The induction motor is the most common driver in industry and has been previously proposed as a means of inferring the condition of an entire equipment train, predominantly through the measurement and processing of power supply parameters. This has obvious advantages in terms of being non-intrusive or remote, less costly to apply and improved safety. This paper describes the use of the induction motor current to identify and quantify a number of common faults seeded on a two-stage reciprocating compressor. An analysis of the compressor working cycle leads to current signal the components that are sensitive to the common faults seeded to compressor system, and second- and third-order signal processing tools are used to analyse the current signals. It is shown that the developed diagnostic features: the bispectral peak value from the amplitude modulation bispectrum and the kurtosis from the current gives rise to reliable fault classification results. The low feature values can differentiate the belt looseness from other fault cases and valve leakage and inter-cooler leakage can be separated easily using two linear classifiers. This work provides a novel approach to the analysis stator current data for the diagnosis of motor drive faults.