Akhil Gupta Chigullapally, Sharvan Vittala, Razin Farhan Hussian
et al.
The fast pace of modern AI is rapidly transforming traditional industrial systems into vast, intelligent and potentially unmanned autonomous operational environments driven by AI-based solutions. These solutions leverage various forms of machine learning, reinforcement learning, and generative AI. The introduction of such smart capabilities has pushed the envelope in multiple industrial domains, enabling predictive maintenance, optimized performance, and streamlined workflows. These solutions are often deployed across the Industrial Internet of Things (IIoT) and supported by the Edge-Fog-Cloud computing continuum to enable urgent (i.e., real-time or near real-time) decision-making. Despite the current trend of aggressively adopting these smart industrial solutions to increase profit, quality, and efficiency, large-scale integration and deployment also bring serious hazards that if ignored can undermine the benefits of smart industries. These hazards include unforeseen interoperability side-effects and heightened vulnerability to cyber threats, particularly in environments operating with a plethora of heterogeneous IIoT systems. The goal of this study is to shed light on the potential consequences of industrial smartness, with a particular focus on security implications, including vulnerabilities, side effects, and cyber threats. We distinguish software-level downsides stemming from both traditional AI solutions and generative AI from those originating in the infrastructure layer, namely IIoT and the Edge-Cloud continuum. At each level, we investigate potential vulnerabilities, cyber threats, and unintended side effects. As industries continue to become smarter, understanding and addressing these downsides will be crucial to ensure secure and sustainable development of smart industrial systems.
María Fernanda Trujillo-Guerrero, William Venegas-Toro, Danni De la Cruz-Guevara
et al.
The ergonomic risks associated with posture in conventional office workstations have been extensively studied, but there is limited research available on these risks in the context of home-based work environments. Most available studies rely solely on questionnaire-based statistical analyses, leaving a gap in understanding the specific conditions of home-based work environments. This study focuses on evaluating the effects of workstation conditions on posture and muscular efforts across three anatomical segments: head-neck, trunk-upper trapezius, and arm-deltoid. The analysis is conducted by simulating workstation setups commonly associated with academic activities performed by students during the COVID-19 pandemic. The conditions examined in this study include inadequate desk height, the use of chairs without armrests, and the use of laptops. Eighteen volunteers, comprising nine women and nine men, participated in experiments conducted under scenarios designed using a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mn>2</mn><mi>k</mi></msup></semantics></math></inline-formula> statistical approach. In all experiments, participants completed questionnaires, and text-writing activities were performed to evaluate the effects of these conditions. This research introduces a new non-invasive technique for ergonomic assessment that integrates photogrammetry and surface electromyography (sEMG) to simultaneously evaluate posture and muscular effort. The developed methodology allows precise, contactless analysis of ergonomic conditions and can be adapted for various professional and academic teleworking environments. Significant effects were observed in the posture (°) of the trunk and head, with both small and large effects identified at significance levels of <i>p</i> < 0.001 under the furniture conditions studied. In terms of EMG activity, moderate effects were observed at <i>p</i> < 0.01 levels between table height and upper trapezius activation, while small effects were detected at <i>p</i> < 0.05 levels between the use of chairs without armrests and neck. Similarly, small to moderate effects were observed in the arm-deltoid segment under the same furniture conditions. These findings reveal information about the posture and muscular effort patterns associated with the studied tasks, offering knowledge that can be referenced for similar tasks in other technical fields where telematics activities are performed.
Industrial safety. Industrial accident prevention, Medicine (General)
Rock fragmentation in hard rock mining has traditionally relied on explosives which raises significant environmental and safety concerns for both workers and local communities. In response, soundless chemical demolition agents (SCDAs) primarily composed of lime (CaO), offer safer and more sustainable alternative to traditional blasting due to their soundless, vibrationless, and fumeless properties. This study is focused on examining the effect of mixing water temperature on the rock breakage performance of two commercially available SCDA brands, namely Betonamit type R (BT-R) and Dexpan type 3 (DXP-3). The experiments were conducted using 15 cm cubic granite rock specimens as the host material under various ambient temperatures. The study revealed an increase in mixing water temperature significantly accelerates the mechanical performance of SCDAs, particularly in cold ambient conditions. For instance, increasing the mixing water temperature from 20°C to 40°C reduced the time to first crack (TFC) by 36 % for BT-R and 74 % for DXP-3 under an ambient temperature of 0°C. A corresponding reduction in minimum demolition time (MDT) was also observed. At higher ambient temperatures, the impact of mixing water temperature was found to be less pronounced for both SCDA types. It is concluded that high mixing water temperature would be highly recommended for cold climate applications in both open pit and underground mining.
