The traditional malicious uniform resource locator (URL) detection method excessively relies on the matching rules formulated by the network security personnel, which is hard to fully express the text information of the URL. Thus, an improved multilayer recurrent convolutional neural network model based on the YOLO algorithm is proposed to detect malicious URL in this paper. First, single characters are mapped to dense vectors using word embedding, and the dense vectors are participated in the training process of the whole model according to the structural characteristics of the URL in the method. Then, the CSPDarknet neural network model based on the improved YOLO algorithm is proposed to extract features of the URL. Finally, the extracted features are used to evaluate malicious URL by the bidirectional LSTM recurrent neural network algorithm. In order to verify the validity of the algorithm, a total of 200,000 URLs are collected, including 100,000 normal URLs labeled “good” and 100,000 malicious URLs labeled “bad”. The experimental results show that the method detects malicious URLs more quickly and effectively and has high accuracy, high recall rate, and high accuracy compared with Text-RCNN, BRNN, and other models.

High energy consumption is an important issue affecting the operation and development of wastewater treatment plants (WWTPs). This paper seeks energy-saving opportunities from three aspects: energy application, process optimization, and performance evaluation. Moreover, effective energy-saving can be achieved from the perspective of energy supply and recovery by using green energy technologies, including wastewater and sludge energy recovery technologies. System optimization and control is used to reduce unnecessary energy consumption in operation. Reasonable indexes and methods can help researchers evaluate the application value of energy-saving technology. Some demonstration WWTPs even can achieve energy self-sufficiency by using these energy conservation technologies. Besides, this paper introduces the challenges faced by the wastewater treatment industry and some emerging energy-saving technologies. The work can give engineers some suggestions about reducing energy consumption from comprehensive perspectives.

After fault occurs, the fault diagnosis of wind turbine system is required accurately and quickly. This paper presents a fault diagnostic method for open-circuit faults in the converter of permanent magnet synchronous generator drive for the wind turbine. To avoid misjudgement or missed judgement caused by improper thresholds, the proposed method applies Local Mean Decomposition and Multiscale Entropy into the converter of wind power system fault diagnosis for the first time. This paper uses a novel multiclass support vector machine to classify the faults hardly diagnosed by other methods. Simulation results show that the method has the characteristics of high adaptability, high accuracy, and less diagnosis time.