In recent years,water collecting systems,with the associated advantages of energy saving and noise reduction,have become the foundation for the development of a scheme to optimize the structure of cooling towers.To ex...In recent years,water collecting systems,with the associated advantages of energy saving and noise reduction,have become the foundation for the development of a scheme to optimize the structure of cooling towers.To explore the feasibility of this approach for mechanical draft cooling towers,a small-scale experimental device has been built to study the resistance and splash performances of three U-type water collecting devices(WCDs)for different water flow rates and wind speeds.The experimental results show that within the considered ranges of wind speed and water flow rate,the pressure drop of the different WCDs can vary significantly.The resistance and local splash performances can also be remarkably different.Some recommendations about the most suitable system are provided.Moreover,a regression analysis of the experimental data is conducted,and the resulting fitting formulas for resistance and splash performance of WCD are reported.展开更多
This paper is concerned with water saving for water-loop cooling tower system in power plants. A newly developed water saving device of swirling flow is presented. The key point is that the new water saving device mak...This paper is concerned with water saving for water-loop cooling tower system in power plants. A newly developed water saving device of swirling flow is presented. The key point is that the new water saving device makes the steam swirl up along the device wall rather than engender laminar flow in a corrugated plate. The corrugated plate device can save approximately 10 percent of the total lost water. In contrast to the scale model of corrugated plate water saving device, experimental analyses have demonstrated that the new water saving device of swirling flow is more efficient, with a capacity of saving more than 20 percent of water.展开更多
Deep Q Network(DQN)is an efficient model-free optimization method,and has the potential to be used in building cooling water systems.However,due to the high dimension of actions,this method requires a complex neural n...Deep Q Network(DQN)is an efficient model-free optimization method,and has the potential to be used in building cooling water systems.However,due to the high dimension of actions,this method requires a complex neural network.Therefore,both the required number of training samples and the length of convergence period are barriers for real application.Furthermore,penalty function based exploration may lead to unsafe actions,causing the application of this optimization method even more difficult.To solve these problems,an approach to limit the action space within a safe area is proposed in this paper.First of all,the action space for cooling towers and pumps are separated into two sub-regions.Secondly,for each type of equipment,the action space is further divided into safe and unsafe regions.As a result,the convergence speed is significantly improved.Compared with the traditional DQN method in a simulation environment validated by real data,the proposed method is able to save the convergence time by 1 episode(one cooling season).The results in this paper suggest that,the proposed DQN method can achieve a much quicker learning speed without any undesired consequences,and therefore is more suitable to be used in projects without pre-learning stage.展开更多
基金This work was supported by the Shandong Natural Science Foundation(Grant No.ZR2022ME008)the Shenzhen Science and Technology Program(KCXFZ20201221173409026)+2 种基金the Young Scholars Program of Shandong University(YSPSDU,No.2018WLJH73)the Open Project of State Key Laboratory of Clean Energy Utilization,Zhejiang University(Program No.ZJUCEU2020011)the Shandong Natural Science Foundation(Grant No.ZR2021ME118).
文摘In recent years,water collecting systems,with the associated advantages of energy saving and noise reduction,have become the foundation for the development of a scheme to optimize the structure of cooling towers.To explore the feasibility of this approach for mechanical draft cooling towers,a small-scale experimental device has been built to study the resistance and splash performances of three U-type water collecting devices(WCDs)for different water flow rates and wind speeds.The experimental results show that within the considered ranges of wind speed and water flow rate,the pressure drop of the different WCDs can vary significantly.The resistance and local splash performances can also be remarkably different.Some recommendations about the most suitable system are provided.Moreover,a regression analysis of the experimental data is conducted,and the resulting fitting formulas for resistance and splash performance of WCD are reported.
文摘This paper is concerned with water saving for water-loop cooling tower system in power plants. A newly developed water saving device of swirling flow is presented. The key point is that the new water saving device makes the steam swirl up along the device wall rather than engender laminar flow in a corrugated plate. The corrugated plate device can save approximately 10 percent of the total lost water. In contrast to the scale model of corrugated plate water saving device, experimental analyses have demonstrated that the new water saving device of swirling flow is more efficient, with a capacity of saving more than 20 percent of water.
文摘Deep Q Network(DQN)is an efficient model-free optimization method,and has the potential to be used in building cooling water systems.However,due to the high dimension of actions,this method requires a complex neural network.Therefore,both the required number of training samples and the length of convergence period are barriers for real application.Furthermore,penalty function based exploration may lead to unsafe actions,causing the application of this optimization method even more difficult.To solve these problems,an approach to limit the action space within a safe area is proposed in this paper.First of all,the action space for cooling towers and pumps are separated into two sub-regions.Secondly,for each type of equipment,the action space is further divided into safe and unsafe regions.As a result,the convergence speed is significantly improved.Compared with the traditional DQN method in a simulation environment validated by real data,the proposed method is able to save the convergence time by 1 episode(one cooling season).The results in this paper suggest that,the proposed DQN method can achieve a much quicker learning speed without any undesired consequences,and therefore is more suitable to be used in projects without pre-learning stage.
