and improves the manufacturing efficiency.
The purpose of the invention is realized by the following technical scheme:
a manufacturing method of an intelligent gas identification system comprises the following steps:
the intelligent gas identification system is at least divided into a gas sensor module, a processor module, a voltage modulation module, a communication module, a data acquisition module, a data processing module and a gas identification model building module, wherein the gas sensor module comprises at least one gas sensor;
designing a gas identification circuit schematic diagram according to each module, wherein a data acquisition module is respectively connected with a gas sensor module and a processor module, a voltage modulation module is connected with the processor module and the gas sensor module, the processor module is connected with a data processing module through a communication module, and the data processing module is connected with a gas identification model construction module;
drawing a gas identification circuit board circuit diagram according to the gas identification circuit schematic diagram, and manufacturing to obtain a gas identification circuit board;
programming is carried out in the processor module, so that after the processor module receives a starting modulation signal, the voltage modulation module is controlled to carry out voltage modulation on the gas sensor module, meanwhile, the data acquisition module acquires training response data of the gas sensor module under the voltage modulation and transmits the training response data to the processor module, the data processing module carries out preprocessing and feature extraction processing on the training response data transmitted by the processor module to obtain a gas training data set, and the gas identification model building module feeds the gas training data set obtained by the data processing module into a deep neural network for deep learning to obtain an intelligent gas identification model for deep learning.
The manufacturing method of the intelligent gas identification system comprises the steps of dividing the intelligent gas identification system to be manufactured into modules, designing a gas identification circuit schematic diagram according to each module, drawing a gas identification circuit board schematic diagram according to the gas identification circuit schematic diagram, manufacturing the gas identification circuit board, and programming on a processor module. The manufacturing method of the intelligent gas identification system has the advantages that the system is comprehensively planned before the intelligent gas identification system is manufactured, the technical difficulty is reduced for manufacturing the intelligent gas identification system in the later period, the manufacturing efficiency is improved, the manufacturing method of the intelligent gas identification system has strong logicality on the whole, the steps are reasonable and compact, the precision and the high integration of the manufactured system can be ensured, and the intelligent gas identification system can be manufactured by testing only a single gas sensor through the manufacturing method of the intelligent gas identification system, so that the problems of poor selectivity, complex operation, multiple redundancy characteristics, long-term drift, multiple consumables, large volume and low integration level of the gas sensor in the manufacturing process are solved.
Further preferably, the method for manufacturing the intelligent gas identification system further comprises the step of compiling a user interface program in the processor module, so that the processor realizes one or more of a voltage modulation start-stop control function, a data acquisition start-stop control function, a data processing start-stop control function, a training response data feedback function and a deep learning result display function of the intelligent gas identification model.
Further preferably, the writing of the user interface program in the processor module is specifically writing the user interface program in the HTML language or PYTHON language in the processor module.
Preferably, the step of drawing the gas identification circuit board circuit diagram according to the gas identification circuit schematic diagram and manufacturing the gas identification circuit board includes the steps of welding the gas identification circuit board according to the gas identification circuit diagram and welding and debugging the gas identification circuit board.
Further preferably, in the step of designing the gas identification circuit schematic diagram according to each module, the gas sensor in the gas sensor module is a TGS2602 ceramic sheet type gas sensor of which the gas sensitive material is tin oxide, the main control chip of the processor module is an ESP32-S chip, the voltage modulation module is provided with a digital-to-analog conversion sub-module and an operational amplification sub-module, the digital-to-analog conversion sub-module is connected with the processor module and the operational amplification sub-module, the operational amplification sub-module is connected with the gas sensor module, the data acquisition module is respectively connected with the gas sensor module and the processor module, and the processor module is connected with the data processing module through the communication module.
Further preferably, in the step of designing the gas identification circuit schematic diagram according to each module, the communication module is a WIFI communication module or a bluetooth communication module.
Further preferably, in the step of designing the gas identification circuit schematic diagram according to each module, a gas sensor in the gas sensor module adopts an MQ-5 ceramic tube type gas sensor of which a gas sensitive material is tin oxide, a processor of the processor module adopts a 16F877A single chip microcomputer, the voltage modulation module adopts a PWM voltage modulation module, and the communication module adopts a serial port communication module.
