The invention specifically discloses a condition diagnosis system for transformer fault types, belonging to the technical field of condition monitoring and fault diagnosis of power equipment. The condition diagnosis system comprises an oil sample collection module, an oil-gas separation module, a gas separation module, a gas detection module, a data processing module and a data transmission module. The condition diagnosis system provided by the invention successfully realizes rapid, accurate and real-time detection of the composition and concentrations of dissolved gases in the insulating oil of a transformer, avoids the shortcoming of lack of monitoring means with long-term stability and credible precision in the operation and maintenance of the transformer, and provides reliable data for online evaluation and analysis of the operating state and remaining life of the transformer; and a sample retrieval algorithm based on Euclidean distance is innovatively introduced for identification of fault types, so the condition diagnosis system overcomes problems in fuzziness and applicability of data about dissolved gases in the insulating oil, is improved in accuracy and timeliness of fault recognition, and achieves the goal of comprehensive optimization of risks, efficiency and cost in power safety production.