It is significant to identify the running-states by obtaining and analyzing the vibration signals to avoid the faults. In this paper, the state recognition system is built based on the feature extraction with Varying Scale (VS) theory and Hidden Semi-Markov model (HSMM) with the example of bushing abrasion on diesel engine. The veracity of state identification can be improved effectively by banding them together. According to experiment and simulation researches, it indicates that the veracity of identification is 97.5% in the 120 test samples after training with 80 training samples. It is satisfied for the demand to the engineering domain and it can be applied for vibration analysis for other complex machineries.