Further preferably, the programming in the processor module enables the data processing module to perform preprocessing and feature extraction processing on the training response data transmitted by the data acquisition module, including enabling the data processing module to perform sensitivity preprocessing, concentration normalization preprocessing and discrete wavelet transform feature extraction processing on the training response data transmitted by the data acquisition module.
Further preferably, the sensitivity pretreatment specifically adopts the formula G (cc, u, t) = Rair(t)/ Rgas(cc, u, t); the concentration normalization pretreatment specifically adopts the formula Y (cc, u, t) = (G (cc, u, t) -G (cc, u, t)min)/ (G(cc,u,t)max- G(cc,u,t)min) Carrying out the following steps; the discrete wavelet transform characteristic extraction processing is specifically carried out by using Daubechies wavelets; where t represents the sampling time, u represents the u-th test, cc represents a certain gas or a certain gas concentration, R represents the training response signal or the response signal to be identified, G represents the sensitivity of the signal, R represents the sensitivity of the signalair(t) represents the training response signal of the air at the sampling time t, Rgas(cc, u, t) represents a training response signal of the gas at the u-th test gas concentration cc at the sampling time t, Y (cc, u, t) represents a concentration normalization pre-processing expression, G (cc, u, t) represents the sensitivity of the signal at the u-th test gas concentration cc at the sampling time t, G (cc, u, t)maxG (cc, u, t) which represents the maximum value of the sensitivity of the signal at the u-th test gas concentration cc at the sampling time tminRepresents the minimum value of the sensitivity of the signal at the u-th test gas concentration cc at the sampling time t.
Further preferably, the processor module is programmed to control the voltage modulation module to perform voltage modulation on the gas sensor module after the processor module receives the start modulation signal, and the adopted voltage modulation waveform is one or a combination of square waves, step waves, sawtooth waves, triangular waves or sine waves; and programming in the processor module to enable the gas recognition model building module to feed the gas training data set into the deep neural network for deep learning, so that the deep neural network in the intelligent gas recognition model for deep learning adopts one of a deep Convolutional Neural Network (CNN), a deep Back Propagation Neural Network (BPNN) and a deep cyclic neural network (RNN).
Compared with the prior art, the manufacturing method of the intelligent gas identification system comprises the steps of dividing the intelligent gas identification system to be manufactured into modules, designing a gas identification circuit schematic diagram according to each module, drawing a gas identification circuit board schematic diagram according to the gas identification circuit schematic diagram, manufacturing the gas identification circuit board, and programming on the processor module. The manufacturing method of the intelligent gas identification system has the advantages that the system is comprehensively planned before the intelligent gas identification system is manufactured, the technical difficulty is reduced for manufacturing the intelligent gas identification system in the later period, the manufacturing efficiency is improved, the manufacturing method of the intelligent gas identification system has strong logicality on the whole, the steps are reasonable and compact, the precision and the high integration of the manufactured system can be ensured, and the intelligent gas identification system can be manufactured by testing only a single gas sensor through the manufacturing method of the intelligent gas identification system, so that the problems of poor selectivity, complex operation, multiple redundancy characteristics, long-term drift, multiple consumables, large volume and low integration level of the gas sensor in the manufacturing process are solved.
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
Drawings
Fig. 1 is a flow chart of a method of making an intelligent gas identification system of the present invention.
Fig. 2 is a schematic block diagram of an intelligent gas identification system partitioned by a method of manufacturing the intelligent gas identification system of the present invention.
Fig. 3 is a schematic circuit diagram of a main control chip of the intelligent gas identification system manufacturing method using an ESP32-S chip as a processor module.
Fig. 4 is a circuit for implementing the voltage modulation module manufactured by the method for manufacturing the intelligent gas identification system of the present invention.
Fig. 5 is a schematic circuit diagram of the connection of several gas sensors by the method of making the intelligent gas identification system of the present invention.
Fig. 6 is a schematic view of a gas identification circuit board manufactured by the method of manufacturing the intelligent gas identification system of the present invention.
Fig. 7 is a CNN structural diagram of a gas identification model constructed by the method of manufacturing an intelligent gas identification system of the present invention.
FIG. 8 is a schematic view of a user interface programmed into a processor module by the method of making the intelligent gas identification system of the present invention.
Detailed Description
The terms of orientation of up, down, left, right, front, back, top, bottom, and the like, referred to or may be referred to in this specification, are defined relative to their configuration, and are relative concepts. Therefore, it may be changed according to different positions and different use states. Therefore, these and other directional terms should not be construed as limiting terms.
The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
A method for manufacturing an intelligent gas identification system, as shown in fig. 1, includes the following steps:
s1: the intelligent gas identification system is at least divided into a gas sensor module, a processor module, a voltage modulation module, a communication module, a data acquisition module, a data processing module and a gas identification model building module, wherein the gas sensor module comprises at least one gas sensor.
