Abstract Air-ratio, also called lambda, is an engine parameter relates closely to vehicular emissions, engine power and brake-specific fuel consumption. Little variation in the air-ratio can significantly affect the vehicular emissions, engine power and fuel consumption. Control the air-ratio to the optimal value according to various operating conditions is significant and effective to reduce pollutant emissions, save energy and improve drivability. So a novel air-ratio control strategy based on model predictive control is proposed in this research. The prediction model of the proposed air-ratio control strategy is constructed and updated with an advanced machine learning technique called online wavelet least-squares support vector machines. Such modelling technique adopts wavelet function as the support vector kernel that can inherit the local analysis ability and feature extraction from the wavelet transformation, as well as a novel online incremental and decremental updating procedure that can maintain the constructed prediction model to be accurate, sparse and updated without losing the generalization by continually adding the latest useful data and pruning out the outdated data. Besides, a fuzzy optimizer is proposed to replace the traditional optimization methods for determining the optimal control signal for the control strategy. Furthermore, a supplementary air-ratio model is constructed without selecting the measured air-ratio as the input signal in order to extend the proposed control strategy as a fault tolerant control algorithm so that the proposed control strategy can maintain a satisfactory air-ratio control performance even though the lambda sensor is under failure or during cold start. The proposed control strategy was implemented on a real performance test car and compared with the latest air-ratio control techniques based on various modelling algorithms, optimizers, updating procedure and support vector kernel for evaluating the effectiveness. Besides the iii experimental comparison, the stability of the proposed control strategy is also analyzed in this research. Both experimental and analytical results show the proposed control strategy is a promising scheme for air-ratio regulation.