Background The lint percentage of seed cotton is one of the most important parameters for evaluating seed cotton quality and affects its price.The traditional measuring method of lint percentage is labor-intensive and...Background The lint percentage of seed cotton is one of the most important parameters for evaluating seed cotton quality and affects its price.The traditional measuring method of lint percentage is labor-intensive and time-consuming;thus,an efficient and accurate measurement method is needed.In recent years,classification-based deep learning and computer vision have shown promise in solving various classification tasks.Results In this study,we propose a new approach for detecting the lint percentage using MobileNetV2 and transfer learning.The model is deployed on a lint percentage detection instrument,which can rapidly and accurately determine the lint percentage of seed cotton.We evaluated the performance of the proposed approach using a dataset comprising 66924 seed cotton images from different regions of China.The results of the experiments showed that the model with transfer learning achieved an average classification accuracy of 98.43%,with an average precision of 94.97%,an average recall of 95.26%,and an average F1-score of 95.20%.Furthermore,the proposed classification model achieved an average accuracy of 97.22%in calculating the lint percentage,showing no significant difference from the performance of experts(independent-sample t-test,t=0.019,P=0.860).Conclusion This study demonstrated the effectiveness of the MobileNetV2 model and transfer learning in calculating the lint percentage of seed cotton.The proposed approach is a promising alternative to traditional methods,providing a rapid and accurate solution for the industry.展开更多
Existing nondestructive detection methods were adopted to test the compressive strength of grouted concrete block masonry,i.e.the rebound method,pulling-out method and core drilling method were employed to test the st...Existing nondestructive detection methods were adopted to test the compressive strength of grouted concrete block masonry,i.e.the rebound method,pulling-out method and core drilling method were employed to test the strength of block,mortar and grouted concrete,respectively.The suitability of these methods for the testing of strength of grouted concrete block masonry was discussed,and the comprehensive strength of block masonry was appraised by combining existing nondestructive or micro-destructive detection methods.The nondestructive detection test on 25 grouted concrete block masonry specimens was carried out.Experimental results show that these methods mentioned above are applicable for the strength detection of grouted concrete block masonry.Moreover,the formulas of compressive strength,detection methods and proposals are given as well.展开更多
The ultrasonic computed tomography （USCT） method is derived from the basic principles of X-ray section scanning. This method records the arriving times of ultrasonic wave between the probes and the sources to ealcul...The ultrasonic computed tomography （USCT） method is derived from the basic principles of X-ray section scanning. This method records the arriving times of ultrasonic wave between the probes and the sources to ealculate the elastic wave velocity values in the section using the arrival times. Through analyzed the distribution Of elastic wave velocity in aim area, the information of the strength and the homogeneity of the investigated zone could be got indirectly. The authors introduced the operational principle of USCT and a practical case of using this method to detect the interior defects in large scale concrete structural member. Compared with other exploration methods, this method is more efficient and accurate.展开更多
The defects of remanufacturing coatings,such as micro-cracks,micro-pores,oxide inclusion,and fatigue cracks producing in the service process have great influence on the qualities and lives of remanufacturing coatings....The defects of remanufacturing coatings,such as micro-cracks,micro-pores,oxide inclusion,and fatigue cracks producing in the service process have great influence on the qualities and lives of remanufacturing coatings.This paper summarizes several methods used for detecting coating defects,including ray method,ultrasonic method,eddy method,magnetic memory method,acoustic emission method.The advantages and limitations of the above methods are also discussed.The detection results by ray method are visualized,and it is easy to achieve qualitative,quantitative and locating detection,but this method has incipient fault and low detecting sensitivity.Ultrasonic detection can exactly locate defects,and it is sensitive to plane defects,but the detection has dead zones,and it is inconvenient to perform qualitative and quantitative measurement.Eddy method detects fast,but it only can detect conductive materials,and is difficult to achieve qualitative,quantitative and locating detection.Magnetic memory method is sensitive to ferromagnetic materials,but it can not detect nonferromagnetic materials and is difficult to attain quantitative measurement.Acoustic emission method has an extensive detection range and high sensitivity,but it has big noise interference,and is hard to achieve qualitative detection.In conclusion,it describes the application prospect of each method for detecting coating.展开更多
