Effective health diagnosis provides multifarious benefits such as improved safety, reliability and economical maintenance of complex engineered systems. This paper presents a novel multi-sensor health diagnosis method using Deep Belief Network (DBN) based state classification. The DBN employs a hierarchical structure with multiple stacked Restricted Boltzmann Machines and works through a layer by layer successive learning process. The proposed multi-sensor health diagnosis can be structured in three consecutive stages: first, defining health states and collecting sensory data for DBN training and testing; second, developing DBN based classification models for the diagnosis of predefined health states; third, validating DBN classification models with testing sensory dataset. The performance of proposed DBN health state classification is compared with four other existing classification methods and demonstrated with a case study.