高效准确的机器学习模型是高通量筛选优质含能分子的基础,为此设计了完全通过结构式便可输出多项含能材料性质的多输入多输出机器学习模型(MIMO-ML)。基于478个含能分子数据集进行模型构建,通过筛选得到AMID_h、ATTS1are、OB三个优秀描...高效准确的机器学习模型是高通量筛选优质含能分子的基础,为此设计了完全通过结构式便可输出多项含能材料性质的多输入多输出机器学习模型(MIMO-ML)。基于478个含能分子数据集进行模型构建,通过筛选得到AMID_h、ATTS1are、OB三个优秀描述符,并在此基础上建立了自定义描述符集。结果表明,随机森林(RF)及多层感知机(MLP)适合被应用于含能材料性能预测多输出模型构建,输出性质包括爆速D(MAE=256 m/s),热分解温度T_(d)(MAE=34.7℃),撞击感度ln H 50(MAE=0.63)。同时,MLP模型相比于RF模型对于特征数量更敏感,且利用更少的特征可得到与RF精度相似的模型,表明MIMO-ML模型能够快速且准确地识别高性能含能材料,可应用于含能分子的设计与快速筛选。展开更多
The experiments of high throughput drilling of Ti-6Al-4V at 183 m/min cutting speed and 156 mm^3/s material removal rate using a 4 mm diameter WC-Co spiral point drill are conducted. At this material removal rate, it ...The experiments of high throughput drilling of Ti-6Al-4V at 183 m/min cutting speed and 156 mm^3/s material removal rate using a 4 mm diameter WC-Co spiral point drill are conducted. At this material removal rate, it took only 0.57 s to drill a hole in a 6.35 mm thick Ti plate. Supplying the cutting fluid via through-the-drill holes and the balance of cutting speed and feed have proven to be critical for drill life. An inverse heat transfer model is developed to predict the heat flux and the drill temperature distribution in drilling. A three-dimensional finite element modeling of drilling is con-ducted to predict the thrust force and torque. Experimental result demonstrates that, using proper machining process parameters, tool geometry, and fine-grained WC-Co tool material, the high throughput machining of Ti alloy is technically feasible.展开更多
In this paper, we conduct a cross-layer analysis of both the jamming capability of the cognitiveradio-based jammers and the anti-jamming capability of the cognitive radio networks (CRN). We use a Markov chain to model...In this paper, we conduct a cross-layer analysis of both the jamming capability of the cognitiveradio-based jammers and the anti-jamming capability of the cognitive radio networks (CRN). We use a Markov chain to model the CRN operations in spectrum sensing, channel access and channel switching under jamming. With various jamming models, the jamming probabilities and the throughputs of the CRN are obtained in closed-form expressions. Furthermore, the models and expressions are simplified to determine the minimum and the maximum CRN throughput expressions under jamming, and to optimize important anti-jamming parameters. The results are helpful for the optimal anti-jamming CRN design. The model and the analysis results are verified by simulations.展开更多
Wireless sensor networks (WSNs) are energy-constrained networks. The residual energy real-time monitoring (RERM) is very important for WSNs. Moreover, network model is an important foundation of RERM research at perso...Wireless sensor networks (WSNs) are energy-constrained networks. The residual energy real-time monitoring (RERM) is very important for WSNs. Moreover, network model is an important foundation of RERM research at personal area network (PAN) level. Because RERM is inherently application-oriented, the network model adopted should also be application-oriented. However, many factors of WSNs applications such as link selected probability and ACK mechanism etc. were neglected by current network models. These factors can introduce obvious influence on throughput of WSNs. Then the energy consumption of nodes will be influenced greatly. So these models cannot characterize many real properties of WSNs, and the result of RERM is not consistent with the real-world situation. In this study, these factors neglected by other researchers are taken into account. Furthermore, an application-oriented general network model (AGNM) for RERM is proposed. Based on the AGNM, the dynamic characteristics of WSNs are simulated. The experimental results show that AGNM can approximately characterize the real situation of WSNs. Therefore, the AGNM provides a good foundation for RERM research.展开更多
文摘高效准确的机器学习模型是高通量筛选优质含能分子的基础,为此设计了完全通过结构式便可输出多项含能材料性质的多输入多输出机器学习模型(MIMO-ML)。基于478个含能分子数据集进行模型构建,通过筛选得到AMID_h、ATTS1are、OB三个优秀描述符,并在此基础上建立了自定义描述符集。结果表明,随机森林(RF)及多层感知机(MLP)适合被应用于含能材料性能预测多输出模型构建,输出性质包括爆速D(MAE=256 m/s),热分解温度T_(d)(MAE=34.7℃),撞击感度ln H 50(MAE=0.63)。同时,MLP模型相比于RF模型对于特征数量更敏感,且利用更少的特征可得到与RF精度相似的模型,表明MIMO-ML模型能够快速且准确地识别高性能含能材料,可应用于含能分子的设计与快速筛选。
基金Selected from Proceedings of the 7th International Conference on Frontiers of Design and Manufacturing (ICFDM’2006).
文摘The experiments of high throughput drilling of Ti-6Al-4V at 183 m/min cutting speed and 156 mm^3/s material removal rate using a 4 mm diameter WC-Co spiral point drill are conducted. At this material removal rate, it took only 0.57 s to drill a hole in a 6.35 mm thick Ti plate. Supplying the cutting fluid via through-the-drill holes and the balance of cutting speed and feed have proven to be critical for drill life. An inverse heat transfer model is developed to predict the heat flux and the drill temperature distribution in drilling. A three-dimensional finite element modeling of drilling is con-ducted to predict the thrust force and torque. Experimental result demonstrates that, using proper machining process parameters, tool geometry, and fine-grained WC-Co tool material, the high throughput machining of Ti alloy is technically feasible.
文摘In this paper, we conduct a cross-layer analysis of both the jamming capability of the cognitiveradio-based jammers and the anti-jamming capability of the cognitive radio networks (CRN). We use a Markov chain to model the CRN operations in spectrum sensing, channel access and channel switching under jamming. With various jamming models, the jamming probabilities and the throughputs of the CRN are obtained in closed-form expressions. Furthermore, the models and expressions are simplified to determine the minimum and the maximum CRN throughput expressions under jamming, and to optimize important anti-jamming parameters. The results are helpful for the optimal anti-jamming CRN design. The model and the analysis results are verified by simulations.
文摘Wireless sensor networks (WSNs) are energy-constrained networks. The residual energy real-time monitoring (RERM) is very important for WSNs. Moreover, network model is an important foundation of RERM research at personal area network (PAN) level. Because RERM is inherently application-oriented, the network model adopted should also be application-oriented. However, many factors of WSNs applications such as link selected probability and ACK mechanism etc. were neglected by current network models. These factors can introduce obvious influence on throughput of WSNs. Then the energy consumption of nodes will be influenced greatly. So these models cannot characterize many real properties of WSNs, and the result of RERM is not consistent with the real-world situation. In this study, these factors neglected by other researchers are taken into account. Furthermore, an application-oriented general network model (AGNM) for RERM is proposed. Based on the AGNM, the dynamic characteristics of WSNs are simulated. The experimental results show that AGNM can approximately characterize the real situation of WSNs. Therefore, the AGNM provides a good foundation for RERM research.
