检索结果-南通市图书馆

A Pressure Sensor calibration model Based on Support Vector Machine

在线全文

学校读者我要写书评

暂无评论

A Pressure Sensor Calibration Model Based on Support Vector ...

Review of methodological and experimental LIBStechniques for coal analysis and their application in power plants in China

第24届中国控制与决策会议

作者： XIE Wenjun 12 , BAI Peng 2 1. School of Automation, Northwestern Polytechnical University, Xi’an 710072, China2. Engineering Institute, Air Force Engineering University, Xi’an 710038, China

This paper proposed a calibration model of pressure sensor based on Support Vector Machine （SVM）. In practice, the output of the temperature and voltage pressure sensor is nonlinear and easy to be affected by temperature and voltage fluctuation over a wide measuring range. This model used the support vector machine can approach any nonlinear function ability. It established a calibration model with the actual voltage output characteristics and its nonlinear mapping relationship to achieve pressure sensor nonlinearity compensation. The results of experiments showed that the maximum of errors reduced to 0.64% from 22.2%. It can eliminate the temperature and voltage fluctuation influence when obtaining expected linear output from the calibration model output terminal.

关键词： SVM pressure sensor compensation calibration model

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Frontiers of physics 2016年第6期11卷 217-230页

作者： Yang Zhao Lei Zhang Shu-Xia Zhao Yu-Fang Li Yao Gong Lei Dong Wei-Guang Ma Wang-Bao Yin Shun-Chun Yao Ji-Dong Lu Lian-Tuan Xiao Suo-Tang Jia State Key Laboratory of Quantum Optics and Quantum Optics Devices Institute of Laser Spectroscopy Shanxi University Taiyuan 030006 China Collaborative Innovation Center of Extreme Optics Shanxi University Taiyuan 030006 China School of Electric Power South China University of Technology Guangzhou 510640 China

Laser-induced breakdown spectroscopy (LIBS) is an emerging analytical spectroscopy technique. This review presents the main recent developments in China regarding the implementation of LIBS for coal analysis. The paper mainly focuses on the progress of the past few years in the fundamentals, data pretreatment, calibration model, and experimental issues of LIBS and its application to coal analysis. Many important domestic studies focusing on coal quality analysis have been conducted. For example, a proposed novel hybrid quantification model can provide more reproducible quantitative analytical results; the model obtained the average absolute errors (AREs) of 0.42%, 0.05%, 0.07%, and 0.17% for carbon, hydrogen, volatiles, and ash, respectively, and a heat value of 0.07 MJ/kg. Atomic/ionic emission lines and molecular bands, such as CN and C-2, have been employed to generate more accurate analysis results, achieving an ARE of 0.26% and a 0.16% limit of detection (LOD) for the prediction of unburned carbon in fly ashes. Both laboratory and on-line LIBS apparatuses have been developed for field application in coal-fired power plants. We consider that both the accuracy and the repeatability of the elemental and proximate analysis of coal have increased significantly and further efforts will be devoted to realizing large-scale commercialization of coal quality analyzer in China.

关键词： Laser-induced breakdown spectroscopy (LIBS) coal quality elemental analysis proximate analysis calibration model

Gaussian process regression for prediction and confidence analysis of fruit traits by near-infrared spectroscopy

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Food Quality and Safety 2023年第1期7卷 132-137页

作者： Xiaojing Chen Jianxia Xue Xiao Chen Xinyu Zhao Shujat Ali Guangzao Huang College of Electrical and Electronic Engineering Wenzhou UniversityWenzhouChina Wenzhou Institute of Industry&Science WenzhouChina

Detection of fruit traits by using near-infrared(NIR)spectroscopy may encounter out-of-distribution samples that exceed the generalization ability of a constructed calibration ***,confidence analysis for a given prediction is required,but this cannot be done using common calibration models of NIR *** address this issue,this paper studied the Gaussian process regression(GPR)for fruit traits detection using NIR *** mean and variance of the GPR were used as the predicted value and confidence,*** show this,a real NIR data set related to dry matter content measurements in mango was *** to partial least squares regression(PLSR),GPR showed approximately 14%lower root mean squared error(RMSE)for the in-distribution test *** with no confidence analysis,using the variance of GPR to remove abnormal samples made GPR and PLSR showed approximately 58%and 10%lower RMSE on the mixed distribution test set,respectively(when the type 1 error rate was set to 0.1).Compared with traditional one-class classification methods,the variance of the GPR can be used to effectively eliminate poorly predicted samples.