Quantitative study of the temporal and spatial evolution of seismic wave characteristic parameters is of great significance for accurately identifying the P-wave and S-wave in seismic waves and improving the accuracy in localizing microseismic events. Based on the field-measured seismic wave data of the Wudong coal mine, this paper studies the temporal and spatial evolution law of seismic wave amplitude and frequency. The time-window sliding algorithm is proposed to process the amplitude and frequency content of the seismic wave. The obtained instantaneous change rates of amplitude and frequency can accurately characterize the arrival times of P-wave and S-wave, and assist in automatically pinpointing the corresponding seismic waves. The amplitude of the seismic wave recorded by seismic sensors located at different spatial locations from the source reveals that the attenuation decreases gradually with the increase of the propagation distance and that the attenuation rate gradually slows down. It is noted that there are some discrepancies in the amplitude and frequency of the seismic waves recorded by different seismic sensors yet with the same distance from the source. Based on the P-wave and S-wave component diagrams of the seismic displacement field of coal and rock rupture, combined with the laws and differences of the amplitude and frequency of the seismic wave signals at different spatial locations, a new method is proposed to roughly determine the rupture source direction. This study provides a new perspective that can be instrumental for a more comprehensive study of the rupture source direction generated by on-site microseismic events.
The foundation model industry exhibits unprecedented concentration in critical inputs: semiconductors, energy infrastructure, elite talent, capital, and training data. Despite extensive sectoral analyses, no comprehensive framework exists for assessing overall industrial vulnerability. We develop the Artificial Intelligence Industrial Vulnerability Index (AIIVI) grounded in O-Ring production theory, recognizing that foundation model production requires simultaneous availability of non-substitutable inputs. Given extreme data opacity and rapid technological evolution, we implement a validated human-in-the-loop methodology using large language models to systematically extract indicators from dispersed grey literature, with complete human verification of all outputs. Applied to six state-of-the-art foundation model developers, AIIVI equals 0.82, indicating extreme vulnerability driven by compute infrastructure (0.85) and energy systems (0.90). While industrial policy currently emphasizes semiconductor capacity, energy infrastructure represents the emerging binding constraint. This methodology proves applicable to other fast-evolving, opaque industries where traditional data sources are inadequate.
Foundation models have revolutionized AI, yet they struggle with zero-shot deployment in real-world industrial settings due to a lack of high-quality, domain-specific datasets. To bridge this gap, Superb AI introduces ZERO, an industry-ready vision foundation model that leverages multi-modal prompting (textual and visual) for generalization without retraining. Trained on a compact yet representative 0.9 million annotated samples from a proprietary billion-scale industrial dataset, ZERO demonstrates competitive performance on academic benchmarks like LVIS-Val and significantly outperforms existing models across 37 diverse industrial datasets. Furthermore, ZERO achieved 2nd place in the CVPR 2025 Object Instance Detection Challenge and 4th place in the Foundational Few-shot Object Detection Challenge, highlighting its practical deployability and generalizability with minimal adaptation and limited data. To the best of our knowledge, ZERO is the first vision foundation model explicitly built for domain-specific, zero-shot industrial applications.
Industrial diagrams such as piping and instrumentation diagrams (P&IDs) are essential for the design, operation, and maintenance of industrial plants. Converting these diagrams into digital form is an important step toward building digital twins and enabling intelligent industrial automation. A central challenge in this digitalization process is accurate object detection. Although recent advances have significantly improved object detection algorithms, there remains a lack of methods to automatically evaluate the quality of their outputs. This paper addresses this gap by introducing a framework that employs Visual Language Models (VLMs) to assess object detection results and guide their refinement. The approach exploits the multimodal capabilities of VLMs to identify missing or inconsistent detections, thereby enabling automated quality assessment and improving overall detection performance on complex industrial diagrams.
Ola D. Al-Maseimi, Nour A. Elsahoryi, Omar A. Alhaj
et al.
Food safety is paramount, especially for vulnerable groups like pregnant and postpartum women. In this cross-sectional study, Jordanian women in different maternal states—pregnant, postpartum, and non-pregnant—were examined for their knowledge and habits regarding food safety. An online survey with 350 respondents yielded information on the participants’ opinions about food safety, personal hygiene, food storage, shopping habits, knowledge of cross-contamination, and handling of baby formula. According to the findings, many participants exhibited poor knowledge (53.7–65.2%) and practices (39.4–50%) related to food safety, with no significant differences in whether or not they were pregnant. Sociodemographic characteristics, including age and information sources, impacted postpartum women’s knowledge and practices about food safety. These findings highlight the importance of food safety education and awareness programs, particularly for pregnant and postpartum women, to lower the risk of foodborne infections during this critical period.
