基于前馈神经网络的焓差试验台故障预测
|
摘要
本文提出了一种基于前馈神经网络的焓差试验台故障预测模型,定义了查准率、查全率与F1系数作为模型的评判依据。基于空调焓差试验台的长期运行数据,建立前馈神经网络预测模型,并采取多种优化策略和方式改进模型。最终基于测试集数据进行性能测试,验证了该模型对焓差试验台故障预测的有效性。在一年多的试验工况下,该模型所预测的焓差试验台故障达到了93.33%的查准率与95.02%的查全率、以及94.14%的F1系数。对焓差试验台使用该模型,可有效预测台架故障,从而采取应对措施,减少试验台架故障导致的损失。
A fault prediction model based on feedforward neural network for enthalpy difference testbench is proposed. The precision, recall and F1 coefficient are defined as the basis for the model evaluation. Based on the long-term operation data of the air conditioning enthalpy difference testbench, the feedforward neural network model is built and improved in various optimization strategies and methods. Finally, the performance test is carried out on the test set to verify the effectiveness of the model for fault prediction of the enthalpy difference testbench. Under the experimental conditions for more than one year, the model predicts the faults of enthalpy difference testbench with the precision of 93.33%, the recall rate of 95.02% and F1 coefficient of 94.14%. Using this model for the enthalpy difference testbench can effectively predict the faults and take countermeasures to reduce the loss caused by the faults of enthalpy difference testbench.
A fault prediction model based on feedforward neural network for enthalpy difference testbench is proposed. The precision, recall and F1 coefficient are defined as the basis for the model evaluation. Based on the long-term operation data of the air conditioning enthalpy difference testbench, the feedforward neural network model is built and improved in various optimization strategies and methods. Finally, the performance test is carried out on the test set to verify the effectiveness of the model for fault prediction of the enthalpy difference testbench. Under the experimental conditions for more than one year, the model predicts the faults of enthalpy difference testbench with the precision of 93.33%, the recall rate of 95.02% and F1 coefficient of 94.14%. Using this model for the enthalpy difference testbench can effectively predict the faults and take countermeasures to reduce the loss caused by the faults of enthalpy difference testbench.
引文
[1]徐志亮,严玉雄.焓差法试验室调试常见问题分析[J].制冷与空调,2007,7(3):66-70.
[2]吴明强,史慧,朱晓华,等.故障诊断专家系统研究的现状与展望[J].计算机测量与控制,2005(12):1301-1304.
[3]何勇枢,陈赣.基于BP神经网络模型的故障预测分析[J].微计算机信息,2006,22(16):13,227-229.
[4]钱宇宁.机械系统旋转部件退化跟踪与故障预测方法研究[D].南京:东南大学,2015.
[5]袁玥,陈焕新,石书彪,等.基于主成分分析和神经网络相结合的制冷剂充注量故障诊断[J].制冷技术,2017,37(6):45-50.
[6]康健,左宪章,吴彩华,等.基于神经网络的柴油发动机故障预测研究[J].计算机测量与控制,2006,14(8):987-989.
[7]寻惟德,李绍斌,谭泽汉,等.基于离散型Hopfield神经网络的制冷剂充注量故障诊断的新策略[J].制冷技术,2018,38(3):8-13.
[8]禹法文,陈焕新,李绍斌,等.基于主元分析法的多联机系统压缩机排气温度传感器故障检测与诊断[J].制冷技术,2017,37(4):29-33.
[9]GEBRAEEL N Z,LAWLEY M A.A neural network degradation model for computing and updating residual life distributions[J].IEEE Transactions on Automation Science and Engineering,2008,5(1):154-163.
[10]LIUKKONEN M,HILTUNEN T,HAVIA E,et al.Modeling of soldering quality by using artificial neural networks[J].IEEE Transactions on Electronics Packaging Manufacturing,2009,32(2):89-96.
[11]陈玲,陈志杰,杜志敏,等.基于减法聚类和支持向量机的故障诊断方法研究[J].制冷技术,2018,38(4):1-5.
[12]郑小海,谭泽汉,郭亚宾,等.基于支持向量机和粒子群算法的多联机气液分离器插反故障诊断[J].制冷技术,2018,38(4):16-20.
[13]YANG I H,YEO M S,KIM K W.Application of artificial neural network to predict the optimal start time for heating system in building[J].Energy Conversion and Management,2003,44(17):2791-2809.
