基于HSIWOA-LSTM模型的工厂空调系统节能优化研究OA
Research on energy-saving optimization of factory air conditioning system based on HSIWOA-LSTM model
为解决工厂空调系统能耗高、运行参数匹配性差的问题,提出基于改进鲸鱼优化算法(HSIWOA)优化长短期记忆网络(LSTM)的节能优化模型.通过混沌初始化等策略改进WOA算法,提升其优化性能;利用HSIWOA优化LSTM超参数,构建HSIWOA-LSTM能耗预测与优化模型,并以某电子工厂为研究对象展开分析.结果表明,HSIWOA算法最终适应度值由传统WOA模型的1.48降至0.88,降低40.5%;HSIWOA-LSTM模型预测精度明显优于传统LSTM模型和WOA-LSTM模型.应用该模型后,空调日均能耗降低12.8%,月均节约电费约1.20万元,节能效果明显.
To address the issues of high energy consumption and poor matching of operating parameters in the factory's air conditioning system,an energy-saving optimization model based on the improved whale optimization algorithm(HSIWOA)and the long short-term memory network(LSTM)is proposed.The WOA algorithm is improved by strategies such as chaotic initialization to enhance its optimization performance.The HSIWOA algorithm is used to optimize the hyperparameters of LSTM to construct the HSIWOA-LSTM energy consumption prediction and optimization model.The model is analyzed using an electronic factory as the research object.The results show that the final fitness value of the HSIWOA algorithm is reduced from 1.48 in the traditional WOA model to 0.88,a decrease of 40.5%.The prediction accuracy of the HSIWOA-LSTM model is significantly better than that of the traditional LSTM model and the WOA-LSTM model.After applying the model,the average daily energy consumption of the air conditioning system is reduced by 12.8%,and the monthly electricity savings amount to 12 000 yuan,demonstrating a significant energy-saving effect.
崔明宇;邹惠芬
沈阳建筑大学市政与环境工程学院,辽宁 沈阳 110168沈阳建筑大学市政与环境工程学院,辽宁 沈阳 110168
建筑与水利
工厂空调系统节能优化改进鲸鱼优化算法长短期记忆网络
factory air conditioning systemenergy-saving optimizationimproved whale optimization algorithmlong short-term memory network
《节能》 2026 (8)
12-16,5
评论