Specifically, the gas sensor module with only one gas sensor is preferably adopted, so that the whole technical difficulty in manufacturing the intelligent gas identification system is reduced, and the mutual influence among a plurality of gas sensors is effectively avoided.
S2: the gas identification circuit schematic diagram is designed according to each module, wherein the data acquisition module is respectively connected with the gas sensor module and the processor module, the voltage modulation module is connected with the processor module and the gas sensor module, the processor module is connected with the data processing module through the communication module, and the data processing module is connected with the gas identification model building module. Fig. 2 shows a block schematic diagram of an intelligent gas identification system partitioned by a method of manufacturing the intelligent gas identification system of the present invention.
In an embodiment, in the step of designing the gas identification circuit schematic diagram according to each module, as shown in fig. 3 to 4, a TGS2602 ceramic sheet type gas sensor with a gas sensitive material of tin oxide is used as a gas sensor in the gas sensor module, an ESP32-S chip is used as a main control chip of the processor module, the voltage modulation module is provided with a digital-to-analog conversion sub-module and an operational amplification sub-module, the digital-to-analog conversion sub-module is connected with the processor module and the operational amplification sub-module, the operational amplification sub-module is connected with the gas sensor module, the data acquisition module is respectively connected with the gas sensor module and the processor module, and the processor module is connected with the data processing module through the communication module.
Further, in the step of designing the gas identification circuit schematic diagram according to each module, the communication module adopts a WIFI communication module or a bluetooth communication module to perform wireless communication, thereby reducing the complexity of the internal structure of the intelligent gas identification system and further simplifying the system structure.
Although the method for manufacturing the intelligent gas identification system of the present invention is preferably performed by a single gas sensor, a plurality of gas sensors may be selected, and when the method for manufacturing the intelligent gas identification system of the present invention is performed by a plurality of gas sensors, the connection of the plurality of gas sensors may be realized by a time division multiplexing circuit or a path switching circuit as shown in fig. 5, so as to perform multi-dimensional sampling, increase the data amount reasonably, and improve the accuracy and efficiency of the manufactured intelligent gas identification system in gas identification.
In another embodiment, in the step of designing the gas identification circuit schematic diagram according to each module, a gas sensor in the gas sensor module adopts an MQ-5 ceramic tube type gas sensor of which a gas sensitive material is tin oxide, a processor of the processor module adopts a 16F877A single chip microcomputer, the voltage modulation module adopts a PWM voltage modulation module, and the communication module adopts a serial port communication module. The wired communication can ensure the communication effectiveness among the modules.
S3: and drawing a gas identification circuit board circuit diagram according to the gas identification circuit schematic diagram, and manufacturing to obtain the gas identification circuit board. Fig. 6 is a schematic view showing a gas recognition circuit board manufactured by the method for manufacturing an intelligent gas recognition system according to the present invention, and in this embodiment, the length and width of the gas recognition circuit board are preferably designed to be 60.00 mm.
Specifically, the step of drawing a gas identification circuit board circuit diagram according to the gas identification circuit schematic diagram and manufacturing the gas identification circuit board comprises the steps of welding the gas identification circuit board according to the gas identification circuit board circuit diagram and welding and debugging the gas identification circuit board.
The welding debugging can ensure the long-term effective use of the manufactured gas identification circuit board and also can ensure the safety in use.
S4: programming is carried out in the processor module, so that after the processor module receives a starting modulation signal, the voltage modulation module is controlled to carry out voltage modulation on the gas sensor module, meanwhile, the data acquisition module acquires training response data of the gas sensor module under the voltage modulation and transmits the training response data to the processor module, the data processing module carries out preprocessing and feature extraction processing on the training response data transmitted by the processor module to obtain a gas training data set, and the gas identification model building module feeds the gas training data set obtained by the data processing module into a deep neural network for deep learning to obtain an intelligent gas identification model for deep learning.
Specifically, the programming is performed in the processor module, so that the data processing module performs preprocessing and feature extraction processing on the training response data transmitted by the processor, including sensitivity preprocessing, concentration normalization preprocessing and discrete wavelet transformation feature extraction processing on the training response data transmitted by the processor, so as to ensure the precision and uniformity of the data and facilitate deep learning of the gas identification model.
