Trained speed of model based on traditional BP neural network was slowly and produced emanative result. A novel land evaluation model based on neural network with genetic optimization algorithm was presented in this paper. The neural network of model is front-network which comprised with five layers architecture which composed of dynamic inference with fuzzy rules where the consequent sub-models are implemented by recurrent neural networks. The recurrent neural networks with internal feedback paths and dynamic neuron synapses. In order to optimized the parameter structure and link weight between layers, the author adopted genetic algorithm into model. Experiment results demonstrated that the novel model exhibit superior performance such as enhanced representation power, calculation speed and veracity of result than traditional BP neural network and the other land evaluation models.
Currently, the higher wind energy extraction efficiency and the lower load are desirable for the maximum power point tracking (MPPT) of wind turbines. However, for the existing control strategies, the higher MPPT efficiency is achieved with the increase of the load. Hence, a dynamic fuzzy integral sliding mode control method is proposed in this paper. This method employs the tracking error of power and its integration as the sliding surface and uses a fuzzy control method to design the parameter of the sliding mode controller, which can improve the MPPT efficiency and reduce the load simultaneously. Then, simulations on FAST (Fatigue, Aerodynamics, Structures, and Turbulence) code are given to verify the effectiveness of this method.
Preamble collision is a bottleneck that impairs the performance of random access (RA) user equipment (UE) in grant-free RA (GFRA). In this paper, by leveraging distributed massive multiple input multiple output (mMIMO) together with machine learning, a novel machine learning based framework solution is proposed to address the preamble collision problem in GFRA. The key idea is to identify and employ the neighboring access points (APs) of a collided RA UE for its data decoding rather than all the APs, so that the mutual interference among collided RA UEs can be effectively mitigated. To this end, we first design a tailored deep neural network (DNN) to enable the preamble multiplicity estimation in GFRA, where an energy detection (ED) method is also proposed for performance comparison. With the estimated preamble multiplicity, we then propose a K-means AP clustering algorithm to cluster the neighboring APs of collided RA UEs and organize each AP cluster to decode the received data individually. Simulation results show that a decent performance of preamble multiplicity estimation in terms of accuracy and reliability can be achieved by the proposed DNN, and confirm that the proposed schemes are effective in preamble collision resolution in GFRA, which are able to achieve a near-optimal performance in terms of uplink achievable rate per collided RA UE, and offer significant performance improvement over traditional schemes.<br>
Digital twin is a core technology for smart power plants aiming to increase the safety and efficiency of power generation in low-carbon transitions. High-precision modelling of in-service power plant thermal systems plays a key role to develop digital twins but remains a challenge. There is a lack of high-precision modelling for in-service power plant thermal systems over the full working ranges to underpin digital twin development. This work proposes a hybrid modelling framework combining physical mechanism and operation data to develop grey-box models of thermal systems. Key equipment characteristics are figured out through historical operation data. Then mass balance, energy balance, process mechanism equations and characteristic equations consist of a system model. An in-service 660 MW ultra-supercritical double reheat power plant, one of the most advanced thermal power generation technologies, is selected as a case study. The grey-box model of high- and intermediate-pressure thermal system is established. Average simulation error of the model is 0.79 percent over the full working ranges. Furthermore, key system characteristics are quantified through the model. It demonstrates the high precision of the proposed modelling method over the full working ranges and provides necessary model support for the digital twin development of thermal power plants.
In the production of 20g(Ti)、410A、410B,the problems of impact toughness and strain aging toughness were resolved by optimizing chemical composition,purification of molten steel,temperature control of the start,final rolling and reduction course,refining the grain size and improving the microstructure of plate.The qualification rate of boiler plate was increased.
The Sub-6GHz spectrum is crucial for outdoor coverage in the fifth generation (5G) mobile communication systems. Considering the typical urban outdoor environment, one of the fundamental challenges for Sub-6GHz system is its susceptibility to occlusion effects. One way to alleviate this influence is to establish another line of sight link by using an intelligent reflecting surface (IRS). Nevertheless, the performance degradation due to the delay and overhead of the channel feedback can not be neglected. To address this issue, in this paper we propose a radio environment map (REM) based method for occlusion and channel prediction to reduce the delay and overhead. Based on the image information captured by the REM constructor, the user equipments' (UEs') location at the next moment are predicted firstly. Then we make prediction for occlusion and channel condition and determine the transmission mode (TM) for each UE. Finally, the optimal phase is obtained by solving a phase optimization problem under a given TM selection matrix constraint. Compared to the state-of-the-art approaches, simulation results show that our proposed method significantly improve the link reliability and energy efficiency.
The major barriers for applying carbon dioxide (CO 2 ) capture technology to coal-fired power plants in China and worldwide are the consequent drop in power plant energy efficiency and significantly higher cost of electricity (COE). This paper proposes a new perspective for determining the most cost-efficient CO 2 capture ratio using a modeling and simulation approach that balances the per unit parasitic energy consumption for absorbent regeneration with the per unit capital cost of the CO 2 capture unit of a coal-fired power plant. Using a typical 550 MW supercritical pulverized coal-fired power plant in China as the reference plant, with monoethanolamine (MEA) absorption unit for CO 2 capture, a process model of the power generation unit together with the MEA CO 2 capture unit was developed and detailed process simulations were conducted with the model. Then, a sensitivity analysis was then conducted to study the impact on key plant behavior indicators, including per unit energy penalty for absorbent regeneration, net power output and power generation efficiency, total capital cost of the power plant together with the MEA CO 2 absorption unit, per unit capital cost of the MEA unit, COE, as well as the per unit CO 2 avoidance cost (indicated by cost per tonne (t) CO 2 avoided), across a CO 2 capture ratio range between 20% and 99%. The results show that when CO 2 capture ratio is low, while the unit energy consumption for absorbent regeneration per tCO 2 avoided increases steadily with the increase of CO 2 capture ratio, the cost per tCO 2 avoided decreases as the MEA absorption train is scaled up given the high capital cost of each MEA train. After CO 2 capture ratio reaches certain level (60% for this plant), the cost per tCO 2 avoided starts to increase with CO 2 capture ratio, since the unit energy consumption for absorbent regeneration per tCO 2 avoided has increased to so high that it supplants the scaling effect of the MEA train and becomes the dominant factor that determines the increase or decrease trend of the cost per tCO 2 avoided. Besides, due to the physical restraint on the upper bound of CO 2 capture capability of one single MEA train by the diameter of the absorber, an additional MEA train is needed when the CO 2 capture ratio increases to certain points (40% and 85% for this plant), resulting in jumps of several parameters including the total capital cost for the power plant and MEA CO 2 capture unit, per unit capital cost for the MEA CO 2 capture unit, and last the cost per tCO 2 avoided. Based on all these result, finally a cost-optimal CO 2 capture ratio of 40% (365 RMB/tCO 2 -_avoided) was obtained, which is easier for the power plant to bear while realizing a significant reduction in CO 2 emission of this plant. Therefore, applying this approach for determining CO 2 capture ratios could help minimize the barrier for the initiation of carbon dioxide capture and storage (CCS) in China's power industry. Besides, future replacement or improvement for the MEA CO 2 capture technology has the potential to further reduce the cost per tCO 2 avoided, which needs special attention.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)