Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient...Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient fluid supply in oil wells based on convolutional neural networks is proposed in this paper. Firstly, 5000 indicator diagrams with insufficient liquid supply were collected from the oilfield site, and a sample set was established after preprocessing;then based on the AlexNet model, combined with the characteristics of the indicator diagram, a convolutional neural network model including 4 layers of convolutional layers, 3 layers of down-pooling layers and 2 layers of fully connected layers is established. The backpropagation, ReLu activation function and dropout regularization method are used to complete the training of the convolutional neural network;finally, the performance of the convolutional neural network under different iteration times and network structure is compared, and the super parameter optimization of the model is completed. It has laid a good foundation for realizing the self-adaptive and intelligent matching of oil well production parameters and formation fluid supply conditions. It has certain application prospects. The results show that the accuracy of training and verification of the method exceeds 98%, which can meet the actual application requirements on site.展开更多
To study the draft sensation distribution of an air jet supply system in a large space building in summer,experiments are conducted in a large laboratory.The temperature,velocity and draft sensation distributions at a...To study the draft sensation distribution of an air jet supply system in a large space building in summer,experiments are conducted in a large laboratory.The temperature,velocity and draft sensation distributions at a nozzle height of 4 m in the occupied zone are obtained.Then,the numerical simulation under the test condition is carried out by the computational fluid dynamics（CFD）method.The calculation results of the indoor vertical temperature and the draft sensation distribution are validated by the test data.Simulations with different nozzle heights are conducted.The satisfactory air supply condition is determined by analyzing the draft sensations and the temperatures in the occupied zone under three conditions.The simulation results show that the optimal draft sensation distribution and the uniform temperature and velocity fields can be obtained at a nozzle height of 5 m.展开更多
We investigated the effect of supply air rate and temperature on formaldehyde emission characteristics in an environment chamber.A three-dimensional computational fluid dynamics(CFD) chamber model for simulating forma...We investigated the effect of supply air rate and temperature on formaldehyde emission characteristics in an environment chamber.A three-dimensional computational fluid dynamics(CFD) chamber model for simulating formaldehyde emission in twelve different cases was developed for obtaining formaldehyde concentration by the area-weighted average method.Laboratory experiments were conducted in an environment chamber to validate the simulation results of twelve different cases and the formaldehyde concentration was measured by continuous sampling.The results show that there was good agreement between the model prediction and the experimental values within 4.3 difference for each case.The CFD simulation results varied in the range from 0.21 mg/m3 to 0.94 mg/m3,and the measuring results in the range from 0.17 mg/m3 to 0.87 mg/m3.The variation trend of formaldehyde concentration with supply air rate and temperature variation for CFD simulation and experiment measuring was consistent.With the existence of steady formaldehyde emission sources,formaldehyde concentration generally increased with the increase of temperature,and it decreased with the increase of air supply rate.We also provided some reasonable suggestions to reduce formaldehyde concentration and to improve indoor air quality for newly decorated rooms.展开更多
In this paper, a manufacturing supply chain system composed by a single-product machine, a buffer and a stochastic demand is considered. A stochastic fluid model is adopted to describe the system and to take into acco...In this paper, a manufacturing supply chain system composed by a single-product machine, a buffer and a stochastic demand is considered. A stochastic fluid model is adopted to describe the system and to take into account stochastic delivery times. The objective of this paper is to evaluate the optimal buffer level used in hedging point policy taken into account planned delivery times, machine failures and random demands. This optimal buffer allows minimizing the sum of inventory, transportation, lost sales and late delivery costs. Infinitesimal perturbation analysis method is used for optimizing the proposed system. Using the stochastic fluid model, the trajectories of buffer level are studied and the infinitesimal perturbation analysis estimators are evaluated. These estimators are shown to be unbiased and then they are implanted in an optimization algorithm, which determines the optimal buffer level in the presence of planned delivery time. Also in this work, we discuss the advantage of the use of the infinitesimal perturbation analysis method comparing to classical simulation methods.展开更多
文摘Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient fluid supply in oil wells based on convolutional neural networks is proposed in this paper. Firstly, 5000 indicator diagrams with insufficient liquid supply were collected from the oilfield site, and a sample set was established after preprocessing;then based on the AlexNet model, combined with the characteristics of the indicator diagram, a convolutional neural network model including 4 layers of convolutional layers, 3 layers of down-pooling layers and 2 layers of fully connected layers is established. The backpropagation, ReLu activation function and dropout regularization method are used to complete the training of the convolutional neural network;finally, the performance of the convolutional neural network under different iteration times and network structure is compared, and the super parameter optimization of the model is completed. It has laid a good foundation for realizing the self-adaptive and intelligent matching of oil well production parameters and formation fluid supply conditions. It has certain application prospects. The results show that the accuracy of training and verification of the method exceeds 98%, which can meet the actual application requirements on site.
基金The National Natural Science Foundation of China(No.50478113)the Leading Academic Discipline Project of Shanghai Municipal Education Commission(No.J50502)
文摘To study the draft sensation distribution of an air jet supply system in a large space building in summer,experiments are conducted in a large laboratory.The temperature,velocity and draft sensation distributions at a nozzle height of 4 m in the occupied zone are obtained.Then,the numerical simulation under the test condition is carried out by the computational fluid dynamics（CFD）method.The calculation results of the indoor vertical temperature and the draft sensation distribution are validated by the test data.Simulations with different nozzle heights are conducted.The satisfactory air supply condition is determined by analyzing the draft sensations and the temperatures in the occupied zone under three conditions.The simulation results show that the optimal draft sensation distribution and the uniform temperature and velocity fields can be obtained at a nozzle height of 5 m.
基金Funded by National Science Foundation(No.50778415 and No.50878177)
文摘We investigated the effect of supply air rate and temperature on formaldehyde emission characteristics in an environment chamber.A three-dimensional computational fluid dynamics(CFD) chamber model for simulating formaldehyde emission in twelve different cases was developed for obtaining formaldehyde concentration by the area-weighted average method.Laboratory experiments were conducted in an environment chamber to validate the simulation results of twelve different cases and the formaldehyde concentration was measured by continuous sampling.The results show that there was good agreement between the model prediction and the experimental values within 4.3 difference for each case.The CFD simulation results varied in the range from 0.21 mg/m3 to 0.94 mg/m3,and the measuring results in the range from 0.17 mg/m3 to 0.87 mg/m3.The variation trend of formaldehyde concentration with supply air rate and temperature variation for CFD simulation and experiment measuring was consistent.With the existence of steady formaldehyde emission sources,formaldehyde concentration generally increased with the increase of temperature,and it decreased with the increase of air supply rate.We also provided some reasonable suggestions to reduce formaldehyde concentration and to improve indoor air quality for newly decorated rooms.
文摘In this paper, a manufacturing supply chain system composed by a single-product machine, a buffer and a stochastic demand is considered. A stochastic fluid model is adopted to describe the system and to take into account stochastic delivery times. The objective of this paper is to evaluate the optimal buffer level used in hedging point policy taken into account planned delivery times, machine failures and random demands. This optimal buffer allows minimizing the sum of inventory, transportation, lost sales and late delivery costs. Infinitesimal perturbation analysis method is used for optimizing the proposed system. Using the stochastic fluid model, the trajectories of buffer level are studied and the infinitesimal perturbation analysis estimators are evaluated. These estimators are shown to be unbiased and then they are implanted in an optimization algorithm, which determines the optimal buffer level in the presence of planned delivery time. Also in this work, we discuss the advantage of the use of the infinitesimal perturbation analysis method comparing to classical simulation methods.