Further, the sensitivity pretreatment specifically adopts a formula G (cc, u, t) = Rair(t)/ Rgas(cc, u, t); the concentration normalization pretreatment specifically adopts the formula Y (cc, u, t) = (G (cc, u, t) -G (cc, u, t)min)/ (G(cc,u,t)max- G(cc,u,t)min) Carrying out the following steps; the discrete wavelet transform feature extraction processing specifically adopts Daubechies wavelets to perform(ii) a Where t represents the sampling time, u represents the u-th test, cc represents a certain gas or a certain gas concentration, R represents the training response signal or the response signal to be identified, G represents the sensitivity of the signal, R represents the sensitivity of the signalair(t) represents the training response signal of the air at the sampling time t, Rgas(cc, u, t) represents a training response signal of the gas at the u-th test gas concentration cc at the sampling time t, Y (cc, u, t) represents a concentration normalization pre-processing expression, G (cc, u, t) represents the sensitivity of the signal at the u-th test gas concentration cc at the sampling time t, G (cc, u, t)maxG (cc, u, t) which represents the maximum value of the sensitivity of the signal at the u-th test gas concentration cc at the sampling time tminRepresents the minimum value of the sensitivity of the signal at the u-th test gas concentration cc at the sampling time t.
More specifically, the processor module is programmed so that after the processor module receives the start modulation signal, the voltage modulation module is controlled to perform voltage modulation on the gas sensor module, and the adopted voltage modulation waveform is one or a combination of square waves, step waves, sawtooth waves, triangular waves and sine waves. This embodiment uses a voltage modulation preferably using a triangular wave.
More specifically, the programming is carried out in the processor module, so that the gas recognition model building module feeds the gas training data set into the deep neural network for deep learning, and the deep neural network in the obtained deep-learning intelligent gas recognition model adopts one of a deep convolutional neural network CNN, a deep back propagation neural network BPNN and a deep cyclic neural network RNN. Fig. 7 shows a CNN structural diagram of a gas identification model constructed by the method of manufacturing an intelligent gas identification system of the present invention.
Preferably, the method for manufacturing the intelligent gas identification system further comprises S5: and compiling a user interface program in the processor module to enable the processor to realize one or more of a voltage modulation start-stop control function, a data acquisition start-stop control function, a data processing start-stop control function, a training response data feedback function and a deep learning result display function of the intelligent gas identification model.
An HTTP server is established on a processor module for a client to access, control and acquire data, the processor module is used as a server, and multiple platforms such as a PC (personal computer)/a mobile phone/an embedded device can be conveniently accessed to control and acquire data.
Specifically, writing the user interface program in the processor module is specifically writing the user interface program in the processor module by using an HTML language or a PYTHON language. FIG. 8 shows a schematic view of a user interface programmed within a processor module by the method of making the intelligent gas identification system of the present invention.
According to the intelligent gas identification system manufactured by the manufacturing method of the intelligent gas identification system, the gas-sensitive characteristics of the gas sensor are influenced and controlled by the temperature of the device, the response to different gases/smells is different in different working temperature ranges, the gas sensor is subjected to thermal voltage modulation, and then the purposes of identifying and classifying the gases/smells are achieved by combining signal processing, feature extraction and deep learning technologies. The intelligent gas identification system converts the space expansion mode of the traditional electronic nose array technology into the time expansion mode, effectively utilizes the temperature control effect of the gas sensor, develops the characteristic extraction algorithm of the transient thermal modulation response of the single oxide gas sensor, can effectively extract the internal characteristics of different adsorbed gas molecules, greatly expands the odor identification capability of the single gas sensor, is expected to promote the deep application of the metal oxide semiconductor gas sensor in the emerging fields of indoor and outdoor air quality monitoring, food safety, respiration monitoring, automobile manufacturing, danger monitoring and early warning and the like, and realizes the intelligent industrial revolution of the information physical fusion system in the artificial olfaction field.
Compared with the prior art, the manufacturing method of the intelligent gas identification system comprises the steps of dividing the intelligent gas identification system to be manufactured into modules, designing a gas identification circuit schematic diagram according to each module, drawing a gas identification circuit board schematic diagram according to the gas identification circuit schematic diagram, manufacturing the gas identification circuit board, and programming on the processor module. The manufacturing method of the intelligent gas identification system has the advantages that the system is comprehensively planned before the intelligent gas identification system is manufactured, the technical difficulty is reduced for manufacturing the intelligent gas identification system in the later period, the manufacturing efficiency is improved, the manufacturing method of the intelligent gas identification system has strong logicality on the whole, the steps are reasonable and compact, the precision and the high integration of the manufactured system can be ensured, and the intelligent gas identification system can be manufactured by testing only a single gas sensor through the manufacturing method of the intelligent gas identification system, so that the problems of poor selectivity, complex operation, multiple redundancy characteristics, long-term drift, multiple consumables, large volume and low integration level of the gas sensor in the manufacturing process are solved.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.

