In recent years, intelligent fault diagnosis technology with deep learning algorithms has been widely used in industry, and they have achieved gratifying results. Most of these methods require large amount of training data. However, in actual industrial systems, it is difficult to obtain enough and balanced sample data, which pose challenges in fault identification and classification. In order to solve the problems, this paper proposes a data generation strategy based on Wasserstein generative adversarial network and convolutional neural network (WG-CNN), which uses generator and discriminator to conduct confrontation training, expands a small sample set into a high-quality dataset, and uses one-dimensional convolutional neural network (1D-CNN) to learn sample characteristics and classify different fault types. Experimental results over the standard Case Western Reserve University (CWRU) bearing fault diagnosis benchmark dataset showed that the proposed method has obvious and satisfactory fault diagnosis effect with 100% classification accuracy for few-shot learning. In different noise environments, this method also has excellent performance.

Real-time smoke detection is of great significance for early warning of fire, which can avoid the serious loss caused by fire. Detecting smoke in actual scenes is still a challenging task due to large variance of smoke color, texture, and shapes. Moreover, the smoke detection in the actual scene is faced with the difficulties in data collection and insufficient smoke datasets, and the smoke morphology is susceptible to environmental influences. To improve the performance of smoke detection and solve the problem of too few datasets in real scenes, this paper proposes a model that combines a deep convolutional generative adversarial network and a convolutional neural network (DCG-CNN) to extract smoke features and detection. The vibe algorithm was used to collect smoke and nonsmoke images in the dynamic scene and deep convolutional generative adversarial network (DCGAN) used these images to generate images that are as realistic as possible. Besides, we designed an improved convolutional neural network (CNN) model for extracting smoke features and smoke detection. The experimental results show that the method has a good detection performance on the smoke generated in the actual scenes and effectively reduces the false alarm rate.

Hex is a board game with simple rules and complex strategy. In the recent years, hex is becoming more and more popular. (Hex is a game with simple rules and complex strategies which is becoming more and more popular recent years.) Although we have used Min-max tree search ^[1] and Alpha-Beta pruning ^[2] during game , the program still has a difficulty to dealing with some situations well . In this paper, we will instruct(describe) a condition which is difficult to deal with existed in hex. By analyzing this situation we found a special and important area called 'connected-region' and we will apply it to the evaluation function. Our experiment found that we will make program get win easier by using this strategy.

Hex is going to be more and more popular because of its simple rules. The simple rules also bring enormous situation of Hex. It is hard for computer to assume the best situation after several rounds even simply use Alpha-beta pruning in a few minutes. In this page, we analysis the Hex and compare MTD(f) with using Alpha-beta pruning only. Our conclusion is that MTD(f) can make it much more effective. We also summarize a useful strategy-TCL (Two Choice Link). Using this strategy based on the topology, we can make a link to win succinctly and flexibly.