Search

Control parameters of classical control system are expected to be online tuned and optimized by intelligent methods, in order to improve performance and help engineers reduce a lot of repetitive work in dangerous and harmful working environments. Main ideas and works of this paper are as follows:Firstly, change ratio based expert PID control method (EA-PID) is proposed to expand range of control parameters. Expert rule table (ERT) of expert PID control method (E-PID) is replaced by change ratio table (CRT) of EA-PID. Adjusted parameters of EA-PID are the results of multiplying change ratios in current adjusting cycle and control parameters in previous adjusting cycle. Secondly, NARX prediction-based NARX-E-PID and NARX-EA-PID are proposed. The NARX neural network is designed as a time series predictor to predict the output of the control system, then control parameters are adjusted according to the predicted output. Thirdly, comparative simulations of all the above methods are implemented to verify the improved effects. Finally, theoretical analysis is provided to ensure the stability of control systems. Effect are as follows: Firstly, comparative simulations verify that the improved methods have faster control speed, smaller steady-state error, less overshoot, and better ability of anti-interference. Secondly, theoretical analysis shows that the unstable control systems with adjusted parameters can be changed into a stable system by stability judgment in each adjusting cycle.

Network security has become a growing concern within the popularity and development of the Internet. Malicious code is one of the main threats to network security. Different types of malicious code have different functions and cause different harms. Therefore, improving the detection efficiency and recognition accuracy of malicious code is becoming an urgent problem to be solved. While traditional machine learning methods for malicious code detection largely depend on hand-designed features with experts’ knowledge of the domain or focus on the images which come from malicious code binary files. These methods spend too much time on feature extraction. With the emergence of a large amount of malicious code data, the efficiency of traditional machine learning algorithms is getting worse and worse. In this paper, a workflow based on deep learning is proposed to detect and classify malicious codes. This workflow adopts a convolutional neural network (CNN) and the regularization algorithms to classify malicious code with N_gram semantic feature as input of the model. The convolutional neural network can automatically extract the features of malicious code while avoiding the need for manual feature selection. Regularization algorithms not only speed up the training process of the deep model but also improve the generalization ability in the case of effective prevention of over-fitting of the model. The proposed method is compared with the state-of-the-art methods and other deep learning models. Experimental results show that our workflow can improve the accuracy and efficiency of malicious code classification.