The firing zone images of rotary kilns contain rich flame information and accurate combustion state recognition are the premise of optimal control for the rotary kilns. The working conditions can be quickly recognized, and the automation level of the rotary kilns can be improved through the convolutional neural network-based methods, but there are problems with large network size and high computational resources required. Therefore, a working condition recognition method based on lightweight network and knowledge distillation was proposed in this paper. The teacher model and the student model were improved by introducing the collaborator differential layer after the convolutional layer of the network. The improved lightweight network MobilenetV2 was used as the backbone network of the student model while the improved Resnet50 was used as the backbone network of the teacher model. The rich classification label information contained in the teacher model was transferred to the student model by constructing the mixed distillation loss function and the student model obtained by distillation training was used as the working condition recognition model to improve the recognition accuracy of the high similar rotary kiln flame images. The experimental results show that the overall recognition accuracy of the improved student model is increased by 3. 33% compared with the original model, and the recognition accuracy of the three working conditions in the test set reaches 93%, 99%, 90% respectively. The accuracy and network size are better than those of other mainstream networks, and the requirements of real time and low cost in actual production process are met.