The implementation of closed loop supply chain system is becoming essential for fashion leather products industry to ensure an economically sustainable business model and eco-friendly industrial practice as demanded b...The implementation of closed loop supply chain system is becoming essential for fashion leather products industry to ensure an economically sustainable business model and eco-friendly industrial practice as demanded by the environmental regulations, consumer awareness and the prevailing social consciousness. In this context, this research work addresses a closed loop supply chain network problem of fashion leather goods industry, with an objective of minimizing the total cost of the entire supply chain and also reducing the total waste from the end of life product returns. The research work commenced with a literature review on the reverse and closed loop supply chain network design problems of fashion and leather goods industry dealt in the past. Then, the identified CLSCND problem is solved using a mathematical model based on Mixed Integer Non-Linear Programme (MINLP) and then a suitable Hybrid Genetic Algorithm (HGA) developed for the CLSCND is implemented for obtaining optimum solution. Both the MINLP model and HGA are customized as per the CLSCND problem chosen and implemented for the industrial case of an Indian Fashion Leather Goods Industry. Finally, the solutions obtained for MINLP model in LINGO 15 and for HGA in VB.NET platform are compared and presented. The optimum solution obtained from the suitable HGA is illustrated as an optimum shipment pattern for the closed loop supply chain network design problem of the fashion leather goods industry case.展开更多
针对目前仓储货物分类速度慢、易出错、灵活性差等问题,提出了一种改进YOLOv5s的货物检测算法,对仓储货物进行预分类。首先,根据仓储货物的外形特征,将其分为包装箱与包装袋两大类,形成训练数据集;其次,将骨干网络更换为具有更小模型尺...针对目前仓储货物分类速度慢、易出错、灵活性差等问题,提出了一种改进YOLOv5s的货物检测算法,对仓储货物进行预分类。首先,根据仓储货物的外形特征,将其分为包装箱与包装袋两大类,形成训练数据集;其次,将骨干网络更换为具有更小模型尺寸的MobileNetV3,加快推理;再次,添加SE注意力机制模块,旨在提高模型的检测精度;最后,结合α_CIoU损失函数,增强模型的灵活度。通过实验验证,改进后的算法相较于原始算法在精确率(Precision,P)、平均类别精度(mean Average precision,mAP)和帧率(Frames per second,FPS)三方面分别提升2.1%、0.5%和10.6%,能够高效地完成对仓储货物的预分类工作。展开更多
锅炉燃烧优化在电厂锅炉经济稳定运行中起着重要作用,NO_(x)排放预测是其中的一个基本环节,因此提出了一种基于改进蜣螂优化算法优化卷积神经网络(convolutional neural network,CNN)与双向长短期记忆神经网络(long short term memory,L...锅炉燃烧优化在电厂锅炉经济稳定运行中起着重要作用,NO_(x)排放预测是其中的一个基本环节,因此提出了一种基于改进蜣螂优化算法优化卷积神经网络(convolutional neural network,CNN)与双向长短期记忆神经网络(long short term memory,LSTM)的组合模型超参数的超超临界锅炉NO_(x)排放预测的方法。首先通过Pearson相关性判定与NO_(x)排放相关的特征参数;其次建立CNN-LSTM预测模型,利用卷积神经网络CNN提取分层数据结构,长短期记忆网络挖掘长期依赖关系,然后结合佳点集、t分布变异策略对蜣螂算法进行改进,用改进后的算法对LSTM超参数进行优化得到最终预测模型;最后与其他神经网络模型进行对比验证。以某660 MW机组锅炉深度调峰实际数据进行预测,结果得到NO_(x)排放浓度实际值与预测值的平均绝对误差为3.3516,平均相对误差为2.4667,数据结果表明该预测模型具有更准确的预测效果。展开更多
文摘The implementation of closed loop supply chain system is becoming essential for fashion leather products industry to ensure an economically sustainable business model and eco-friendly industrial practice as demanded by the environmental regulations, consumer awareness and the prevailing social consciousness. In this context, this research work addresses a closed loop supply chain network problem of fashion leather goods industry, with an objective of minimizing the total cost of the entire supply chain and also reducing the total waste from the end of life product returns. The research work commenced with a literature review on the reverse and closed loop supply chain network design problems of fashion and leather goods industry dealt in the past. Then, the identified CLSCND problem is solved using a mathematical model based on Mixed Integer Non-Linear Programme (MINLP) and then a suitable Hybrid Genetic Algorithm (HGA) developed for the CLSCND is implemented for obtaining optimum solution. Both the MINLP model and HGA are customized as per the CLSCND problem chosen and implemented for the industrial case of an Indian Fashion Leather Goods Industry. Finally, the solutions obtained for MINLP model in LINGO 15 and for HGA in VB.NET platform are compared and presented. The optimum solution obtained from the suitable HGA is illustrated as an optimum shipment pattern for the closed loop supply chain network design problem of the fashion leather goods industry case.
文摘针对目前仓储货物分类速度慢、易出错、灵活性差等问题,提出了一种改进YOLOv5s的货物检测算法,对仓储货物进行预分类。首先,根据仓储货物的外形特征,将其分为包装箱与包装袋两大类,形成训练数据集;其次,将骨干网络更换为具有更小模型尺寸的MobileNetV3,加快推理;再次,添加SE注意力机制模块,旨在提高模型的检测精度;最后,结合α_CIoU损失函数,增强模型的灵活度。通过实验验证,改进后的算法相较于原始算法在精确率(Precision,P)、平均类别精度(mean Average precision,mAP)和帧率(Frames per second,FPS)三方面分别提升2.1%、0.5%和10.6%,能够高效地完成对仓储货物的预分类工作。
文摘锅炉燃烧优化在电厂锅炉经济稳定运行中起着重要作用,NO_(x)排放预测是其中的一个基本环节,因此提出了一种基于改进蜣螂优化算法优化卷积神经网络(convolutional neural network,CNN)与双向长短期记忆神经网络(long short term memory,LSTM)的组合模型超参数的超超临界锅炉NO_(x)排放预测的方法。首先通过Pearson相关性判定与NO_(x)排放相关的特征参数;其次建立CNN-LSTM预测模型,利用卷积神经网络CNN提取分层数据结构,长短期记忆网络挖掘长期依赖关系,然后结合佳点集、t分布变异策略对蜣螂算法进行改进,用改进后的算法对LSTM超参数进行优化得到最终预测模型;最后与其他神经网络模型进行对比验证。以某660 MW机组锅炉深度调峰实际数据进行预测,结果得到NO_(x)排放浓度实际值与预测值的平均绝对误差为3.3516,平均相对误差为2.4667,数据结果表明该预测模型具有更准确的预测效果。