Current orchestration and choreography process engines only serve with dedicate process languages.To solve these problems,an Event-driven Process Execution Model(EPEM) was developed.Formalization and mapping principle...Current orchestration and choreography process engines only serve with dedicate process languages.To solve these problems,an Event-driven Process Execution Model(EPEM) was developed.Formalization and mapping principles of the model were presented to guarantee the correctness and efficiency for process transformation.As a case study,the EPEM descriptions of Web Services Business Process Execution Language(WS-BPEL) were represented and a Process Virtual Machine(PVM)-OncePVM was implemented in compliance with the EPEM.展开更多
Based on QoS (quality of service) parameters: time delay, jitter, bandwidth and package loss. As time delay in the Internet is variable, it is hard to compensate it by traditional methods. Event synchronization commun...Based on QoS (quality of service) parameters: time delay, jitter, bandwidth and package loss. As time delay in the Internet is variable, it is hard to compensate it by traditional methods. Event synchronization communication driven method is proposed to overcome the negative effects induced by time delay. This method is a non-time based method and it can get rid of the effects of time in the control loop of telerobotics. Stability, transparency and synchronization can be maintained in it by event-driven method. Multimodal enhanced telerobotics is put forward with its feedback including force, video, audio and temperature etc. The use of multimodal feedback improves the efficiency and safety of the whole system. Synchronization in multimodal feedback is hard to ensure and event-driven method is also good for it. Experiments on an Internet-based shaft-hole assemblage system show good results by using event synchronization communication driven method and UDP protocol.展开更多
针对复杂化工过程非平稳性、事件驱动性导致的关键指标参数难以精确软测量的问题,提出了一种事件驱动的深度信念网络(event-driven deep belief network,EDDBN)软测量模型设计方法。首先,获取化工过程运行数据并搭建深度信念网络(driven...针对复杂化工过程非平稳性、事件驱动性导致的关键指标参数难以精确软测量的问题,提出了一种事件驱动的深度信念网络(event-driven deep belief network,EDDBN)软测量模型设计方法。首先,获取化工过程运行数据并搭建深度信念网络(driven deep belief network,DBN)模型,以数据驱动的方式对DBN模型进行训练,获得基于DBN的软测量模型。其次,根据DBN模型的训练误差变化特性定义事件,当积极事件发生时会加速当前模型参数的学习步长,当消极事件发生时会跳过当前数据样本并直接进入下一时刻的数据样本学习。这种事件驱动的选择性学习策略不仅能够有效地优化软测量模型训练过程,而且还能降低计算复杂度。同时,通过构造基于马尔可夫链的动态学习过程,分析任意连续两次事件对应输出性能势之差的有界性,给出了EDDBN训练过程的收敛性分析。最后,将EDDBN软测量模型用于湿法烟气脱硫系统二氧化硫(SO_(2))浓度软测量实验,结果表明所提出的EDDBN软测量模型能够在非平稳运行工况下实现对SO_(2)浓度快速、精确地预测分析,并且计算复杂度在数据集(1)和数据集(2)上分别降低约63.83%和63.33%。展开更多
文摘Current orchestration and choreography process engines only serve with dedicate process languages.To solve these problems,an Event-driven Process Execution Model(EPEM) was developed.Formalization and mapping principles of the model were presented to guarantee the correctness and efficiency for process transformation.As a case study,the EPEM descriptions of Web Services Business Process Execution Language(WS-BPEL) were represented and a Process Virtual Machine(PVM)-OncePVM was implemented in compliance with the EPEM.
文摘Based on QoS (quality of service) parameters: time delay, jitter, bandwidth and package loss. As time delay in the Internet is variable, it is hard to compensate it by traditional methods. Event synchronization communication driven method is proposed to overcome the negative effects induced by time delay. This method is a non-time based method and it can get rid of the effects of time in the control loop of telerobotics. Stability, transparency and synchronization can be maintained in it by event-driven method. Multimodal enhanced telerobotics is put forward with its feedback including force, video, audio and temperature etc. The use of multimodal feedback improves the efficiency and safety of the whole system. Synchronization in multimodal feedback is hard to ensure and event-driven method is also good for it. Experiments on an Internet-based shaft-hole assemblage system show good results by using event synchronization communication driven method and UDP protocol.
文摘针对复杂化工过程非平稳性、事件驱动性导致的关键指标参数难以精确软测量的问题,提出了一种事件驱动的深度信念网络(event-driven deep belief network,EDDBN)软测量模型设计方法。首先,获取化工过程运行数据并搭建深度信念网络(driven deep belief network,DBN)模型,以数据驱动的方式对DBN模型进行训练,获得基于DBN的软测量模型。其次,根据DBN模型的训练误差变化特性定义事件,当积极事件发生时会加速当前模型参数的学习步长,当消极事件发生时会跳过当前数据样本并直接进入下一时刻的数据样本学习。这种事件驱动的选择性学习策略不仅能够有效地优化软测量模型训练过程,而且还能降低计算复杂度。同时,通过构造基于马尔可夫链的动态学习过程,分析任意连续两次事件对应输出性能势之差的有界性,给出了EDDBN训练过程的收敛性分析。最后,将EDDBN软测量模型用于湿法烟气脱硫系统二氧化硫(SO_(2))浓度软测量实验,结果表明所提出的EDDBN软测量模型能够在非平稳运行工况下实现对SO_(2)浓度快速、精确地预测分析,并且计算复杂度在数据集(1)和数据集(2)上分别降低约63.83%和63.33%。