Industrial safety. Industrial accident prevention, Medicine (General)
Chieh-Wen Chang, Tomohisa Nagata, Louise E. Anthony
et al.
The construction industry has been identified as a major contributor to occupational accidents that can lead to fatalities. As a result, this study aims to evaluate the effectiveness of new safety and health regulations and revised guidelines in improving safety and health disclosures and performance within the construction industry. We retrieved safety and health disclosure reports from 25 Taiwanese construction companies between 2013 and 2020 using the Market Observation Post System website. We analyzed the data using the Kaplan–Meier method to assess the timing of disclosures and differences between larger (≥300 employees) and smaller (<300 employees) companies. We found that construction companies reported safety indicators more promptly than health indicators and that larger companies disclosed earlier compared to smaller ones. Only 45% of companies provide detailed reviews and preventative measures in their sustainability reports despite 64% disclosing occupational accidents. We found that from 2013 to 2020, more companies improved their occupational safety and health (OSH) reporting. This improvement coincided significantly with the adoption of international standards and Taiwan’s government regulations. In summary, the study found that larger companies were more likely to disclose OSH data compared to smaller ones. This suggests that company size and available resources could have an impact on reporting practices. While some progress was made, companies still struggle to provide detailed reports on major accidents, balancing transparency with competitiveness.
Industrial safety. Industrial accident prevention, Medicine (General)
Valentina Zaccaria, Chiara Masiero, David Dandolo
et al.
While Machine Learning has become crucial for Industry 4.0, its opaque nature hinders trust and impedes the transformation of valuable insights into actionable decision, a challenge exacerbated in the evolving Industry 5.0 with its human-centric focus. This paper addresses this need by testing the applicability of AcME-AD in industrial settings. This recently developed framework facilitates fast and user-friendly explanations for anomaly detection. AcME-AD is model-agnostic, offering flexibility, and prioritizes real-time efficiency. Thus, it seems suitable for seamless integration with industrial Decision Support Systems. We present the first industrial application of AcME-AD, showcasing its effectiveness through experiments. These tests demonstrate AcME-AD's potential as a valuable tool for explainable AD and feature-based root cause analysis within industrial environments, paving the way for trustworthy and actionable insights in the age of Industry 5.0.
Nowadays, electric robots play big role in many fields as they can replace humans and/or decrease the amount of load on humans. There are several types of robots that are present in the daily life, some of them are fully controlled by humans while others are programmed to be self-controlled. In addition there are self-control robots with partial human control. Robots can be classified into three major kinds: industry robots, autonomous robots and mobile robots. Industry robots are used in industries and factories to perform mankind tasks in the easier and faster way which will help in developing products. Typically industrial robots perform difficult and dangerous tasks, as they lift heavy objects, handle chemicals, paint and assembly work and so on. They are working all the time hour after hour, day by day with the same precision and they do not get tired which means that they do not make errors due to fatigue. Indeed, they are ideally suited to complete repetitive tasks.
Nabylla Sharfina Sekar Nurriwanti, Y. Denny A. Wahyudiono, Indriati Paskarini
et al.
Introduction: The steel box girder of Suramadu Bridge is a confined work area with sensor maintenance activities and potential hazards. The purpose of this study was to determine the potential hazards and risk levels in the Suramadu Bridge steel box girder work area. Methods: This descriptive study involved cross-sectional data collection. This study used a qualitative risk assessment method. The primary data used in this research included interviews with informants, which consisted of five key informants from experts and five main informants from technicians. The secondary data of the study include a job safety analysis document issued by the Suramadu Bridge Structural Health Monitoring System (SHMS). Risk assessment was performed by determining the level of likelihood and consequences using a risk analysis matrix. Data processing techniques and analysis are based on job safety analysis documents and interviews, whereas the risk analysis table is based on AS/NZS 4360 (2004). Results: The study results show that sensor maintenance work in the steel box girder area involves eight activities, 15 potential hazards, and 19 risks. Conclusion: The study concludes that, Out of the 19 identified risks, three risks (16%) were in the low-risk category, 15 risks (79%) were in the medium-risk category, and one risk (5 %) was in the high-risk category with the potential for fire.
Patrick Jonk, Vincent de Vries, Rombout Wever
et al.
