基于投票机制的暖通空调空气处理单元传感器故障诊断

Sensor Fault Diagnosis for Air Handling Unit of Heating Ventilation and Air Conditioning Based on Voting Mechanism

现有暖通空调(HVAC)空气处理单元(AHU)的故障诊断研究往往是集中式的。少量的分布式方法大多需要求解大量耗时的优化问题,使得无法及时完成故障诊断。针对以上挑战,该文提出一种基于投票机制的分布式故障诊断方法。在该方法中,建立一个玻尔兹曼机来描述传感器网络,通过传感器之间的相互投票来确定玻尔兹曼机的边权值,基于边权值对玻尔兹曼机的状态也就是传感器的状态进行迭代,从而定位传感器的故障。设计了一种基于欧氏距离的投票策略确定投票值。开发了一种方法,通过在玻尔兹曼机中增加一个额外的节点来重置其权值矩阵,在将玻尔兹曼机对称化的同时,保持原来各传感器之间的投票关系,以保证玻尔兹曼机状态的迭代收敛。该方法不需要求解大量的优化问题,相较于当前的分布式方法计算量小。使用ASHRAE Project RP-1312提供的实际数据对所提方法进行验证。实验结果表明所提方法可以精确且高效地诊断出空气处理单元传感器的偏差故障和漂移故障。

Existing fault diagnosis methods developed for Air Handling Unit(AHU)of Heating Ventilation and Air Conditioning(HVAC)tend to be centralized.The few distributed methods usually require solving a large number of time-consuming optimization problems,making it impossible to complete fault diagnosis in a timely manner.In response to the above challenges,a distributed fault diagnosis method based on a novel voting mechanism is proposed.In this method,a novel voting mechanism is proposed to establish a Boltzmann machine to describe the sensor network,determine the edge weights of the Boltzmann machine through mutual voting among sensors,and iterate over the state of the Boltzmann machine,which is also the state of the sensors,based on the edge weights to locate the sensor faults.Moreover,a novel voting strategy based on Euclidean distance is designed to determine the voting values.Additionally,a method is developed to reset the Boltzmann machine’s weight matrix by adding a node to the Boltzmann machine,which maintains the original voting relationship among the sensors while symmetrizing the Boltzmann machine to ensure convergence of the iteration of the Boltzmann machine state.This method does not need solving many optimization problems,leading to lower computational requirements compared to existing distributed methods.The proposed method is validated using actual data provided by ASHRAE Project RP-1312.The experimental results show that the proposed method can accurately and efficiently diagnose bias and drift faults in AHU sensors.