Entity

Time filter

Source Type


Zeng C.,National Engineering Laboratory for Pipeline Safety | Wu C.,National Engineering Laboratory for Pipeline Safety | Zuo L.,National Engineering Laboratory for Pipeline Safety | Zhang B.,National Engineering Laboratory for Pipeline Safety | And 3 more authors.
Energy | Year: 2014

In this paper artificial neural network is introduced to forecast the daily electricity consumption of a multiproduct pipeline which is used to drive oil pumps. Forecasting electricity energy consumption is complicated since there are so many parameters affecting the energy consumption. Two different sets of input vectors are selected from these parameters by detailed analysis of energy consumption in this study, and two corresponding multilayer perceptron artificial neural network (MLP ANN) models are developed. To enhance the generalization ability, the numbers of hidden layers and neurons, activation functions and training algorithm of each model are optimized by the trial-and-error process step by step. The performances of the two proposed MLP ANN models are evaluated on real data of a Chinese multiproduct pipeline, and compared with two linear regression and two support vector machine (SVM) models which are produced using different inputs. Results show that the two MLP ANN models have very high accuracy for prediction and better forecasting performance than the other models. The proposed input vectors and MLP ANN models are useful not only in the effective evaluation of batch scheduling and pumping operation, but also in the energy consumption target setting. © 2014. Source


You Z.,National Engineering Laboratory for Pipeline Safety | You Z.,China National Petroleum Corporation | Li Y.,National Engineering Laboratory for Pipeline Safety | Li Y.,China National Petroleum Corporation
Materials Science Forum | Year: 2016

In this paper, the application of 9% Ni steel in natural gas storage tanks and the welding thermal crack tendency of 9% Ni steel were studied. For the section shrinkage and breaking strength of tensile specimens at different temperature, the high temperature tensile test (600℃~1450℃) of 9%Ni steel was carried out by Gleeble 3500 thermal simulation machine. The nil-ductility transition temperature (NDT), nil-ductility stength temperature (NST) and ductility recovery temperature (DRT) of 9%Ni steel were identified. The result showed that the NDT for 9% Ni steel was 1400℃, the NST was 1430℃, the DRT is 1370℃, and the brittle temperature range (BTR) was 60℃. In this study, the welding hot crack of 9% Ni steel was a little sensitive. © 2016 Trans Tech Publications, Switzerland. Source


Liu Y.,China Petroleum Pipeline Research Institute | Liu Y.,National Engineering Laboratory for Pipeline Safety | Ma A.,Tian Jin SERI Machinery Equipment Co. | Feng B.,China Petroleum Pipeline Research Institute | Feng B.,National Engineering Laboratory for Pipeline Safety
Materials Science Forum | Year: 2016

In this paper, the simulation heat affected zone (HAZ) continuous cooling transformation (SHCCT) curve of X90 pipeline steel was drew by using Gleeble 3500 simulator. The results show that the trend of hardening of the weld HAZ of X90 pipeline steel was moderate, and softening tendency was not significant. When cooling rate was between 1°C/s and 10°C/s, the microstructure of X90 pipeline steel weld HAZ were composed of granular bainite and lath bainite. The recommended welding heat input of X90 pipeline steel was between 21kJ/cm and 66.4kJ/cm, and the weld preheating temperature was controlled about 100°C. In conclusion, optimization control measures on the microstructure and properties of X90 pipeline steel weld HAZ are presented by above comprehensive analysis. © 2016 Trans Tech Publications, Switzerland. Source


Yao D.,China National Petroleum Corporation | Zhang L.,China Petroleum Pipeline Bureau International | Fan Y.,China National Petroleum Corporation | Fan Y.,National Engineering Laboratory for Pipeline Safety | And 4 more authors.
Materials Science Forum | Year: 2016

To confirm pipeline designs and validate the weld toughness, extensively works of Curved Wide Plate (CWP) test methods was carried out. The method of Two Clip Gauge-CTOD was firstly introduced in CWP test in this paper. The test results of CWP analyzed by Two Clip Gauge-CTOD method and Compliance—J method was compared. The CTOD-R curves achieved by these methods showed the good consistence with each other. Furthermore, the difference of the test results among SENB(single edge-notched bend), SENT(single edge-notched tensile) and CWP was discussed. It shows that the toughness obtained by SENB is relatively conservative, and CWP and SENT are recommend to be chosen for pipeline steel welds toughness test. © 2016 Trans Tech Publications, Switzerland. Source


Wu J.,China National Petroleum Corporation | Yao D.,China National Petroleum Corporation | Yao D.,National Engineering Laboratory for Pipeline Safety | Yuan X.,China National Petroleum Corporation | And 4 more authors.
Materials Science Forum | Year: 2016

In the pipeline construction, the girth welds tend to be the weakness because of defects and microstructure. The importance of suitable assessment of various defects in the weld is not only to prevent the cracks from unstable growth to cause catastrophic accident but also can effectively reduce the weld repair to reduce construction cost. Although many welding defects assessment methods and codes are used in this field, there are many differences among them. In this paper, the welding defect assessment methods, such as API 1104 and BS7910, were studied. The results show the key factors that affect the result of these assessment methods. The application of these methods was also discussed. The results indicate that API 1104 level1 has the highest conservatism, while API 1104 level 2 is next. © 2016 Trans Tech Publications, Switzerland. Source

Discover hidden collaborations