[14]ZHU G,CHOW T T,LEE C K.Performance analysis of counter-flow regenerative heat and mass exchanger for indirect evaporative cooling based on data-driven model[J].Energy and Buildings,2017,155:503-512.
[15]魏峥,王碧玲.基于机器学习的冷水机组能耗模型辨识方法研究[J].建筑科学,2018,34(6):115-122.
[16]李晗,萧德云.基于数据驱动的故障诊断方法综述[J].控制与决策,2011,26(1):1-9,16.
[17]戴文战.基于三层BP网络的多指标综合评估方法及应用[J].系统工程理论与实践,1999,19(5):29-34.
[18]ZHANG K,ZHANG Z,LI Z,et al.Joint face detection and alignment using multitask cascaded convolutional networks[J].IEEE Signal Processing Letters,2016,23(10):1499-1503.
[19]罗艳芬.提高神经网络泛化能力的方法研究及仿真[J].电子世界,2018(17):82-84.
[20]张会生,吴微.一种具有自适应动量因子的BP算法[J].大连海事大学学报,2008,34(4):45-47,51.
[2]吴明强,史慧,朱晓华,等.故障诊断专家系统研究的现状与展望[J].计算机测量与控制,2005(12):1301-1304.
[3]何勇枢,陈赣.基于BP神经网络模型的故障预测分析[J].微计算机信息,2006,22(16):13,227-229.
[4]钱宇宁.机械系统旋转部件退化跟踪与故障预测方法研究[D].南京:东南大学,2015.
[5]袁玥,陈焕新,石书彪,等.基于主成分分析和神经网络相结合的制冷剂充注量故障诊断[J].制冷技术,2017,37(6):45-50.
[6]康健,左宪章,吴彩华,等.基于神经网络的柴油发动机故障预测研究[J].计算机测量与控制,2006,14(8):987-989.
[7]寻惟德,李绍斌,谭泽汉,等.基于离散型Hopfield神经网络的制冷剂充注量故障诊断的新策略[J].制冷技术,2018,38(3):8-13.
[8]禹法文,陈焕新,李绍斌,等.基于主元分析法的多联机系统压缩机排气温度传感器故障检测与诊断[J].制冷技术,2017,37(4):29-33.
[9]GEBRAEEL N Z,LAWLEY M A.A neural network degradation model for computing and updating residual life distributions[J].IEEE Transactions on Automation Science and Engineering,2008,5(1):154-163.
[10]LIUKKONEN M,HILTUNEN T,HAVIA E,et al.Modeling of soldering quality by using artificial neural networks[J].IEEE Transactions on Electronics Packaging Manufacturing,2009,32(2):89-96.
[11]陈玲,陈志杰,杜志敏,等.基于减法聚类和支持向量机的故障诊断方法研究[J].制冷技术,2018,38(4):1-5.
[12]郑小海,谭泽汉,郭亚宾,等.基于支持向量机和粒子群算法的多联机气液分离器插反故障诊断[J].制冷技术,2018,38(4):16-20.
[13]YANG I H,YEO M S,KIM K W.Application of artificial neural network to predict the optimal start time for heating system in building[J].Energy Conversion and Management,2003,44(17):2791-2809.
[14]ZHU G,CHOW T T,LEE C K.Performance analysis of counter-flow regenerative heat and mass exchanger for indirect evaporative cooling based on data-driven model[J].Energy and Buildings,2017,155:503-512.
[15]魏峥,王碧玲.基于机器学习的冷水机组能耗模型辨识方法研究[J].建筑科学,2018,34(6):115-122.
[16]李晗,萧德云.基于数据驱动的故障诊断方法综述[J].控制与决策,2011,26(1):1-9,16.
[17]戴文战.基于三层BP网络的多指标综合评估方法及应用[J].系统工程理论与实践,1999,19(5):29-34.
[18]ZHANG K,ZHANG Z,LI Z,et al.Joint face detection and alignment using multitask cascaded convolutional networks[J].IEEE Signal Processing Letters,2016,23(10):1499-1503.
[19]罗艳芬.提高神经网络泛化能力的方法研究及仿真[J].电子世界,2018(17):82-84.
[20]张会生,吴微.一种具有自适应动量因子的BP算法[J].大连海事大学学报,2008,34(4):45-47,51.