In recent years, with the increasing abundance of high-quality data, continuous development of machine learning techniques and significant improvements of computational capabilities, data-driven inventory management is experiencing unprecedented development opportunities. However, comprehensive and systematic reviews of research advances in this emerging field are currently lacking. In this study, an in-depth analysis of 183 academic papers is conducted using bibliometrics, and the state of the art in this field is visualized through scientific knowledge graphs. Then, the research results of data-driven inventory management from the perspectives of big data and operation management are summarized and synthesized in three aspects: demand information, basic models and basic methods. Essentially, this paper introduces four inventory management models from the perspectives of demand uncertainty and feature data: univariate data-driven newsvendor model, univariate data-driven dynamic inventory model, multi-feature data-driven newsvendor model and multi-feature data-driven dynamic inventory model. On this basis, six main data-driven decision-making methods are summarized: Bayesian analysis, robust optimization, sample average approximation, quantile regression, operation statistics and machine learning. Finally, future research directions and suggestions are discussed from the perspectives of methodologies, tools, challenges, and application hotspots in data-driven inventory management, aiming to provide valuable references and insights for researchers and practitioners in the relevant fields, and to foster the continuous development of data-driven inventory management.

The Industrial Internet of Things (IIoT), as a new industrial ecosystem integrating advanced information technologies with manufacturing, holds significant importance for enhancing operational efficiency and promoting high-quality development in the manufacturing sector. A comprehensive analysis of literature related to operational management in the IIoT context reveals several key findings. 1) Research on IIoT platforms often employs qualitative methods to analyze their application scenarios and ecosystems across various industries. However, it is essential to focus on quantitative methods to explore operational and coordination mechanisms in depth. 2) Existing studies on value creation suggest enhancing product quality, reducing costs, and optimizing business processes through digitalization, networking, and intelligence. Thereby, it highlights the importance of understanding value co-creation mechanisms and patterns among multiple stakeholders, including manufacturing enterprises and customers. 3) Current research primarily concentrates on optimizing individual activities in production operations using IIoT technologies, mathematical models and algorithms. Nevertheless, there exists a critical need to investigate methods for constructing integrated collaborative processes with the cycle of “research, manufacturing and maintenance” within the IIoT environment, along with exploring multi-level closed-loop decision-making systems and intelligent decision-making methods. 4) It is demonstrated that supply chain management in IIoT can improve operational performance through interconnection, visibility, real-time capabilities, and traceability, while the impact of technology adoption on strategy selection and coordination mechanisms is also explored. Future attention may shift towards downstream clients in supply chain management.

Machine learning technology is continuously evolving and is extensively applied across various domains, demonstrating capabilities beyond human abilities. However, improper use of machine learning methods or biased decision-making can harm human interests, especially in sensitive areas with high-security demand such as finance and healthcare, etc., leading to an increasing attention on the trustworthiness of machine learning. Currently, machine learning technology commonly exhibits several drawbacks, such as biases against underrepresented groups, lack of user privacy protection, lack of model interpretability, and vulnerability to threats and attacks. These shortcomings undermine human trust in machine learning methods. Although researchers have conducted targeted studies on these issues, there is a lack of a comprehensive framework and methodology to systematically provide trustworthy analysis of machine learning. Therefore, this paper reviews the current mainstream definitions, indicators, methods, and evaluations of fairness, interpretability, robustness, and privacy in machine learning. Then, the relationships among these elements are discussed, while a trustworthy machine learning framework is established by integrating an entire lifecycle of machine learning. Finally, we present some of the current issues and challenges awaiting resolution in the field of trustworthy machine learning.

The exploration on surface defect detection based on deep intelligent vision plays an increasingly important role in the manufacturing industry. The importance of surface defect detection based on deep intelligent vision in modern industrial quality inspection is explained and the existing research progress is summarized in this paper. Deep intelligent vision provides high-precision and high-efficiency surface defect detection algorithms for different industrial scenarios based on the technologies of machine vision and deep learning. Surface defect detection can be divided into three categories: surface defect classification, localization, and segmentation from the perspective of detection fineness. The classification, localization, and segmentation methods are systematically reviewed, respectively, to sort out the problematic points and lines of the existing surface defect detection methods. Surface defect classification focuses on the problem of data and defective graphical features, which shows decentralized development due to its basic and easily expandable nature for application in different industrial scenarios. Surface defect localization takes the model framework, rectangular box detection mechanism, and annotation cost as the main problems, showing a research trend of pursuing lightweight and feature fusion mechanisms. Surface defect segmentation pays more attention to detailed features of an image. A multi-task framework for classification, localization, and segmentation, is studied to explore the complementarity between classification and segmentation detection. Finally, the current issues of existing surface defect detection studies are concluded and an outlook on the development trend is given.

To deeply explore the impact and empowerment of artificial intelligence (AI) large models on the innovative development of industrial engineering, this paper first briefly introduces the historical integration of industrial engineering and AI, analyzing the challenges and opportunities faced by industrial engineering in addressing complex problems in manufacturing and service systems in the era of AI large models. Then, the current applications of AI large models in industrial engineering are introduced, including their innovative applications in manufacturing, supply chain management, and service industries. The future trends in the implementation of AI large models in the industrial engineering are also discussed. Finally, the paper proposes several suggestions for talent training in industrial engineering empowered by AI, emphasizing the importance of innovative thinking and practical skills.

Focusing on low-altitude logistics and delivery scenarios using unmanned aerial vehicles (UAVs), this paper analyzes key technologies and research hotspots in the field through a keyword co-occurrence network map. According to the core components of UAV logistics systems, the study systematically reviews the domestic and international research issues such as motion and environment perception, flight control, route planning, UAV-truck cooperative optimization, profit allocation in cooperative operations, transportation safety and privacy security, and sustainable development of industry. Furthermore, the evolution process and application prospects of related control technologies and optimization methods are interpreted in detail, while the future research interests are concluded. The motivation of this review is to shed light on the trends in low-altitude UAV logistics and provide some insight for researchers.

As an innovative product integrating multidisciplinary technologies, low-altitude aircraft have rapidly expanded in application scale over the past few years and demonstrate foreseeable potential for further growth. However, low-altitude aircraft are highly likely to become a new source of environmental noise pollution, potentially causing increasing noise-related complaints. To address this issue, this paper reviews the current state of domestic and international research from three aspects: regulations related to low-altitude aircraft noise emissions, noise measurement and analysis, and noise calculation. In the aspect of regulations, the paper introduces the noise emission limits stipulated by the European Union Aviation Safety Agency (EASA) and the United States Federal Aviation Administration (FAA), as well as Chinese governance objectives for low-altitude aircraft noise emissions. In the aspect of noise measurement and analysis, it highlights three standards for noise measurement of low-altitude aircraft both domestically and internationally, and discusses the measurement methods employed in outdoor and laboratory environments. In the aspect of noise calculation, the paper concentrates on model-based and noise propagation-based methods. Finally, the paper analyzes challenges in these aspects and suggests future directions for noise prevention and research in low-altitude aircraft, including broader regulations, standardized measurement guidelines, and enhanced verification, to advance the development of noise control technologies.