Claims (10)

1. A manufacturing method of an intelligent gas identification system is characterized by comprising the following steps:
the intelligent gas identification system is at least divided into a gas sensor module, a processor module, a voltage modulation module, a communication module, a data acquisition module, a data processing module and a gas identification model building module, wherein the gas sensor module comprises at least one gas sensor;
designing a gas identification circuit schematic diagram according to each module, wherein a data acquisition module is respectively connected with a gas sensor module and a processor module, a voltage modulation module is connected with the processor module and the gas sensor module, the processor module is connected with a data processing module through a communication module, and the data processing module is connected with a gas identification model construction module;
drawing a gas identification circuit board circuit diagram according to the gas identification circuit schematic diagram, and manufacturing to obtain a gas identification circuit board;
programming is carried out in the processor module, so that after the processor module receives a starting modulation signal, the voltage modulation module is controlled to carry out voltage modulation on the gas sensor module, meanwhile, the data acquisition module acquires training response data of the gas sensor module under the voltage modulation and transmits the training response data to the processor module, the data processing module carries out preprocessing and feature extraction processing on the training response data transmitted by the processor module to obtain a gas training data set, and the gas identification model building module feeds the gas training data set obtained by the data processing module into a deep neural network for deep learning to obtain an intelligent gas identification model for deep learning.
2. The method of claim 1, further comprising programming a user interface program in the processor module such that the processor implements one or more of a voltage modulation start-stop control function, a data acquisition start-stop control function, a data processing start-stop control function, a training response data feedback function, and a deep learning result display function of the intelligent gas identification model.
3. A method of making an intelligent gas identification system as claimed in claim 2, wherein the programming of the user interface program in the processor module is in particular in the HTML language or the PYTHON language.
4. The method for manufacturing an intelligent gas identification system according to claim 1, wherein the step of drawing a gas identification circuit board circuit diagram according to the gas identification circuit schematic diagram and manufacturing the gas identification circuit board comprises the steps of welding the gas identification circuit board according to the gas identification circuit board circuit diagram and welding and debugging the gas identification circuit board.
5. A method of manufacturing an intelligent gas identification system as claimed in any one of claims 1 to 4, it is characterized in that in the step of designing the gas identification circuit schematic diagram according to each module, the gas sensor in the gas sensor module adopts a TGS2602 ceramic chip type gas sensor with tin oxide as a gas sensitive material, the main control chip of the processor module adopts an ESP32-S chip, the voltage modulation module is provided with a digital-to-analog conversion sub-module and an operational amplification sub-module, the digital-to-analog conversion sub-module is connected with the processor module and the operational amplification sub-module, the operational amplification sub-module is connected with the gas sensor module, the data acquisition module is respectively connected with the gas sensor module and the processor module, and the processor module is connected with the data processing module through the communication module.
