A soft sensing strategy based on neural network is proposed for product quality of FCCU main fractionator.From the analysis of the process mechanism and the use of operating data,a neural network soft sensing model （...A soft sensing strategy based on neural network is proposed for product quality of FCCU main fractionator.From the analysis of the process mechanism and the use of operating data,a neural network soft sensing model （static） was developed for the end point of naphtha.A dynamic error correction ele ment is supplemented.Long-time running shows that it can substitute conventional process analyzer and no measurement delay times is expected.展开更多
传统的概率转移矩阵(Probabilistic Transfer Matrix,PTM)方法是一种能够比较精确地估计软差错对门级电路可靠度影响的方法,但现有的方法只适用于组合逻辑电路的可靠度估计.本文提出基于PTM的时序电路可靠度估计方法(reliability estima...传统的概率转移矩阵(Probabilistic Transfer Matrix,PTM)方法是一种能够比较精确地估计软差错对门级电路可靠度影响的方法,但现有的方法只适用于组合逻辑电路的可靠度估计.本文提出基于PTM的时序电路可靠度估计方法(reliability estimation of Sequential circuits based on PTM,S-PTM),先把待评估时序电路划分为输出逻辑模块和次态逻辑模块,然后用本文提出的时序电路PTM计算模型得到电路的PTM,最后根据输入信号的概率分布计算出时序电路的可靠度.用ISCAS 89基准电路为对象进行实验和验证,实验表明所提方法是准确和合理的.展开更多
The development of VLSI technology results in the dramatically improvement of the performance of integrated circuits. However, it brings more challenges to the aspect of reliability. Integrated circuits become more su...The development of VLSI technology results in the dramatically improvement of the performance of integrated circuits. However, it brings more challenges to the aspect of reliability. Integrated circuits become more susceptible to soft errors. Therefore, it is imperative to study the reliability of circuits under the soft error. This paper implements three probabilistic methods (two pass, error propagation probability, and probabilistic transfer matrix) for estimating gate-level circuit reliability on PC. The functions and performance of these methods are compared by experiments using ISCAS85 and 74-series circuits.展开更多
文摘A soft sensing strategy based on neural network is proposed for product quality of FCCU main fractionator.From the analysis of the process mechanism and the use of operating data,a neural network soft sensing model （static） was developed for the end point of naphtha.A dynamic error correction ele ment is supplemented.Long-time running shows that it can substitute conventional process analyzer and no measurement delay times is expected.
文摘传统的概率转移矩阵(Probabilistic Transfer Matrix,PTM)方法是一种能够比较精确地估计软差错对门级电路可靠度影响的方法,但现有的方法只适用于组合逻辑电路的可靠度估计.本文提出基于PTM的时序电路可靠度估计方法(reliability estimation of Sequential circuits based on PTM,S-PTM),先把待评估时序电路划分为输出逻辑模块和次态逻辑模块,然后用本文提出的时序电路PTM计算模型得到电路的PTM,最后根据输入信号的概率分布计算出时序电路的可靠度.用ISCAS 89基准电路为对象进行实验和验证,实验表明所提方法是准确和合理的.
基金the National Basic Research and Development (973) Program of China (No. 2005CB321604)the National Natural Science Foundation of China (No. 90207021)
文摘The development of VLSI technology results in the dramatically improvement of the performance of integrated circuits. However, it brings more challenges to the aspect of reliability. Integrated circuits become more susceptible to soft errors. Therefore, it is imperative to study the reliability of circuits under the soft error. This paper implements three probabilistic methods (two pass, error propagation probability, and probabilistic transfer matrix) for estimating gate-level circuit reliability on PC. The functions and performance of these methods are compared by experiments using ISCAS85 and 74-series circuits.
