为了提高光伏/温差联合发电系统的效率,需要进行最大功率点跟踪(Maximum Power Point Tracking,MPPT)控制。针对传统电导增量法步长固定不变导致跟踪速度慢和稳态误差大的缺点,该研究提出一种恒定电压法和双曲正切型自适应变步长算法结...为了提高光伏/温差联合发电系统的效率,需要进行最大功率点跟踪(Maximum Power Point Tracking,MPPT)控制。针对传统电导增量法步长固定不变导致跟踪速度慢和稳态误差大的缺点,该研究提出一种恒定电压法和双曲正切型自适应变步长算法结合的MPPT控制策略。该策略利用双曲正切函数单调递增、变化速度快的特点,使步长可以根据光强等外界环境条件的变化,自适应地快速调整,同时利用恒定电压法加快追踪的响应速度。Matlab/Simulink软件仿真和硬件试验表明,该研究所提方法在光照强度剧烈变化时,系统能够在15 ms内快速跟踪到最大功率点,同时稳态误差低于0.3%,实现了MPPT控制在跟踪速度和稳态精度方面的同步优化。展开更多
为研究北方寒冷地区管道垂直通风保育猪舍内环境分布规律,以黑龙江省齐齐哈尔市保育猪舍为研究对象,通过计算流体力学(Computational fluid dynamics,CFD)模拟不加挡风板与不同角度挡风板下温度场、风速场和平均空气龄分布情况。设计5...为研究北方寒冷地区管道垂直通风保育猪舍内环境分布规律,以黑龙江省齐齐哈尔市保育猪舍为研究对象,通过计算流体力学(Computational fluid dynamics,CFD)模拟不加挡风板与不同角度挡风板下温度场、风速场和平均空气龄分布情况。设计5种方案,方案1无挡风板,方案2圆柱形挡风板,方案3~5挡风板角度(α)为60°、45°、30°圆台形挡风板。保育猪舍管道垂直通风模型经现场试验验证,结果表明管道垂直通风CFD模型温度场和风速场与实际测量值差异不显著(决定系数R2分别达到0.9268和0.8926),表明模型仿真精度高;增加挡风板猪舍动物占用区域(Animal occupied zone,AOZ)温度场中温差降低50.77%~71.39%,温度标准差降低28.77%~62.32%,风速场中气流变异系数降低28.60%~61.37%,平均空气龄(Mean age of air,MAA)标准差降低14.83%~43.40%。不同角度挡板产生不同气流,影响温度场、风速场和平均空气龄分布。研究可为北方寒冷地区保育猪舍管道垂直通风结构优化设计和环境调控提供理论依据。展开更多
为充分利用猪肉光谱与图像信息,实现猪肉肌红蛋白含量的在线检测,该研究提出一种基于深度学习模型的猪肉肌红蛋白含量无损检测方法。采用高光谱设备采集冷藏过程中猪肉高光谱图像,通过ENVI5.3选择图像感兴趣区域(Region Of Interest,RO...为充分利用猪肉光谱与图像信息,实现猪肉肌红蛋白含量的在线检测,该研究提出一种基于深度学习模型的猪肉肌红蛋白含量无损检测方法。采用高光谱设备采集冷藏过程中猪肉高光谱图像,通过ENVI5.3选择图像感兴趣区域(Region Of Interest,ROI),分别提取ROI平均光谱信息与主成分图像信息。利用卷积自动编码器(Convolutional Auto Encoder,CAE)提取光谱与图像信息深度特征,分别建立光谱特征、图像特征及图-谱融合特征与肌红蛋白含量之间关系的卷积神经网络(Convolutional Neural Network,CNN)预测模型。其中基于融合深度特征CNN预测模型准确度较高,该模型对脱氧肌红蛋白(DeoMb)、氧合肌红蛋白(OxyMb)、高铁肌红蛋白(MetMb)含量预测集决定系数R_(p)^(2)分别为0.9645、0.9732、0.9585,预测集均方根误差RMSEP分别为0.0158、0.2266、0.3816。为进一步验证图-谱融合特征与猪肉肌红蛋白存在对应关系,分别建立偏最小二乘回归(Partial Least Squares Regression,PLSR)、支持向量机回归(Support Vector Regression,SVR)预测模型。结果表明:CAE能充分提取图像与光谱特征;基于融合特征建立回归模型能提高肌红蛋白含量预测精度,相比于光谱信息与图像信息,以MetMb为例,其2 P R分别提高5.42%、16.12%。该检测方法为肉类质量在线检测提供参考,具有好的应用前景。展开更多
Taoren and Xingren are commonly used herbs in East Asian medicine with different medication functions but huge economic differences,and there are cases of adulterated sales in market transactions.An effective adultera...Taoren and Xingren are commonly used herbs in East Asian medicine with different medication functions but huge economic differences,and there are cases of adulterated sales in market transactions.An effective adulteration recognition based on hyperspectral technology and machine learning was designed as a non-destructive testing method in this paper.A hyperspectral dataset comprising 500 Taoren and 500 Xingren samples was established;six feature selection methods were considered in the modeling of radial basis function-support vector machine(RBF-SVM),whose interaction between the two optimization methods was further researched.Two mixed metaheuristics modeling methods,Mixed-PSO and Mixed-SA,were designed,which fused both band selection and hyperparameter optimization from two-stage into one with detailed process analysis.The metrics of this mixed model were improved by comparing with traditional two-stage method.The accuracy of Mixed-PSO was 89.2%in five-floods crossvalidation that increased 4.818%than vanilla RBF-SVM;the accuracy of Mixed-SA was 88.7%which could reach the same as the traditional two-stage method,but it only relied on 48 crux bands in full 100 bands in RBF-SVM model fitting.展开更多
