The multi-fault phenomena are common in the turbo-rotor system of a liquid rocket engine. As it has many excellent qualities, the neural network might be used to solve the problems of multi-fault diagnosis of a turbo-rotor system. First, the feature expression of a common turbo-rotor fault was studied in order to build up the standard fault pattern and satisfy the need of neural network studying and diagnosing. Then, the turbo-rotor fault identification and diagnosis problems were investigated by using a BP(back-propagation) neural network. According to the BP neural network problems, the parallel BP neural network method of multi-fault diagnosis and classification was presented and investigated. The results indicated that the parallel BP neural network method could solve the turbo-rotor multi-fault diagnosis problems. The multi-fault phenomena are common in the turbo-rotor system of a liquid rocket engine. As it has many excellent qualities, the neural network might be used to solve the problems of multi-fault diagnosis of a turbo-rotor system. First, the feature expression of a common turbo-rotor fault was studied in order to build up the standard fault pattern and satisfy the need of neural network studying and diagnosing. Then, the turbo-rotor fault identification and diagnosis problems were investigated by using a BP ( back-propagation) neural network. According to the BP neural network problems, the parallel BP neural network method of multi-fault diagnosis and classification was presented and investigated. The results indicated that the parallel BP neural network method could solve the turbo-rotor multi -fault diagnosis problems.