Jul 2026· Academic Journal of Management Science and Engineering· 0 citations· 10 references
Abstract
The integration of artificial intelligence into instrumentation and measurement systems has emerged as a transformative force across industrial, environmental, and scientific domains. This article provides a systematic overview of AI applications in instrumentation, encompassing intelligent sensor data processing, predictive maintenance, automated meter reading, and fault diagnosis. Drawing upon recent advances documented in the literature, we examine the methodological landscape ranging from conventional machine learning to deep learning and large language models. Key benefits include enhanced measurement accuracy through intelligent compensation, reduced downtime through predictive maintenance, and improved operational efficiency through automation. However, significant challenges persist, including the blackbox nature of AI models, data scarcity, uncertainty quantification, and the gap between laboratory performance and realworld deployment. We argue that the future of intelligent instrumentation lies in hybrid approaches that integrate datadriven AI with conventional modeldriven methods, thereby combining the pattern recognition capabilities of AI with the interpretability and rigor of physicsbased models.
The integration of artificial intelligence (AI) into instrumentation and measurement systems is reshaping industrial monitoring, control, and maintenance practices. This article provides a comprehensive overview of AI-empowered intelligent instrumentation, with a focus on three representative application paradigms: automatic meter reading, fault diagnosis for predictive maintenance, and sensor calibration with drift compensation. We review recent advances in deep learning-based object detection for analog and digital meters, highlighting frameworks such as improved YOLO and Fast R-CNN that achieve accuracy exceeding 98% while reducing measurement time by up to 85%. In the domain of prognostics and health management, we examine how convolutional neural networks with time-frequency transformations enable near-perfect fault classification in rotating machinery. Additionally, we discuss AI-driven calibration methods using neural networks and Gaussian process regression, which not only improve accuracy but also provide rigorous uncertainty quantification compatible with international measurement standards. Despite these successes, challenges remain regarding data scarcity, model interpretability, uncertainty quantification, and real-time edge deployment. We conclude by advocating hybrid approaches that combine data-driven AI with conventional model-driven techniques to achieve both high performance and trustworthiness. This review serves as a practical reference for researchers and engineers seeking to adopt AI solutions in instrumentation applications.
Fujie Lu· International Journal of Adv...· 0 citations
The integration of Artificial Intelligence (AI) has emerged as a crucial technology for making electrical systems intelligent and efficient.AI has been a pivotal technology in making electrical systems intelligent and efficient, enhancing automation, reliability, and decision-making. In this review, the integration of AI within the field of electrical engineering is explored, highlighting the role of machine learning techniques, deep learning models, and their applications in various areas such as smart grid, renewable energy prediction, fault detection, energy prediction, and predictive maintenance. It also covers benchmark datasets, evaluation platforms, and the performance of AI algorithms. In addition, the review identifies key challenges, such as Interpretability of the Models, Data Quality, Security of Data and Computational Complexity, and investigates new trends like Explainable AI, Digital Twins, Federated Learning and Edge AI for future electrical systems.
Fawad Khan· Global Trends in Science and...· 0 citations
The rapid evolution of intelligent systems has shifted the focus of electrical and computer engineering from isolated data processing toward integrated models of machine cognition. This editorial introduces a foundational perspective on machine intelligence systems, emphasizing the transformation from raw data to meaningful intelligence through learning systems, representation mechanisms, and computational perception. In contemporary AI-driven environments, intelligence is no longer defined solely by algorithmic performance, but by the ability to construct structured representations of the world and interpret complex multimodal signals. Learning systems, particularly those grounded in machine learning and deep learning paradigms, serve as the core mechanism enabling this transformation. Representation learning provides the bridge between unstructured data and abstract knowledge, while computational perception enables machines to interpret visual, auditory, and sensor-based information in real time. Together, these components form the foundational architecture of intelligent systems that underpin emerging applications in engineering, automation, and cyber-physical environments. This editorial sets the stage for understanding intelligence as an emergent computational construct, highlighting its role as the first phase in the broader cognitive intelligence systems continuum that progresses toward adaptive, autonomous, and socio-cognitive systems in future research directions.