Electromagnetic self-induction theory and computer are adopted and study of online monitoring technique for wire-core belt is conducted, the study shows that there is direct proportion between distance Ⅰ of broken en...Electromagnetic self-induction theory and computer are adopted and study of online monitoring technique for wire-core belt is conducted, the study shows that there is direct proportion between distance Ⅰ of broken ends and output volt Ⅴ, when Ⅰ ≥60 mm, Ⅴ keeps constantly, the running speed v of wire-core belt has no big effect on output volt Ⅴ, there is inverse proportion between the height h from probe to the surface of the belt and output volt Ⅴ, when h≥30 mm, Ⅴ tends to be zero. Based on the test result, on-line monitoring installation is developed, the practice proved that the accuracy of broken wire monitoring can be above 95%, the monitoring accuracy of joint twitch can be 0 .04 Ⅴ/mm.展开更多
This paper proposed a high-sensitivity phase imaging eddy current magneto-optical (PI-ECMO) system for carbon fiber reinforced polymer (CFRP) defect detection. In contrast to other eddy current-based detection systems...This paper proposed a high-sensitivity phase imaging eddy current magneto-optical (PI-ECMO) system for carbon fiber reinforced polymer (CFRP) defect detection. In contrast to other eddy current-based detection systems, the proposed system employs a fixed position excitation coil while enabling the detection point to move within the detection region. This configuration effectively mitigates the interference caused by the lift-off effect, which is commonly observed in systems with moving excitation coils. Correspondingly, the relationship between the defect characteristics (orientation and position) and the surface vertical magnetic field distribution (amplitude and phase) is studied in detail by theoretical analysis and numerical simulations. Experiments conducted on woven CFRP plates demonstrate that the designed PI-ECMO system is capable of effectively detecting both surface and internal cracks, as well as impact defects. The excitation current is significantly reduced compared with traditional eddy current magneto-optical (ECMO) systems.展开更多
目的建立适用于抹茶品质的可见近红外(visible-nearinfrared,Vis-NIR)光谱快速无损检测模型以实现多种品质指标的定量分析。方法通过Vis-NIR获取抹茶样本的光谱数据,使用一阶导数(first derivative,1^(st))光谱预处理方法,最后采用自助...目的建立适用于抹茶品质的可见近红外(visible-nearinfrared,Vis-NIR)光谱快速无损检测模型以实现多种品质指标的定量分析。方法通过Vis-NIR获取抹茶样本的光谱数据,使用一阶导数(first derivative,1^(st))光谱预处理方法,最后采用自助软收缩法(bootstrapping soft shrinkage,BOSS)、迭代变量子集优化法(iterative variable subset optimization,IVSO)和竞争性自适应重加权采样法(competitive adaptive reweighted sampling,CARS)筛选光谱特征变量,构建抹茶品质指标的偏最小二乘(partial least square,PLS)预测模型,探究光谱信息与茶多酚、游离氨基酸、酚氨比、咖啡碱和可溶性糖之间的定量关系。结果构建的Vis-NIR的CARS-PLS预测模型在抹茶品质指标含量预测方面均获得了最佳结果,预测相关系数(correlation coefficient in the prediction set,Rp)分别为0.9227、0.8906、0.9243、0.9381和0.9522;预测均方根误差(root mean square error in the prediction set,RMSEP)分别为0.867、0.337、0.557、0.216和0.440。结论本研究采用的Vis-NIR光谱技术综合了可见光、短波近红外和长波近红外的优势,在快速无损预测多种抹茶品质指标方面具有良好应用潜力,为抹茶品质的快速无损高效检测提供理论依据和技术支撑。展开更多
基金National Natural Science Foundation of China(Grant number:11904327,61905223,and 62073299)Training Plan of Young Backbone Teachers in Universities of Henan Province(2023GGJS087)+1 种基金Henan Provincial Science and Technology Research Project(222102110279,222102210085,and 242102210157)Project of Central Plains Science and Technology Innovation Leading Talents(224200510026).
文摘Background The lint percentage of seed cotton is one of the most important parameters for evaluating seed cotton quality and affects its price.The traditional measuring method of lint percentage is labor-intensive and time-consuming;thus,an efficient and accurate measurement method is needed.In recent years,classification-based deep learning and computer vision have shown promise in solving various classification tasks.Results In this study,we propose a new approach for detecting the lint percentage using MobileNetV2 and transfer learning.The model is deployed on a lint percentage detection instrument,which can rapidly and accurately determine the lint percentage of seed cotton.We evaluated the performance of the proposed approach using a dataset comprising 66924 seed cotton images from different regions of China.The results of the experiments showed that the model with transfer learning achieved an average classification accuracy of 98.43%,with an average precision of 94.97%,an average recall of 95.26%,and an average F1-score of 95.20%.Furthermore,the proposed classification model achieved an average accuracy of 97.22%in calculating the lint percentage,showing no significant difference from the performance of experts(independent-sample t-test,t=0.019,P=0.860).Conclusion This study demonstrated the effectiveness of the MobileNetV2 model and transfer learning in calculating the lint percentage of seed cotton.The proposed approach is a promising alternative to traditional methods,providing a rapid and accurate solution for the industry.
文摘Existing nondestructive detection methods were adopted to test the compressive strength of grouted concrete block masonry,i.e.the rebound method,pulling-out method and core drilling method were employed to test the strength of block,mortar and grouted concrete,respectively.The suitability of these methods for the testing of strength of grouted concrete block masonry was discussed,and the comprehensive strength of block masonry was appraised by combining existing nondestructive or micro-destructive detection methods.The nondestructive detection test on 25 grouted concrete block masonry specimens was carried out.Experimental results show that these methods mentioned above are applicable for the strength detection of grouted concrete block masonry.Moreover,the formulas of compressive strength,detection methods and proposals are given as well.
