A robust self-adaptive dynamic surface control method for an adjustable metal cutting system is characterized by comprising the steps of description of an adjustable metal cutting system mathematical model, a hysteresis model and a neural network system, design of a self-adaptive dynamic surface controller and the like. By means of an introduced error transformation function, control accuracy can be specified at will, so that accurate control over the cutting depth of a cutter is realized; under the condition that a system model is not completely known, approach to unknown terms is realized through an RBF neural network; estimation of the norm of an unknown parameter vector is used for replacing estimation of an unknown parameter ground vector, so that the computation burden of the system is greatly relieved; by the adoption of the strategy that the self-adaptive dynamic surface technology is combined with the error transformation function and an RBF, the hypothesis of time lag is relaxed, it is guaranteed that tracking errors and the transient process can be within any specified index at the same time, the problem of 'differential explosion' of the inverse method is eliminated, semi-global uniform ultimate boundedness of system signals is guaranteed, and the robust self-adaptive dynamic surface control method has the advantages of being scientific and reasonable, high in control accuracy, applicable and the like.