关键词： Near-infrared spectroscopy fruit traits calibration model confidence analysis Gaussian process regression

Rapid and nondestructive detection of watercore and sugar content in Asian pear by near infrared spectroscopy for commercial trade

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2014年第6期7卷 9-15页

作者： Ronnarit Rittiron Sureeporn Narongwongwattana Unaruj Boonprakob Worapa Seehalak Department of Food Engineering Faculty of Engineering at Kamphaengsaen Kasetsart UniversityNakhonpathomThailand Department of Horticulture Faculty of Agriculture at Kamphaengsaen Kasetsart UniversityNakhonpathomThailand

Watercore and sugar content are internal qualities which are impossible for exterior *** the aims of this study were to develop models for nondestructive detection of watercore and predicting sugar content in pear using Near Infrared Spectrosoopy(NIR)tech-nique.A total of 93 samples of Asian pear variety“SH-078”were *** sugar content,spectrum of each fruit was measured in the short wavelength region(700-1100nm)in the reflection mode and the first derivative of spectra were then correlated with the sugar content in juice determined by digital *** equation was performed by multiple linear *** result showed Standard Error of Prediction(SEP)=0.58°Bx,and Bias=*** result from t-test showed that sugar content predicted by NIR was not signifcantly different from the value analyzed by refractometer at 95%*** watercore disorder,NIR measurement was performed over the short wavelength range(700-850 nm)in the transmission *** first derivative spectra were correlated with intemnal *** principle com-ponent analysis(PCA)and partial least squares discriminant analysis(PLSDA)were used to perform discrimination *** accuracy of the PCA model was greater than the PLSDA *** scores from PC1 were separated into two boundaries,one predicted rejected pears with 100%classification accuracy,and the other was accepted pears with 92%*** high accuracy of sugar content determining and watercore detecting by NIR reveal the high efficiency of NIR technique for detecting other internal qualities of fruit in the future.

关键词： NIR internal quality damage calibration model

Prediction of Crude Protein in Ramie by Near-Infrared Spectroscopy(NIR)

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Agricultural Science & Technology 2016年第11期17卷 2657-2660页

作者：彭玉梅蒋欢王旭祎重庆市渝东南农业科学院重庆涪陵408000

[Objective] This study was conducted to evaluate the feasibility of deter- mining crude protein in ramie using near-infrared （NIR） spectrometer. [Method] Par- tial least square regression （PLSR） was performed to establish a calibration model based on 50 samples for predicting the crude protein content in ramie, and the model was validated with data in the validation set consisting of 10 samples. [Result] The correlation coefficient of the model was 0.98. There was a good correla- tion between the predicted values by the near-infrared prediction model and the measured values by chemical analysis, and the relative error was 3.54% on aver- age between the predicted and the measured values. [Conclusion] The results showed that it is feasible to determine crude protein content in ramie using NIR spectroscopy-based prediction model.

关键词： Near-infrared spectroscopy Ramie Crude protein calibration model

Analysis of Protein Content in Panicum miliaceum L. Using Near Infrared Transmittance Spectroscopy

在线全文

学校读者我要写书评

暂无评论

Agricultural Science & Technology 2012年第5期13卷 965-968页

作者：牛宇蒙秋霞张丽珍赵婷婷乔治军牛伟刘根科冯耐红山西省农业科学院农业资源与经济研究所山西太原030006 山西省农业科学院农业环境与资源研究所山西太原030006 山西大学生命科学学院山西太原030006 山西大学生物工程学院山西太原030006 山西省农业科学院农作物品种资源研究所山西太原030031 山西省农业科学院山西太原030006 山西省农业科学院右玉试验站山西右玉037200 山西省农业科学院经济作物研究所山西汾阳032200

[Objective] To explore a method for the rapid determination of protein con- tent in grains of Panicum miliaceum L. [Method] The near infrared transmittance spec- troscopy （NITS） was used to build the mathematical models for the quantitative analy- sis of protein content in the grains. Four combinations of treatment that first derivative and second derivative were respectively combined with partial least squares （PLS） and modified partial least squares （MPLS） were set to compare their effects on the original transmission spectrum. [Result] The predicting effects of the 4 combinations were similar. The optimal combination was first derivative with MPLS, in which the average determination coefficient of validation （RSQ） was 0.880 6, correlation coeffi- cient of cross validation （1-VR） was 0.857 0, standard error of calibration （SEC） was 0.342 4, standard error of cross validation （SECV） was 0.375 1, and the standard er- ror of prediction （SEP） was 0.454. [Conclusion] The constructed NITS model is a rapid way for the determination of protein content in grains of P. miliaceum.

关键词： Near infrared transmittance spectroscopy Panicum miliaceum L. Protein calibration model

calibration Method Based on RBF Neural Networks for Soil Moisture Content Sensor

在线全文

学校读者我要写书评

暂无评论

Agricultural Science & Technology 2010年第2期11卷 140-142页

作者：杨敬锋李亭卢启福陈志民广东融讯信息科技有限公司广东广州510656 广东瑞图万方科技股份有限公司广东顺德528305 中山火炬职业技术学院广东中山528436 华南农业大学公共基础课实验教学中心广东广州510642

Temporal and spatial variation of soil moisture content is significant for crop growth,climate change and the other *** order to overcome shortage of non-linear output voltage of TDR3 soil moisture content sensor and increase soil moisture content data collection and computational efficiency,this paper presents a RBF neural network calibration method of soil moisture content based on TDR3 soil moisture sensor and wireless sensor *** results show that the calibration method is effective...

关键词： calibration model Soil Moisture Sensor Wireless Sensor Networks RBF Neural Networks