For the characteristics of randomness and fuzziness of tool wear,the prediction method of tool wear was proposed based on uncertainty cloud reasoning model.First of all,the reverse cloud algorithm was used to calculate the three cloud characteristics parameters of tool wear acoustic emission signal parameters,expectation,entropy and hyper entropy.Secondly,the relationship between different wear stages wear trends and the different wear stages cloud characteristic parameter was mined,and the cloud prediction rules based on cloud condition generator were built.Lastly,multi-condition and single rule wear prediction model was set up.The results show that the cloud reasoning tool wear prediction model conforms to the law of tool wear;for non-deterministic model prediction,cloud reasoning is more in line with the actual situation than fuzzy reasoning.In addition,this method can reflect the real-time condition of the tool wear,has strong practicability.