基金Supported by Project of the National High Technology Research and Development Program of China(No.2007AA06Z215)
文摘The ultrasonic computed tomography （USCT） method is derived from the basic principles of X-ray section scanning. This method records the arriving times of ultrasonic wave between the probes and the sources to ealculate the elastic wave velocity values in the section using the arrival times. Through analyzed the distribution Of elastic wave velocity in aim area, the information of the strength and the homogeneity of the investigated zone could be got indirectly. The authors introduced the operational principle of USCT and a practical case of using this method to detect the interior defects in large scale concrete structural member. Compared with other exploration methods, this method is more efficient and accurate.
基金National Natural Science Foundations of China(50975285,50735006)Advanced Maintenance Research Project(9140A270304090C8501)+1 种基金Equipment Research ProjectFundamental Research Funds for the Central Universities(2009PY07)
文摘The defects of remanufacturing coatings,such as micro-cracks,micro-pores,oxide inclusion,and fatigue cracks producing in the service process have great influence on the qualities and lives of remanufacturing coatings.This paper summarizes several methods used for detecting coating defects,including ray method,ultrasonic method,eddy method,magnetic memory method,acoustic emission method.The advantages and limitations of the above methods are also discussed.The detection results by ray method are visualized,and it is easy to achieve qualitative,quantitative and locating detection,but this method has incipient fault and low detecting sensitivity.Ultrasonic detection can exactly locate defects,and it is sensitive to plane defects,but the detection has dead zones,and it is inconvenient to perform qualitative and quantitative measurement.Eddy method detects fast,but it only can detect conductive materials,and is difficult to achieve qualitative,quantitative and locating detection.Magnetic memory method is sensitive to ferromagnetic materials,but it can not detect nonferromagnetic materials and is difficult to attain quantitative measurement.Acoustic emission method has an extensive detection range and high sensitivity,but it has big noise interference,and is hard to achieve qualitative detection.In conclusion,it describes the application prospect of each method for detecting coating.
文摘Electromagnetic self-induction theory and computer are adopted and study of online monitoring technique for wire-core belt is conducted, the study shows that there is direct proportion between distance Ⅰ of broken ends and output volt Ⅴ, when Ⅰ ≥60 mm, Ⅴ keeps constantly, the running speed v of wire-core belt has no big effect on output volt Ⅴ, there is inverse proportion between the height h from probe to the surface of the belt and output volt Ⅴ, when h≥30 mm, Ⅴ tends to be zero. Based on the test result, on-line monitoring installation is developed, the practice proved that the accuracy of broken wire monitoring can be above 95%, the monitoring accuracy of joint twitch can be 0 .04 Ⅴ/mm.
基金the National Natural Science Foundation of China under Grants No.U2030205,No.62003075,No.61903065,and No.62003074Sichuan Science and Technology Planning Project under Grant No.2022JDJQ0040.
文摘This paper proposed a high-sensitivity phase imaging eddy current magneto-optical (PI-ECMO) system for carbon fiber reinforced polymer (CFRP) defect detection. In contrast to other eddy current-based detection systems, the proposed system employs a fixed position excitation coil while enabling the detection point to move within the detection region. This configuration effectively mitigates the interference caused by the lift-off effect, which is commonly observed in systems with moving excitation coils. Correspondingly, the relationship between the defect characteristics (orientation and position) and the surface vertical magnetic field distribution (amplitude and phase) is studied in detail by theoretical analysis and numerical simulations. Experiments conducted on woven CFRP plates demonstrate that the designed PI-ECMO system is capable of effectively detecting both surface and internal cracks, as well as impact defects. The excitation current is significantly reduced compared with traditional eddy current magneto-optical (ECMO) systems.
文摘目的建立适用于抹茶品质的可见近红外(visible-nearinfrared,Vis-NIR)光谱快速无损检测模型以实现多种品质指标的定量分析。方法通过Vis-NIR获取抹茶样本的光谱数据,使用一阶导数(first derivative,1^(st))光谱预处理方法,最后采用自助软收缩法(bootstrapping soft shrinkage,BOSS)、迭代变量子集优化法(iterative variable subset optimization,IVSO)和竞争性自适应重加权采样法(competitive adaptive reweighted sampling,CARS)筛选光谱特征变量,构建抹茶品质指标的偏最小二乘(partial least square,PLS)预测模型,探究光谱信息与茶多酚、游离氨基酸、酚氨比、咖啡碱和可溶性糖之间的定量关系。结果构建的Vis-NIR的CARS-PLS预测模型在抹茶品质指标含量预测方面均获得了最佳结果,预测相关系数(correlation coefficient in the prediction set,Rp)分别为0.9227、0.8906、0.9243、0.9381和0.9522;预测均方根误差(root mean square error in the prediction set,RMSEP)分别为0.867、0.337、0.557、0.216和0.440。结论本研究采用的Vis-NIR光谱技术综合了可见光、短波近红外和长波近红外的优势,在快速无损预测多种抹茶品质指标方面具有良好应用潜力,为抹茶品质的快速无损高效检测提供理论依据和技术支撑。
