The composition of the distillation column is a very important quality value in refineries, unfortunately, few hardware sensors are available on-line to measure the distillation compositions. In this paper, a novel me...The composition of the distillation column is a very important quality value in refineries, unfortunately, few hardware sensors are available on-line to measure the distillation compositions. In this paper, a novel method using sensitivity matrix analysis and kernel ridge regression (KRR) to implement on-line soft sensing of distillation compositions is proposed. In this approach, the sensitivity matrix analysis is presented to select the most suitable secondary variables to be used as the soft sensor's input. The KRR is used to build the composition soft sensor. Application to a simulated distillation column demonstrates the effectiveness of the method.展开更多
电池健康状况的在线估计对于电池管理系统一直是一个非常重要的问题。近年来,由于其具有灵活性和无模型优势,基于数据驱动的方法在在线健康状态(state of health,SOH)估计领域展现出极大的潜力。文中针对现有的大部分基于数据驱动的SOH...电池健康状况的在线估计对于电池管理系统一直是一个非常重要的问题。近年来,由于其具有灵活性和无模型优势,基于数据驱动的方法在在线健康状态(state of health,SOH)估计领域展现出极大的潜力。文中针对现有的大部分基于数据驱动的SOH估计方法存在计算量大以及较难在BMS微控制器中实现等问题,提出一种采用片段充电曲线和核岭回归(kernel ridge regression,KRR)的锂离子电池SOH估计方法。KRR是一种基于核方法的非线性回归算法,通过将核技巧与岭回归结合,能够建立充电电压片段和SOH之间的非线性映射关系。在2个公开锂离子电池老化数据集上的实验表明,该方法只需采用实际电池使用工况中容易获得的充电电压片段,就能够实现快速准确的SOH估计,并且应用到现有的BMS微控制器中。展开更多
基金supported by National Basic Research Program of China (973 Program) (No. 2007CB714006)
文摘The composition of the distillation column is a very important quality value in refineries, unfortunately, few hardware sensors are available on-line to measure the distillation compositions. In this paper, a novel method using sensitivity matrix analysis and kernel ridge regression (KRR) to implement on-line soft sensing of distillation compositions is proposed. In this approach, the sensitivity matrix analysis is presented to select the most suitable secondary variables to be used as the soft sensor's input. The KRR is used to build the composition soft sensor. Application to a simulated distillation column demonstrates the effectiveness of the method.
文摘电池健康状况的在线估计对于电池管理系统一直是一个非常重要的问题。近年来,由于其具有灵活性和无模型优势,基于数据驱动的方法在在线健康状态(state of health,SOH)估计领域展现出极大的潜力。文中针对现有的大部分基于数据驱动的SOH估计方法存在计算量大以及较难在BMS微控制器中实现等问题,提出一种采用片段充电曲线和核岭回归(kernel ridge regression,KRR)的锂离子电池SOH估计方法。KRR是一种基于核方法的非线性回归算法,通过将核技巧与岭回归结合,能够建立充电电压片段和SOH之间的非线性映射关系。在2个公开锂离子电池老化数据集上的实验表明,该方法只需采用实际电池使用工况中容易获得的充电电压片段,就能够实现快速准确的SOH估计,并且应用到现有的BMS微控制器中。