The ground source heat pump (GSHP) is a commonly employed technique that utilises geothermal resources to heat or cool buildings, offering an advantageous alternative for reducing conventional energy consumption. Cons...
详细信息
The ground source heat pump (GSHP) is a commonly employed technique that utilises geothermal resources to heat or cool buildings, offering an advantageous alternative for reducing conventional energy consumption. Considering that the output energy of GSHP system is a critical criterion for evaluating the geothermal energy extraction, this study proposes an improved long short-term memory (LSTM) model for predicting the energy output of geothermal heat exchangers (GHE) EGHE-PT and the electrical energy consumption EEC-PT of a GSHP system. The model is trained and validated using a comprehensive real-time monitoring dataset gathered over a four-year period from a three-story residential house situated in Cleveland, Ohio, USA. To process the raw data, the wavelet denoising method is employed, while the fast non-dominated sorting genetic algorithm-II (NSGA-II) is employed to automatically determine the optimal hyperparameters for the LSTM model. Comparative analyses with alternative prediction models demonstrate the superior performance of the Denoised-LSTM-NSGA-II model. The results indicate that the Denoised-LSTM-NSGA-II model yields reasonable prediction for the two performance indicators: EGHE-PT and EEC-PT (with the R2 of 0.91 and 0.89, respectively). Further examination reveals that outdoor temperature holds a significantly high importance rank within the Denoised-LSTM-NSGA-II model. This implies that the proposed method can achieve an acceptable level of accuracy by only utilising weather data from the preceding 5 days. The aforementioned findings present a potentially cost-effective approach for predicting the performance of GSHP system based on limited monitoring data.
This study employs a multi-objective optimization approach integrating the fast non-dominated sorting genetic algorithm (NSGA-II) and response surface methodology (RSM) to enhance the performance of battery thermal ma...
详细信息
This study employs a multi-objective optimization approach integrating the fast non-dominated sorting genetic algorithm (NSGA-II) and response surface methodology (RSM) to enhance the performance of battery thermal management systems (BTMS) through the design and optimization of a novel bionic lotus leaf (NBLL) channel. Heat generation rates, obtained from lithium-ion battery (LIB) testing experiments conducted under various discharge rates, along with design variables such as channel spacing, width, angle, and mass flow rate, are optimized. The objective functions, comprising maximum temperature difference, heat transfer coefficient, and pressure drop, are optimized while adhering to a maximum temperature constraint. Optimal Latin Hypercube Sampling (OLHS) is utilized for selecting design points, and RSM constructs objective function expressions. The optimal combination is determined through the Pareto optimal frontier generated by NSGA-II. Relative to the initial model, the optimized design demonstrates a reduction in the maximum temperature difference by 14.898 %, an increase in the heat transfer coefficient by 35.786 %, and a decrease in the pressure drop by 68.325 %. This optimized BTMS design significantly enhances heat dissipation performance, which is crucial for battery performance, longevity, and safety in the realm of battery thermal management.
Evolutionary algorithms are optimization methods commonly used to solve engineering and business optimization problems. The parameters in evolutionary algorithm must be perfectly tuned in a way that the optimization a...
详细信息
Evolutionary algorithms are optimization methods commonly used to solve engineering and business optimization problems. The parameters in evolutionary algorithm must be perfectly tuned in a way that the optimization algorithm solves the optimization problems efficiently and effectively. Several parameter tuning approaches with a single performance metric have been proposed in the literature. However, simultaneous consideration of multiple performance metrics could provide the optimal setting for the parameters in the evolutionary algorithm. In this research, a new hybrid parameter tuning approach is proposed to simultaneously optimize the performance metrics of the evolutionary optimization algorithm while it is used in solving an optimization problem. The proposed hybrid approach provides the optimal value of parameters of the evolutionary optimization algorithm. The proposed approach is the first parameter tuning approach in the evolutionary optimization algorithm which simultaneously optimizes all performance metrics of the evolutionary optimization algorithm. To do this, a full factorial design of experiment is used to find the significant parameters of the evolutionary optimization algorithm, as well as an approximate equation for each performance metric. The individual and composite desirability function approaches are then proposed to provide the optimal setting for the parameters of the evolutionary optimization algorithm. For the first time, we use the desirability function approach to find an optimal level for the parameters in the evolutionary optimization algorithm. To show the real application of the proposed parameter tuning approach, we consider two multi-objective evolutionary algorithms, i.e., a multi-objective particle swarm optimization algorithm (MOPSO) and a fast non-dominated sorting genetic algorithm (NSGA-III) and solve a single machine scheduling problem. We demonstrate the applicability and efficiency of the proposed hybrid approach in prov
暂无评论