{"title":"结合支持向量机神经网络的铜、铁氧化物传感器阵列实现VOCs气体分类与浓度预测","authors":"Xiao Li;Meihua Li;Ruiqi Li;Weiyi Li","doi":"10.1109/JSEN.2025.3526253","DOIUrl":null,"url":null,"abstract":"CuFe2O4/<inline-formula> <tex-math>$\\alpha $ </tex-math></inline-formula>-Fe2O3 and CuO/<inline-formula> <tex-math>$\\alpha $ </tex-math></inline-formula>-Fe2O3 heterojunctions were synthesized by solvothermal modulation of the Cu to Fe ratio, and highly sensitive volatile organic compounds (VOCs) sensing materials were successfully prepared for the self-building of sensor arrays. The measured responses of the sensor arrays were functionally fitted and later combined with a support vector machine (SVM) algorithm to classify and predict the concentration of VOCs gases. The optimal working temperature of the four types of sensors prepared in this article is <inline-formula> <tex-math>$240~^{\\circ }$ </tex-math></inline-formula>C, and the optimal working temperature of the previously working sensors is <inline-formula> <tex-math>$260~^{\\circ }$ </tex-math></inline-formula>C. Then, the dynamic corresponding test of VOC gas from 10 to 100 ppm at their respective optimal operating temperature showed good response results for the seven types of sensors. Among them, S500 has the best response to five VOC gases, and its response to ammonia, benzene, methanol, formaldehyde, and n-butanol at 100 ppm is 5.07, 5.08, 11.76, 10.10, and 46.67, respectively. The sensor array has good performances to VOCs gas in the simulated experimental environment, and the combination with SVM algorithm achieves good results in VOCs classification and concentration prediction.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 5","pages":"8759-8765"},"PeriodicalIF":4.3000,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Copper and Iron Oxide Sensor Arrays Combined With SVM Neural Networks to Achieve Classification and Concentration Prediction of VOCs Gases\",\"authors\":\"Xiao Li;Meihua Li;Ruiqi Li;Weiyi Li\",\"doi\":\"10.1109/JSEN.2025.3526253\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"CuFe2O4/<inline-formula> <tex-math>$\\\\alpha $ </tex-math></inline-formula>-Fe2O3 and CuO/<inline-formula> <tex-math>$\\\\alpha $ </tex-math></inline-formula>-Fe2O3 heterojunctions were synthesized by solvothermal modulation of the Cu to Fe ratio, and highly sensitive volatile organic compounds (VOCs) sensing materials were successfully prepared for the self-building of sensor arrays. The measured responses of the sensor arrays were functionally fitted and later combined with a support vector machine (SVM) algorithm to classify and predict the concentration of VOCs gases. The optimal working temperature of the four types of sensors prepared in this article is <inline-formula> <tex-math>$240~^{\\\\circ }$ </tex-math></inline-formula>C, and the optimal working temperature of the previously working sensors is <inline-formula> <tex-math>$260~^{\\\\circ }$ </tex-math></inline-formula>C. Then, the dynamic corresponding test of VOC gas from 10 to 100 ppm at their respective optimal operating temperature showed good response results for the seven types of sensors. Among them, S500 has the best response to five VOC gases, and its response to ammonia, benzene, methanol, formaldehyde, and n-butanol at 100 ppm is 5.07, 5.08, 11.76, 10.10, and 46.67, respectively. The sensor array has good performances to VOCs gas in the simulated experimental environment, and the combination with SVM algorithm achieves good results in VOCs classification and concentration prediction.\",\"PeriodicalId\":447,\"journal\":{\"name\":\"IEEE Sensors Journal\",\"volume\":\"25 5\",\"pages\":\"8759-8765\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2025-01-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Sensors Journal\",\"FirstCategoryId\":\"103\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10839257/\",\"RegionNum\":2,\"RegionCategory\":\"综合性期刊\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Sensors Journal","FirstCategoryId":"103","ListUrlMain":"https://ieeexplore.ieee.org/document/10839257/","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Copper and Iron Oxide Sensor Arrays Combined With SVM Neural Networks to Achieve Classification and Concentration Prediction of VOCs Gases
CuFe2O4/$\alpha $ -Fe2O3 and CuO/$\alpha $ -Fe2O3 heterojunctions were synthesized by solvothermal modulation of the Cu to Fe ratio, and highly sensitive volatile organic compounds (VOCs) sensing materials were successfully prepared for the self-building of sensor arrays. The measured responses of the sensor arrays were functionally fitted and later combined with a support vector machine (SVM) algorithm to classify and predict the concentration of VOCs gases. The optimal working temperature of the four types of sensors prepared in this article is $240~^{\circ }$ C, and the optimal working temperature of the previously working sensors is $260~^{\circ }$ C. Then, the dynamic corresponding test of VOC gas from 10 to 100 ppm at their respective optimal operating temperature showed good response results for the seven types of sensors. Among them, S500 has the best response to five VOC gases, and its response to ammonia, benzene, methanol, formaldehyde, and n-butanol at 100 ppm is 5.07, 5.08, 11.76, 10.10, and 46.67, respectively. The sensor array has good performances to VOCs gas in the simulated experimental environment, and the combination with SVM algorithm achieves good results in VOCs classification and concentration prediction.
期刊介绍:
The fields of interest of the IEEE Sensors Journal are the theory, design , fabrication, manufacturing and applications of devices for sensing and transducing physical, chemical and biological phenomena, with emphasis on the electronics and physics aspect of sensors and integrated sensors-actuators. IEEE Sensors Journal deals with the following:
-Sensor Phenomenology, Modelling, and Evaluation
-Sensor Materials, Processing, and Fabrication
-Chemical and Gas Sensors
-Microfluidics and Biosensors
-Optical Sensors
-Physical Sensors: Temperature, Mechanical, Magnetic, and others
-Acoustic and Ultrasonic Sensors
-Sensor Packaging
-Sensor Networks
-Sensor Applications
-Sensor Systems: Signals, Processing, and Interfaces
-Actuators and Sensor Power Systems
-Sensor Signal Processing for high precision and stability (amplification, filtering, linearization, modulation/demodulation) and under harsh conditions (EMC, radiation, humidity, temperature); energy consumption/harvesting
-Sensor Data Processing (soft computing with sensor data, e.g., pattern recognition, machine learning, evolutionary computation; sensor data fusion, processing of wave e.g., electromagnetic and acoustic; and non-wave, e.g., chemical, gravity, particle, thermal, radiative and non-radiative sensor data, detection, estimation and classification based on sensor data)
-Sensors in Industrial Practice