The imbalance between normal and attack samples in the industrial control systems (ICSs) network environment leads to the low recognition rate of the intrusion detection model for a few abnormal samples when classifying. Since traditional machine learning methods can no longer meet the needs of increasingly complex networks, many researchers use deep learning to replace traditional machine learning methods. However, when a large amount of unbalanced data is used for training, the detection performance of deep learning decreases significantly. This paper proposes an intrusion detection method for industrial control systems based on a 1D CWGAN. The 1D CWGAN is a network attack sample generation method that combines 1D CNN and WGAN. Firstly, the problem of low ICS intrusion detection accuracy caused by a few types of attack samples is analyzed. This method balances the number of various attack samples in the data set from the aspect of data enhancement to improve detection accuracy. According to the temporal characteristics of network traffic, the algorithm uses 1D convolution and 1D transposed convolution to construct the modeling framework of network traffic data of two competing networks and uses gradient penalty instead of weight cutting in the Wasserstein Generative Adversarial Network (WGAN) to generate virtual samples similar to real samples. After a large number of data sets are used for verification, the experimental results show that the method improves the classification performance of the CNN and BiSRU. For the CNN, after data balancing, the accuracy rate is increased by 0.75%, and the accuracy, recall rate and F1 are improved. Compared with the BiSRU without data processing, the accuracy of the s1D CWGAN-BiSRU is increased by 1.34%, and the accuracy, recall and F1 are increased by 7.2%, 3.46% and 5.29%.

In accordance with the actual production circumstances of enterprises, a scheduling problem model is designed for open-shop environments, considering AGV transport time. A Q-learning-based method is proposed for the resolution of such problems. Based on the characteristics of the problem, a hybrid encoding approach combining process encoding and AGV encoding is applied. Three pairs of actions are constituted to form the action space. Decay factors and a greedy strategy are utilized to perturb the decision-making of the intelligent agent, preventing it from falling into local optima while simultaneously facilitating extensive exploration of the solution space. Finally, the proposed method proved to be effective in solving the open-shop scheduling problem considering AGV transport time through multiple comparative experiments.

As energy plays a fundamental role in our modern life and most of a building’s energy is used for air conditioning, understanding the sustainable regulation theory of central air conditioning remains a significant scientific issue. In view of three shortcomings of existing energy-saving regulation methods of central air conditioning: (1) few studies on low-latency, high-reliability, and safer energy-saving control operation modes, (2) lack of consideration for human comfort, and (3) insufficient analysis of the comprehensive impact of the human–machine–environment, this paper proposes an energy-saving control framework of central air conditioning based on cloud–edge–device architecture. The framework establishes a prediction model of human comfort based on recurrent neural network. An intelligent energy-saving control strategy is proposed to ensure indoor personnel’s thermal comfort, considering the human–machine–environment factors. This study provides a basis for better understanding the sustainable control theory of building central air conditioning. Finally, the experiment proves that the proposed method can effectively reduce the energy consumption of central air conditioning. Compared with traditional regulation approaches, the proposed real-time control strategy can save up to 91% of energy consumption, depending on the environment, and advance control strategies can save an average of 4%.

Imbalanced data cause low recognition of wind turbine blade cracking. Existing data-level augmentation methods, including sampling and generative strategies, may yield lots of high-confidence but low-value samples, which fail to improve the detection of blade cracking. Therefore, this paper designs a novel RTAE (roundtrip auto-encoder) method. Based on the idea of the roundtrip approach, we design two generator networks and two discriminator networks to ensure the cycle mapping between cracking samples and latent variables. Further, by leveraging cycle consistency loss, generated samples fit the distribution of historical cracking samples well. Thus, these generated samples effectively realize data augmentation and improve recognition of blade cracking. Additionally, we apply an auto-encoder method to reduce the dimension of historical samples and thus the complexity of the generator network and discriminator network. Through the analysis of real wind turbine blade cracking data, the recognition of cracking samples is improved by 19.8%, 23.8% and 22.7% for precision, recall and F1-score.