A contact state recognition method for robot assembly based on GWA-SVM comprises the following steps: 1, using an industrial robot to assemble parts, and collecting force data in the assembly process;2, setting initial parameters; 3, standardizing the data set; 4, initializing a population of SVM parameters by using a chaotic logic mapping strategy; 5, optimizing the population of SVM parametersby using an improved reverse learning strategy; 6, updating the population by using a GWA operator; 7, calculating the fitness of population individuals, and updating the optimal individual; 8, if thecurrent iteration reaches the maximum allowable iteration frequency, executing the step 9, otherwise, t=t+1 and returning to the step 6; 9, ending the SVM parameter optimization process, substitutingthe optimal SVM parameters C and gamma and the training data set into the SVM, and establishing a GWA-SVM based contact state identification model; and 10, identifying the test data set by using thecontact state model, and drawing a classification result graph. The method is high in classification precision.