ID 原文 译文
12494 提出了一种新型的基于遗传算法 (GA) 优化的误差反向传播 (BP) 神经网络的寿命预测模型。 A new lifetime prediction model based on the error back propagation ( BP) neural network optimized by genetic algorithm ( GA) was presented.
12495 选取不同公司生产的LED, 以LED光源光通量维持率测量方法 (LM-80-08) 测试报告中的电流、结温、初始光通量和初始色坐标作为神经网络的输入, LED在网络输入的应力条件下的寿命为输出, 可以预测LED在任意电流和结温下的寿命。 A variety of LEDs produced by different companies were selected for test. The parameters which were obtained by test reports ( LM-80-08) of light flux maintenance rate of LEDs light sources were served as the inputs of the neural network, such as electric current, junction temperature, initial luminous flux and initial chromaticity coordinates, while the lifetime of LEDs under the stress of network's input was served as the output of the neural network. The lifetime of LEDs could be predicted under any current and junction temperature.
12496 研究结果表明, 该GA-BP模型相比于LED光源长期流明维持率的预测方法 (TM-21-11) 更具灵活性, 预测误差较传统BP神经网络降低了65.5%, 平均相对误差达到1.47%, 优于Adaboost模型的54%和3.16%, 训练样本相关系数达到99.4%, GA-BP模型预测LED寿命误差更小, 普适性更高, 在LED的寿命预测中具有实际意义。 The research results show that this GA-BP model is more flexible than the prediction method ( TM-21-11) of long term lumen maintenance rate of LED light sources. Compared with the traditional BP neural network, the prediction error of GA-BP model is reduced by 65. 5%, the average relative error is 1. 47%, which is better than the Adaboost model of 54% and 3. 16%. The correlation coefficient of training samples reaches 99. 4%. The GA-BP model is more accurate and adaptable in the prediction lifetime of LEDs, which is of practical significance in the prediction lifetime of LEDs.
12497 为了降低电路老化对数字集成电路性能的影响, 提出了一种通过对比输入信号与其反向延迟信号对电路老化进行预测的传感器结构。 In order to reduce the influence of circuit aging on the performance of digital integrated circuits, a sensor was proposed to predict the aging of the circuit by comparing the input signal and its reverse delay signal.
12498 提出的传感器结构预测部分可对组合逻辑电路进行数据失效前的老化预测, 当检测到电路已发生老化致数据失效时, 容错部分可对错误信号进行矫正。 The aging of the combinational logic circuit can be predicted by the proposed sensor before the data failure. When the circuit has been degraded and the data are invalid, the fault tolerance part can be used to correct the error signal.
12499 该结构特殊的设计减小了面积开销和功耗。 The special design of this structure saves chip area and power consumption.
12500 采用HSPICE软件对传感器功能进行模拟仿真, 实验结果验证了传感器可在不同环境下正确地预测电路的老化情况, 并对已发生错误的信号进行矫正, 与其他功能相同的传感器相比, 该传感器的面积及功耗分别降低了30.91%和41.3%。 Based on HSPICE software, the function of the sensor was simulated, and the experimental results verify that the sensor can precisely predict the aging of the circuit in different situations, and correct the wrong signal. Compared with other sensors with the same function, the area and power consumption are reduced by 30. 91% and 41. 3%, respectively.
12501 阻变随机存储器 (RRAM) 中存在的故障严重影响产品的可靠性和良率。 The malfunctions existing in the resistive random access memory ( RRAM) seriously affect the reliability and yield of the storage production.
12502 采用精确高效的测试方法能有效缩短工艺优化周期, 降低测试成本。 By utilizing the precise and efficient testing method, the process optimization cycle can be greatly shortened, and the product cost can be reduced.
12503 基于SMIC 28 nm工艺平台, 完成了1T1R结构的1 Mbit RRAM模块的流片。 The 1 Mbit RRAM memory module with the structure of one transistor one resistance ( 1 T1 R) was fabricated based on the SMIC 28 nm process platform.