剩余使用寿命(Remaining useful life,RUL)预测是大型设备故障预测与健康管理(Prognostics and health management,PHM)的重要环节,对于降低设备维修成本和避免灾难性故障具有重要意义.针对RUL预测,首次提出一种基于多变量分析的时序图...剩余使用寿命(Remaining useful life,RUL)预测是大型设备故障预测与健康管理(Prognostics and health management,PHM)的重要环节,对于降低设备维修成本和避免灾难性故障具有重要意义.针对RUL预测,首次提出一种基于多变量分析的时序图推理模型(Multivariate similarity temporal knowledge graph,MSTKG),通过捕捉设备各部件的运行状态耦合关系及其变化趋势,挖掘其中蕴含的设备性能退化信息,为寿命预测提供有效依据.首先,设计时序图结构,形式化表达各部件不同工作周期的关联关系.其次,提出联合图卷积神经网络(Convolutional neural network,CNN)和门控循环单元(Gated recurrent unit,GRU)的深度推理网络,建模并学习设备各部件工作状态的时空演化过程,并结合回归分析,得到剩余使用寿命预测结果.最后,与现有预测方法相比,所提方法能够显式建模并利用设备部件耦合关系的变化信息,仿真实验结果验证了该方法的优越性.展开更多
为了提高锂离子电池在运行过程中的内短路故障检测效率,提出基于弛豫电压的锂离子电池内短路分级及检测方法。首先根据内短路电池暂停放电后的弛豫电压曲线特征,基于支持向量机模型对电池内短路等级进行分类。然后根据分类结果,提出相...为了提高锂离子电池在运行过程中的内短路故障检测效率,提出基于弛豫电压的锂离子电池内短路分级及检测方法。首先根据内短路电池暂停放电后的弛豫电压曲线特征,基于支持向量机模型对电池内短路等级进行分类。然后根据分类结果,提出相应的电池内短路故障检测方法。对于中期内短路电池,立即令其退出电池系统;对于早期内短路电池,利用卡尔曼滤波(Kalman filtering,KF)算法实时计算电池荷电状态(state of charge,SOC)偏差;对于无短路电池,保持原检测措施。最后对所提分类及检测方法进行实验验证。实验结果表明该分类方法的正确率受弛豫电压序列的采样总时间长度和采样间隔时间影响,增加恒流恒压充电阶段获取的特征数据能进一步提高内短路分类结果的正确率,实时检测电池SOC偏差的方法能及时发现异常的早期内短路电池。展开更多
Scarce resources,precedence and non-determined time-lag are three constraints commonly found in small and medium manufacturing enterprises(SMEs),which are deemed to block the application of workflow management system(...Scarce resources,precedence and non-determined time-lag are three constraints commonly found in small and medium manufacturing enterprises(SMEs),which are deemed to block the application of workflow management system(WfMS). To tackle this problem,a workflow scheduling approach is proposed based on timing workflow net(TWF-net) and genetic algorithm(GA). The workflow is modelled in a form of TWF-net in favour of process simulation and resource conflict checking. After simplifying and reconstructing the set of workflow instance,the conflict resolution problem is transformed into a resource-constrained project scheduling problem(RCPSP),which could be efficiently solved by a heuristic method,such as GA. Finally,problems of various sizes are utilized to test the performance of the proposed algorithm and to compare it with first-come-firstserved(FCFS) strategy. The evaluation demonstrates that the proposed method is an overwhelming and effective approach for scheduling the concurrent processes with precedence and resource constraints.展开更多
文摘为了提高锂离子电池在运行过程中的内短路故障检测效率,提出基于弛豫电压的锂离子电池内短路分级及检测方法。首先根据内短路电池暂停放电后的弛豫电压曲线特征,基于支持向量机模型对电池内短路等级进行分类。然后根据分类结果,提出相应的电池内短路故障检测方法。对于中期内短路电池,立即令其退出电池系统;对于早期内短路电池,利用卡尔曼滤波(Kalman filtering,KF)算法实时计算电池荷电状态(state of charge,SOC)偏差;对于无短路电池,保持原检测措施。最后对所提分类及检测方法进行实验验证。实验结果表明该分类方法的正确率受弛豫电压序列的采样总时间长度和采样间隔时间影响,增加恒流恒压充电阶段获取的特征数据能进一步提高内短路分类结果的正确率,实时检测电池SOC偏差的方法能及时发现异常的早期内短路电池。
基金Supported by the Postdoctoral Science Foundation of China(No.2015M572022)the National Natural Science Foundation of China(No.51175304)
文摘Scarce resources,precedence and non-determined time-lag are three constraints commonly found in small and medium manufacturing enterprises(SMEs),which are deemed to block the application of workflow management system(WfMS). To tackle this problem,a workflow scheduling approach is proposed based on timing workflow net(TWF-net) and genetic algorithm(GA). The workflow is modelled in a form of TWF-net in favour of process simulation and resource conflict checking. After simplifying and reconstructing the set of workflow instance,the conflict resolution problem is transformed into a resource-constrained project scheduling problem(RCPSP),which could be efficiently solved by a heuristic method,such as GA. Finally,problems of various sizes are utilized to test the performance of the proposed algorithm and to compare it with first-come-firstserved(FCFS) strategy. The evaluation demonstrates that the proposed method is an overwhelming and effective approach for scheduling the concurrent processes with precedence and resource constraints.
