Data-driven Automated Fault Detection and Diagnosis (AFDD) is the automated process of detecting deviations (faults) from normal operation and diagnosing the type of problem and/or its location based on the exploitation of data collected under normal and faulty conditions. The performance of a typical single-duct dual-fan constant air volume air-handling unit (AHU) are investigated through a number of experiments performed during Italian cooling and heating seasons under both fault free and faulty scenarios. The AHU operation is analysed while artificially introducing six typical faults: 1) positive offset (+3 °C) of the return air temperature sensor; 2) negative offset (−3 °C) of the return air temperature sensor; 3) positive offset (+15%) of the return air relative humidity sensor; 4) negative offset (−15%) of the return air relative humidity sensor; 5) complete failure of the return air fan; 6) complete failure of the supply air fan. The faulty tests are compared with the fault free experiments performed under the same boundary conditions to assess the impacts of the faults on both thermal/hygrometric indoor comfort and patterns of key operating parameters with the aim of supporting the studies focusing on new and accurate data-driven AFDD methods for AHUs.

数据驱动的自动故障检测和诊断 (AFDD) 是检测与正常操作的偏差（故障）并根据在正常和故障条件下收集的数据的利用来诊断问题类型和/或其位置的自动化过程。通过在意大利制冷和供暖季节在无故障和故障情况下进行的大量实验，研究了典型的单风道双风扇恒风量空气处理机组 (AHU) 的性能。分析AHU运行情况，人为引入6个典型故障：1）回风温度传感器正偏移（+3℃）；2）回风温度传感器的负偏移（-3℃）；3）回风相对湿度传感器正偏移（+15%）；4）回风相对湿度传感器的负偏移（-15%）；5）回风风机完全失效；6）送风机完全失效。将故障测试与在相同边界条件下进行的无故障实验进行比较，以评估故障对室内热/湿度舒适度和关键运行参数模式的影响，以支持专注于新的和准确数据的研究-用于 AHU 的驱动 AFDD 方法。