A strategy based on neural networks is presented to diagnose the measurement faults of outdoor and supply flow sensor, and accomplish the fault tolerant control of outdoor air flow when the fault occurs. The neural networks are trained using the data collected under various normal conditions. The residual between the measurement of flow sensor and the output of the neural network is used to identify the faults. When the fault of outdoor or supply air flow sensor occurs, the recovered estimate of outdoor or supply air flow rate obtained from the network is used in the feedback control loop to regain the control of outdoor air flow. Simulation results are presented that demonstrate the IAQ and energy performance of the system under fault-tolerant control strategy in the presence of the failure of outdoor or supply air flow sensor.