6. A method for manufacturing an intelligent gas identification system as claimed in claim 5, wherein in the step of designing the gas identification circuit schematic diagram according to each module, the communication module adopts a WIFI communication module or a Bluetooth communication module.
7. A method for manufacturing an intelligent gas identification system according to any one of claims 1-4, wherein in the step of designing a gas identification circuit schematic diagram according to each module, the gas sensors in the gas sensor modules adopt MQ-5 ceramic tube type gas sensors with tin oxide as a gas sensitive material, the processor of the processor module adopts a 16F877A single chip microcomputer, the voltage modulation module adopts a PWM voltage modulation module, and the communication module adopts a serial communication module.
8. A method for making an intelligent gas identification system as claimed in any one of claims 1-4, wherein the programming in the processor module causes the data processing module to perform pre-processing and feature extraction processing on the training response data transmitted by the processor, including causing the data processing module to perform sensitivity pre-processing, concentration normalization pre-processing, and discrete wavelet transform feature extraction processing on the training response data transmitted by the processor.
9. The method of claim 8, wherein the intelligent gas identification system is manufactured byThe sensitivity pretreatment specifically adopts a formula G (cc, u, t) = Rair(t)/ Rgas(cc, u, t); the concentration normalization pretreatment specifically adopts the formula Y (cc, u, t) = (G (cc, u, t) -G (cc, u, t)min)/ (G(cc,u,t)max- G(cc,u,t)min) Carrying out the following steps; the discrete wavelet transform characteristic extraction processing is specifically carried out by using Daubechies wavelets; where t represents the sampling time, u represents the u-th test, cc represents a certain gas or a certain gas concentration, R represents the training response signal or the response signal to be identified, G represents the sensitivity of the signal, R represents the sensitivity of the signalair(t) represents the training response signal of the air at the sampling time t, Rgas(cc, u, t) represents a training response signal of the gas at the u-th test gas concentration cc at the sampling time t, Y (cc, u, t) represents a concentration normalization pre-processing expression, G (cc, u, t) represents the sensitivity of the signal at the u-th test gas concentration cc at the sampling time t, G (cc, u, t)maxG (cc, u, t) which represents the maximum value of the sensitivity of the signal at the u-th test gas concentration cc at the sampling time tminRepresents the minimum value of the sensitivity of the signal at the u-th test gas concentration cc at the sampling time t.
10. The method for manufacturing an intelligent gas identification system according to any one of claims 1-4, wherein the processor module is programmed so that when the processor module receives the start modulation signal, the voltage modulation module is controlled to perform voltage modulation on the gas sensor module, and the adopted voltage modulation waveform is one or a combination of square wave, step wave, sawtooth wave, triangular wave or sine wave; and programming in the processor module to enable the gas recognition model building module to feed the gas training data set into the deep neural network for deep learning, so that the deep neural network in the intelligent gas recognition model for deep learning adopts one of a deep Convolutional Neural Network (CNN), a deep Back Propagation Neural Network (BPNN) and a deep cyclic neural network (RNN).
CN202110826590.3A 2021-07-21 2021-07-21 Manufacturing method of intelligent gas identification system Pending CN113267534A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110826590.3A CN113267534A (en) 2021-07-21 2021-07-21 Manufacturing method of intelligent gas identification system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110826590.3A CN113267534A (en) 2021-07-21 2021-07-21 Manufacturing method of intelligent gas identification system

