Transformer is one of the important components of the power system, capable of transmitting and distributing the electricity generated by renewable energy sources. Dissolved Gas Analysis (DGA) is one of the effective techniques to diagnose early faults in oil-immersed transformers. It correlates the concentration and ratio of dissolved gases with transformer faults. Researchers have proposed many methods for fault diagnosis, such as double ratio method, Rogers method, Duval triangle method, etc., but all of them have some problems. Based on the strong data mining capability and good robustness of AI techniques, many researchers introduced AI techniques to mine the features of DGA data. According to the characteristics and scale of DGA data, researchers select appropriate AI techniques or make appropriate improvements to AI techniques to improve diagnostic performance. This paper presents a systematic review of the literature on the application of artificial intelligence techniques for DGA-based diagnosis and for solving intractable problems in early transformer fault diagnosis, which include neural networks, clustering, support vector machines, etc. In addition to reviewing the applications of these intelligent techniques, the diagnostic thinking proposed in this literature, such as the introduction of temporal parameters for comprehensive analysis of DGA data and the extraction of optimal features for DGA data, is also reviewed. Finally, this paper summarizes and prospects the artificial intelligence techniques applied by researchers in transformer fault diagnosis.

In order to handle heavy chattering and negative robustness caused by time‐varying system parameters and external load disturbance of the speed control system, thereby having high‐precision control over surface permanent magnetic synchronous machine (PMSM), this paper combines the advantages of sliding mode variable structure control (SMVSC) and fuzzy control. Firstly, a fuzzy sliding mode variable structure control (FUZZY‐SMVSC) method is proposed, based on the vector control foundation framework of surface PMSM (SPMSM). It effectively reduces chattering while keeping sliding mode, according to the fuzzy rules formulated based on fuzzy control principle. Secondly, integral sliding mode surface is used and integration element is introduced into fuzzy control input, thereby reducing the static error of the conventional fuzzy control. Simulation and experimental results show that the proposed fuzzy sliding mode variable structure control reduces chattering by fuzzy reasoning and softening. Also, it still can maintain the strong robustness of sliding mode variable structure and ensures the fine dynamics of the system, against time‐varying system parameters and external load disturbance.

The precise matching of medication regimens to individual patients, known as personalized medication, is critical for the effective management of chronic diseases. Traditional machine learning‐based models for personalized medication regimens typically rely solely on either clinical macro‐phenotypes or molecular‐level drug characteristics. It remains challenging to capture the patient‐medication relationship from a comprehensive perspective that integrates individual patient characteristics with macro‐ and micro‐level properties of the medication. Determining patient‐medication relationships constitutes a three‐stage sequential decision process from a clinical decision‐making perspective. Therefore, inspired by Chain‐of‐Thought prompting, which simulates the decision‐making process of human experts, a Multimodal Data‐Driven Chain‐of‐Decisions (MDD‐CoD) framework is proposed, where three‐stage deep learning tasks are sequentially organized to reflect upstream–downstream logical dependencies, thereby forming a coherent clinical decision‐making process. The model incorporates multimodal clinical phenotype data, multi‐attribute medication data, and insights from clinical experts. Performance evaluation of the model involved comprehensive experiments utilizing five datasets covering four chronic diseases sourced from three hospitals. The dataset comprises information from chronic kidney disease (CKD), membranous nephropathy (MN), rheumatoid arthritis (RA), colorectal cancer (CRC), and knee osteoarthritis (KOA), totaling 3173 unimodal, 502 multimodal, and 2187 medication records from 3675 patients. Experimental results demonstrate that the framework achieves enhanced predictive performance in personalized medication decision‐making based on individual patient disease characteristics, surpassing the strongest baseline across all tasks. This framework serves as a foundational model for clinical mixed data, with improved generalization and interpretability in cross‐disease personalized decision‐making tasks. It offers a scalable solution for the implementation of personalized medication regimens for chronic diseases.

Chilled water system of central air conditioning is a typical hybrid system; variable frequency behavior with amplitude limited of pumps reflects continuous and discrete dynamic characteristics. The way of energy-saving is variable water volume, via variable frequency behavior of pumps to gain adjustment of power consumption. Facing the situation of the variable frequency pumps with parallel operation, single continuous or discrete modeling cannot reflect the hybrid features. Thus, the control method will have some questions, such as bad energy-saving effect, difficult accurate adjustment of cold capacity, and low running energy efficiency. However, hybrid system modeling can reflect hybrid dynamic behavior of pumps, which is combining continuous and discrete features. The questions of nonlinear and multiparameters can be solved by control method based on hybrid system. Here, an optimum control method is proposed with the principle of the minimum, by setting the minimum power consumption as the performance function in fixed time, which realizes variable control of pumps and accurate adjustment of temperature inside room. At last, it shows the system characteristics and energy-saving affection by hybrid system modeling and the optimum control method.