文摘为了提高光伏/温差联合发电系统的效率,需要进行最大功率点跟踪(Maximum Power Point Tracking,MPPT)控制。针对传统电导增量法步长固定不变导致跟踪速度慢和稳态误差大的缺点,该研究提出一种恒定电压法和双曲正切型自适应变步长算法结合的MPPT控制策略。该策略利用双曲正切函数单调递增、变化速度快的特点,使步长可以根据光强等外界环境条件的变化,自适应地快速调整,同时利用恒定电压法加快追踪的响应速度。Matlab/Simulink软件仿真和硬件试验表明,该研究所提方法在光照强度剧烈变化时,系统能够在15 ms内快速跟踪到最大功率点,同时稳态误差低于0.3%,实现了MPPT控制在跟踪速度和稳态精度方面的同步优化。
文摘为研究北方寒冷地区管道垂直通风保育猪舍内环境分布规律,以黑龙江省齐齐哈尔市保育猪舍为研究对象,通过计算流体力学(Computational fluid dynamics,CFD)模拟不加挡风板与不同角度挡风板下温度场、风速场和平均空气龄分布情况。设计5种方案,方案1无挡风板,方案2圆柱形挡风板,方案3~5挡风板角度(α)为60°、45°、30°圆台形挡风板。保育猪舍管道垂直通风模型经现场试验验证,结果表明管道垂直通风CFD模型温度场和风速场与实际测量值差异不显著(决定系数R2分别达到0.9268和0.8926),表明模型仿真精度高;增加挡风板猪舍动物占用区域(Animal occupied zone,AOZ)温度场中温差降低50.77%~71.39%,温度标准差降低28.77%~62.32%,风速场中气流变异系数降低28.60%~61.37%,平均空气龄(Mean age of air,MAA)标准差降低14.83%~43.40%。不同角度挡板产生不同气流,影响温度场、风速场和平均空气龄分布。研究可为北方寒冷地区保育猪舍管道垂直通风结构优化设计和环境调控提供理论依据。
文摘为充分利用猪肉光谱与图像信息,实现猪肉肌红蛋白含量的在线检测,该研究提出一种基于深度学习模型的猪肉肌红蛋白含量无损检测方法。采用高光谱设备采集冷藏过程中猪肉高光谱图像,通过ENVI5.3选择图像感兴趣区域(Region Of Interest,ROI),分别提取ROI平均光谱信息与主成分图像信息。利用卷积自动编码器(Convolutional Auto Encoder,CAE)提取光谱与图像信息深度特征,分别建立光谱特征、图像特征及图-谱融合特征与肌红蛋白含量之间关系的卷积神经网络(Convolutional Neural Network,CNN)预测模型。其中基于融合深度特征CNN预测模型准确度较高,该模型对脱氧肌红蛋白(DeoMb)、氧合肌红蛋白(OxyMb)、高铁肌红蛋白(MetMb)含量预测集决定系数R_(p)^(2)分别为0.9645、0.9732、0.9585,预测集均方根误差RMSEP分别为0.0158、0.2266、0.3816。为进一步验证图-谱融合特征与猪肉肌红蛋白存在对应关系,分别建立偏最小二乘回归(Partial Least Squares Regression,PLSR)、支持向量机回归(Support Vector Regression,SVR)预测模型。结果表明:CAE能充分提取图像与光谱特征;基于融合特征建立回归模型能提高肌红蛋白含量预测精度,相比于光谱信息与图像信息,以MetMb为例,其2 P R分别提高5.42%、16.12%。该检测方法为肉类质量在线检测提供参考,具有好的应用前景。
基金Supported by the Natural Science Foundation of Heilongjiang Province(LH2020C003)。
文摘Taoren and Xingren are commonly used herbs in East Asian medicine with different medication functions but huge economic differences,and there are cases of adulterated sales in market transactions.An effective adulteration recognition based on hyperspectral technology and machine learning was designed as a non-destructive testing method in this paper.A hyperspectral dataset comprising 500 Taoren and 500 Xingren samples was established;six feature selection methods were considered in the modeling of radial basis function-support vector machine(RBF-SVM),whose interaction between the two optimization methods was further researched.Two mixed metaheuristics modeling methods,Mixed-PSO and Mixed-SA,were designed,which fused both band selection and hyperparameter optimization from two-stage into one with detailed process analysis.The metrics of this mixed model were improved by comparing with traditional two-stage method.The accuracy of Mixed-PSO was 89.2%in five-floods crossvalidation that increased 4.818%than vanilla RBF-SVM;the accuracy of Mixed-SA was 88.7%which could reach the same as the traditional two-stage method,but it only relied on 48 crux bands in full 100 bands in RBF-SVM model fitting.