Occurrence reporting is a commonly used method in safety management systems to obtain insight in the prevalence of hazards and accident scenarios. In support of safety data analysis, reports are often categorized according to a taxonomy. However, the processing of the reports can require significant effort from safety analysts and a common problem is interrater variability in labeling processes. Also, in some cases, reports are not processed according to a taxonomy, or the taxonomy does not fully cover the contents of the documents. This paper explores various Natural Language Processing (NLP) methods to support the analysis of aviation safety occurrence reports. In particular, the problems studied are the automatic labeling of reports using a classification model, extracting the latent topics in a collection of texts using a topic model and the automatic generation of probable cause texts. Experimental results showed that (i) under the right conditions the labeling of occurrence reports can be effectively automated with a transformer-based classifier, (ii) topic modeling can be useful for finding the topics present in a collection of reports, and (iii) using a summarization model can be a promising direction for generating probable cause texts.
This paper investigates the inter-regional intra-industry disparity within selected Indian manufacturing industries and industrial states. The study uses three measures - the Output-Capital Ratio, the Capital-Labor Ratio, and the Output-Labor Ratio - to critically evaluate the level of disparity in average efficiency of labor and capital, as well as capital intensity. Additionally, the paper compares the rate of disparity of per capita income between six major industrial states. The study finds that underutilization of capacity is driven by an unequal distribution of high-skilled labor supply and upgraded technologies. To address these disparities, the paper suggests that policymakers campaign for labor training and technology promotion schemes throughout all regions of India. By doing so, the study argues, the country can reduce regional inequality and improve economic outcomes for all.
The Internet of Things (IoT) will bring about the next industrial revolution in Industry 4.0. The communication aspect of IoT devices is one of the most critical factors in choosing the suitable device for the suitable usage. So far, the IoT physical layer communication challenges have been met with various communications protocols that provide varying strengths and weaknesses. Moreover, most of them are wireless protocols due to the sheer number of device requirements for IoT. This paper summarizes the network architectures of some of the most popular IoT wireless communications protocols. It also presents a comparative analysis of critical features, including power consumption, coverage, data rate, security, cost, and Quality of Service (QoS). This comparative study shows that Low Power Wide Area Network (LPWAN) based IoT protocols (LoRa, Sigfox, NB-IoT, LTE-M ) are more suitable for future industrial applications because of their energy efficiency, high coverage, and cost efficiency. In addition, the study also presents an industrial Internet of Things (IIoT) application perspective on the suitability of LPWAN protocols in a particular scenario and addresses some open issues that need to be researched. Thus, this study can assist in deciding the most suitable protocol for an industrial and production field.
The recent rapid development of deep learning has laid a milestone in industrial Image Anomaly Detection (IAD). In this paper, we provide a comprehensive review of deep learning-based image anomaly detection techniques, from the perspectives of neural network architectures, levels of supervision, loss functions, metrics and datasets. In addition, we extract the new setting from industrial manufacturing and review the current IAD approaches under our proposed our new setting. Moreover, we highlight several opening challenges for image anomaly detection. The merits and downsides of representative network architectures under varying supervision are discussed. Finally, we summarize the research findings and point out future research directions. More resources are available at https://github.com/M-3LAB/awesome-industrial-anomaly-detection.
2D-based Industrial Anomaly Detection has been widely discussed, however, multimodal industrial anomaly detection based on 3D point clouds and RGB images still has many untouched fields. Existing multimodal industrial anomaly detection methods directly concatenate the multimodal features, which leads to a strong disturbance between features and harms the detection performance. In this paper, we propose Multi-3D-Memory (M3DM), a novel multimodal anomaly detection method with hybrid fusion scheme: firstly, we design an unsupervised feature fusion with patch-wise contrastive learning to encourage the interaction of different modal features; secondly, we use a decision layer fusion with multiple memory banks to avoid loss of information and additional novelty classifiers to make the final decision. We further propose a point feature alignment operation to better align the point cloud and RGB features. Extensive experiments show that our multimodal industrial anomaly detection model outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTec-3D AD dataset. Code is available at https://github.com/nomewang/M3DM.
Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice. XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We utilize XSafety to empirically study the multilingual safety for 4 widely-used LLMs, including both close-API and open-source models. Experimental results show that all LLMs produce significantly more unsafe responses for non-English queries than English ones, indicating the necessity of developing safety alignment for non-English languages. In addition, we propose several simple and effective prompting methods to improve the multilingual safety of ChatGPT by evoking safety knowledge and improving cross-lingual generalization of safety alignment. Our prompting method can significantly reduce the ratio of unsafe responses from 19.1% to 9.7% for non-English queries. We release our data at https://github.com/Jarviswang94/Multilingual_safety_benchmark.