利用改进的神经网络预测腐蚀管道的剩余强度

将BP神经网络和遗传算法相结合 ,得到一种新的神经网络 ,并将这种神经网络成功用于计算腐蚀管道的剩余强度和最大允许输送压力。通过示例分析 ,得到下面结论 :不同计算方法计算得到的剩余强度和最大允许输送压力相差较大 ,Wes - 2 80 5 - 97规范、ASME -B31G规范、CVDA— 84规范等都比J积分方法计算得到的剩余强度和最大允许输送压力偏大 ;DM断裂力学方法计算得到的剩余强度和最大允许输送压力比J积分偏小 ;J积分方法和基于J积分方法的改进的遗传神经网络方法计算结果比较接近 ,可以认为是计算剩余强度和最大允许输送压力较好的方法

预测腐蚀管道剩余强度的新方法

将BP神经网络和遗传算法相结合 ,得到了一种可计算腐蚀管道剩余强度和最大允许注水压力的新神经网络。通过实例分析 ,将 7种常用规范和改进的遗传神经网络方法进行了比较。结果表明 ,不同计算方法得到的剩余强度和最大允许注水压力相差较大 ,Wes 2 80 5 - 97规范、ASMEB31G规范、CVDA— 84规范、Irwin断裂力学方法等都比J积分方法的剩余强度和最大允许注水压力偏大 ;Burdiken和DM断裂力学方法计算得到的剩余强度和最大允许注水压力比J积分偏小 ;J积分方法和基于J积分方法的改进遗传神经网络方法计算结果比较接近 ,比较适中 ,可以认为是计算管道剩余强度和最大允许注水压力较好的方法

Evaluation of wheat or corn dried distillers' grains with solubles on performance and carcass characteristics of feedlot steers

[EN]A study was conducted on crossbred steers (n=275; 376±924 kg) to evaluate performance and carcass quality of cattle fed wheat or corn dried distillers’ grains with solubles (DDGS). The control ration contained 86.6% rolled barley grain, 5.7% supplement and 7.7% barley silage (DM basis). The four treatments included replacement of barley grain at 20 or 40% of the diet (DM basis) with wheat or corn DDGS. Steers were slaughtered at a common end weight of 645 kg with 100 steers randomly (n=20 per treatment) selected for determination of the retail yield of sub-primal boneless boxed beef (SPBBB). Data were analyzed as a completely randomized design using pen as the experimental unit. Feeding increasing levels of wheat DDGS led to a quadratic increase in dry matter intake (DMI) (P<0.01), whereas increasing levels of corn DDGS led to a quadratic decrease in DMI (P=0.01). Average daily gain was not influenced (P=0.13) by feeding wheat or corn DDGS, but cattle fed corn DDGS exhibited a quadratic increase (P=0.01) in gain:feed. As a result, a quadratic increase (P<0.01) in calculated NEg of the diet was observed as corn DDGS levels increased. A linear decrease (P=0.04) in days on feed (169, 166 and 154 d) was noted when increasing levels of wheat DDGS (0, 20 and 40%) were fed. Dressing percentage increased in a linear fashion with wheat DDGS (P<0.01) inclusion level and in a quadratic fashion (P=0.01) as corn DDGS inclusion level increased although other carcass traits were not affected (P=0.10) by treatment. The results indicate that replacement of barley grain with corn or wheat DDGS up to 40% of the diet (DM) can lead to superior performance (improved gain:feed or reduced days on feed, respectively) with no detrimental effect on quality grade or carcass SPBBB yield.

腐蚀管道的剩余强度计算方法研究

对目前国内外常用规范进行归纳和总结,得到5种常用方法: ASME—B31G,DM方法,Wes-2805—97,CVDA-84和J积分方法.本文将BP神经网络和遗传算法相结合,得到一种新的神经网络,并将这种神经网络成功用于计算腐蚀管道的剩余强度和最大允许注水压力.通过示例分析,对7种常用规范和本文提出的改进的遗传神经网络方法进行了比较,得到下面结论:不同计算方法计算得到的剩余强度和最大允许注水压力相差较大, Wes-2805-97规范、 ASME—B31G规范、 CVDA-84规范等都比J积分方法计算得到的剩余强度和最大允许注水压力偏大、偏保守; DM断裂力学方法计算得到的剩余强度和最大允许注水压力比J积分偏小、偏危险; J积分方法和基于J积分方法的改进的遗传神经网络方法计算结果比较接近,比较适中,可以认为是计算剩余强度和最大允许注水压力较好的方法.