中央空调制冷系统节能诊断模型分析

Analysis of Energy-Saving Diagnostic Models for Central Air-Conditioning Refrigeration Systems

针对中央空调运营中存在的粗放管理和能源浪费问题,提出了一种基于改进PSO-SVM神经网络的建筑节能诊断模型。通过聚类算法从收集的能耗历史数据中选取节能特性较好的运行数据作为模型建立的数据基础。利用Adaboost算法对PSO-SVM神经网络进行优化,完成模型构建,利用节能数据完成模型的训练。最后,建立异常能耗的判断标准,利用训练好的节能诊断模型对当前时刻的能耗情况进行诊断。通过分析和验证,建立的节能诊断模型的节能率由-1.1%提高到11.9%,并成功诊断出中央空调运行过程中产生的问题时刻。

A building energy-saving diagnosis model based on an improved PSO-SVM neural network is proposed to address the problems of gross management and energy wastage in central air-conditioning operations.Firstly,operational data with good energy saving characteristics are selected from the collected energy consumption history data by means of clustering algorithm as the data basis for model building.Secondly,the PSO-SVM neural network is optimised using the Adaboost algorithm to complete the model construction,and the training of the model is completed using the energy saving data.Finally,the judgement criteria for abnormal energy consumption are established,and the trained energy-saving diagnostic model is used to diagnose the energy consumption situation at the current moment.Through analysis and validation,the energy saving rate of the established energy saving diagnostic model was increased from-1.1%to 11.9%,and the problematic moments arising during the operation of the central air-conditioner were successfully diagnosed.