CAJ | 학술논문

房间空调器实际运行过程中的能效是空调器持续节能的重要考核指标，为研究房间空调器长效运行性能特性，采用BP神经网络进行新机器的性能预测分析，获得在多因素影响下选择成本最优的空调长效性能的设计方法。BP网络的学习样本来自于旧机器实验室测试数据及房间空调器在真实运行工况下的在线监测动态衰减数据，通过对大量样本数据的学习，分析影响长效运行性能各因素的权重，确定长效运行性能的优化策略。对26台使用中的房间空调器进行性能进行测试，85%的样本作为数学模型的训练样本，15%的样本作为模型验证样本，结果表明，采用小样本训练的BP神经网络预测的长效综合评价值误差均在5%以内，预测结果收敛；经过对BP神经网络的权重分析，时间加权后的高温制冷性能、额定制冷性能、低温制热性能、额定制热性能归一化值所占决策权重分别为0.187、0.203、0.312、0.298。为验证BP网络的正确性，建立房间空调器在线性能监测系统软硬件及长效性能分析预测软件平台，通过大量和长期在用空调的实测数据，验证和优化BP网络。基于以上基础数据，进一步提出大数据关联规则挖掘模型应用于空调器长效分析的研究思路，应用于多因素影响下空调长效特性的优化设计。
방간공조기실제운행과정중적능효시공조기지속절능적중요고핵지표，위연구방간공조기장효운행성능특성，채용BP신경망락진행신궤기적성능예측분석，획득재다인소영향하선택성본최우적공조장효성능적설계방법。BP망락적학습양본래자우구궤기실험실측시수거급방간공조기재진실운행공황하적재선감측동태쇠감수거，통과대대량양본수거적학습，분석영향장효운행성능각인소적권중，학정장효운행성능적우화책략。대26태사용중적방간공조기진행성능진행측시，85%적양본작위수학모형적훈련양본，15%적양본작위모형험증양본，결과표명，채용소양본훈련적BP신경망락예측적장효종합평개치오차균재5%이내，예측결과수렴；경과대BP신경망락적권중분석，시간가권후적고온제랭성능、액정제랭성능、저온제열성능、액정제열성능귀일화치소점결책권중분별위0.187、0.203、0.312、0.298。위험증BP망락적정학성，건립방간공조기재선성능감측계통연경건급장효성능분석예측연건평태，통과대량화장기재용공조적실측수거，험증화우화BP망락。기우이상기출수거，진일보제출대수거관련규칙알굴모형응용우공조기장효분석적연구사로，응용우다인소영향하공조장효특성적우화설계。
Performance of occupied room air-conditioner(RAC) is an important evaluation index to estimate RAC continue energy saving efficiency. In order to investigate characteristic of RAC long-term performance(LTP) and acquire the cost optimation design methodology of high LTP in multi-factors impact condition, a BP neural network prediction method has been applied. The training sample of LTP prediction BP neural network acquired form experimental result of occupied RACs and data of RACs dynamic LTP on-line monitor system. By a large size of training sample, the decision weights of multi-impact factors and LTP optimation strategies can be obtained. The performances of 26 occupied RACs have also been tested. 85% of testing data ias served as training sample data and 15% of testing data ias served as validation data to LTP prediction BP neural network. The result indicated that the prediction is convergence and error is less than 5% during the BP neural network training by 22 samples. The decision weights of time weighted high temperature cooling, rated cooling, low temperature heating, rated heating normalized performance value are 0.187, 0.203, 0.312, 0.298, respectively. For further increasing the prediction precision, RAC performance online monitor system and LTP online data acquisition website has been established for data acquisition to validate LTP prediction BP neural network. Based on the acquisition database, a big data mining method has also been proposed in RAC LTP optimization design and investigation.