This paper proposes a novel method of intelligent condition diagnosis for rotating machinery using non-dimensional symptom parameter (NSP) and particle swarm optimization (PSO) to detect faults and distinguish fault types at an early stage. NSPs in the time domain are defined for reflecting the features of vibration signals measured in each state. The state identification for the condition diagnosis of rotating machinery is converted to a clustering problem of the values of the NSPs, calculated from vibration signals in different states of the machine. PSO is also introduced for this purpose. Moreover, synthetic detection index (SDI) using statistical theory has also defined to evaluate the applicability of the NSPs for the condition diagnosis measured in each state. The SDI can be used to indicate the fitness of a NSP for PSO. A practical example of condition diagnosis for a rolling bearing used in the centrifugal fan system verifies that the method is effective.