Publications (1)

Publication Number Publication Date
CN113267534A true CN113267534A (en) 2021-08-17

Family

ID=77236991

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110826590.3A Pending CN113267534A (en) 2021-07-21 2021-07-21 Manufacturing method of intelligent gas identification system

Country Status (1)

Country Link
CN (1) CN113267534A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201867387U (en) * 2010-10-11 2011-06-15 河北农业大学 Ammonia measuring and recording instrument based on a USB (universal serial bus) interface
CN202993473U (en) * 2012-12-25 2013-06-12 长沙学院 Indoor air quality monitoring and controlling device
CN205484171U (en) * 2016-03-10 2016-08-17 沈阳工程学院 Multi -functional combustible gas detection device based on single phase power can measurement system level chip
CN109709163A (en) * 2019-01-17 2019-05-03 中国科学院合肥物质科学研究院 P-type metal-oxide gas transducer and its preparation and application
CN113030194A (en) * 2021-02-03 2021-06-25 中国科学院合肥物质科学研究院 Gas sensor array, three alcohol types and identification method of concentration of three alcohol types

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201867387U (en) * 2010-10-11 2011-06-15 河北农业大学 Ammonia measuring and recording instrument based on a USB (universal serial bus) interface
CN202993473U (en) * 2012-12-25 2013-06-12 长沙学院 Indoor air quality monitoring and controlling device
CN205484171U (en) * 2016-03-10 2016-08-17 沈阳工程学院 Multi -functional combustible gas detection device based on single phase power can measurement system level chip
CN109709163A (en) * 2019-01-17 2019-05-03 中国科学院合肥物质科学研究院 P-type metal-oxide gas transducer and its preparation and application
CN113030194A (en) * 2021-02-03 2021-06-25 中国科学院合肥物质科学研究院 Gas sensor array, three alcohol types and identification method of concentration of three alcohol types

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘宏禹: "氧化物半导体气体传感器的热调制特征提取及VOCs分子识别研究", 《中国优秀博硕士学位论文全文数据库（博士）》 *

Similar Documents

Publication Publication Date Title
Vergara et al. On the performance of gas sensor arrays in open sampling systems using Inhibitory Support Vector Machines
CN104569062B (en) Electronic nose air chamber based on molecular sieve filtration
CN106503458B (en) A kind of surface air temperature data quality control method
KR20190005820A (en) Gas sensor controller
Betta et al. Contaminants detection and classification through a customized IoT-based platform: A case study
CN102590450B (en) Based on the array odor detection element of MEMS technology
CN106841067B (en) A kind of gas sensor and its detection method based on selective wave band
Ziyatdinov et al. Bioinspired early detection through gas flow modulation in chemo-sensory systems
CN205898730U (en) Multichannel polytypic sensor capability test system
CN106053551A (en) Multi-channel multi-type sensor capability test system
CN108614071B (en) Distributed outdoor air quality monitoring precision correction system and parameter updating method
CN101699283A (en) Intelligent food safety detection system and detection method
CN102539628A (en) Device for acquiring field data of various kinds of harmful gas
CN102053109A (en) Electronic tongue sensor array and method for controlling quality of beverage products
EP3928102A1 (en) Systems and methods for learning across multiple chemical sensing units using a mutual latent representation
Simić Design and development of air temperature and relative humidity monitoring system with AVR processor based web server
CN109406588A (en) Soil nitrate-N multi-parameter detecting method and instrument based on ion selective electrode
CN113267534A (en) Manufacturing method of intelligent gas identification system
CN113267535A (en) Intelligent gas identification method and device
CN113533654A (en) Intelligent gas identification method, system, equipment and computer readable storage medium
Das et al. Design of an IoT based real time environment monitoring system using legacy sensors
CN102565878A (en) High-precision movable environment data acquisition device
CN109239207B (en) Electronic nose-based smell identification method and device and electronic nose system
CN109116042A (en) A kind of network communication electronic nose detection system and detection method
Ji et al. Gas detection strategy to suppress flow rate interference baesd on semiconductor sensor dynamic temperature modulation measurement

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210817