Tole Sutikno· International Journal of Ele...· 0 citations
The integration of artificial intelligence into instrumentation and measurement systems promises transformative improvements in accuracy, efficiency, and operational intelligence. However, this technological convergence also introduces novel risks that challenge established practices in measurement science, legal metrology, and industrial safety. This article provides a balanced analysis of the potential benefits and risks associated with AI-driven instrumentation. We examine key benefits including enhanced measurement accuracy through intelligent compensation, predictive maintenance capabilities, self-diagnostics and adaptive calibration, and operational efficiency gains. Concurrently, we analyze critical risks: the “black box” problem and lack of interpretability, data quality dependence, cybersecurity vulnerabilities, workforce displacement and skills gaps, and regulatory and standardization challenges. We argue that realizing the full potential of AI in instrumentation requires a balanced approach that combines technological innovation with robust governance frameworks, human oversight, and rigorous uncertainty quantification. This analysis serves as a reference for researchers, practitioners, and policymakers navigating the complex landscape of AI-empowered instrumentation.
Fujie Lu· Academic Journal of Applied...· 0 citations
Manufacturing systems are undergoing a fundamental transformation driven by the convergence of cyber-physical infrastructure, ubiquitous sensing, and artificial intelligence. At the heart of this transformation lies the challenge of embedding physical knowledge into data-driven models to achieve both predictive accuracy and engineering interpretability. Physics-informed machine learning (PIML) has emerged as a paradigm for integrating conservation laws, constitutive equations, and domain constraints into neural architectures.
Despite significant advances in smart design and manufacturing, three persistent gaps remain. First, multimodal sensor fusion in manufacturing environments continues to struggle with heterogeneous data types and varying sampling rates, where data-driven approaches often fail to generalize across operating conditions. Second, intelligent fault diagnosis under data scarcity, label noise, and cross-domain shifts demands methods that can encode physical priors while maintaining sample efficiency. Third, dynamic production planning under disturbances requires optimization frameworks that respect physical constraints while adapting in real time.
This special issue brings together 10 contributions that address these challenges through novel PIML models. These works demonstrate how the systematic integration of physical knowledge can enhance model robustness, reduce data requirements, and improve generalization across manufacturing applications.
Jiewu Leng, Hui Yang, Min Xia et al.· Journal of Computing and Inf...· 0 citations
Artificial intelligence has altered the way computer science research is planned, carried out, and judged. What began in the early twentieth century as a body of formal theory about computation and reasoning matured, over several decades, into a practical discipline: early decision trees and rule-based systems prepared the ground for the statistical learning algorithms in use today (Taulli T). Machine learning, and within it deep learning, now anchors work in natural language processing, computer vision, and robotics, where multi-layered neural networks extract structure from data volumes no manual analysis could cover (Aslay F). Two consequences of this shift frame the present review. The first is methodological. Learning-based models let researchers process large datasets quickly and surface regularities that complexity previously hid from view; in areas ranging from medical diagnostics to autonomous systems, this has translated into measurable gains in accuracy and speed of discovery. The second consequence is organizational. Because AI methods travel well across domains, computer scientists increasingly work alongside specialists in health, finance, and environmental science. These collaborations do more than export algorithms; they feed domain requirements back into algorithm design, producing tools that answer to real problems such as climate modeling and public health surveillance. Integration of this kind is not free of cost. It brings technical hurdles — data quality, reproducibility, computational expense — and it raises ethical questions about bias, transparency, and accountability that the discipline is still learning to answer. Frameworks that establish ethical standards are needed both to preserve public trust and to comply with emerging regulation. The sections that follow trace the historical development of AI within computer science, review the principal technique families and their applications, and close with an original discussion of cross-cutting patterns, ethical obligations, and likely future directions.
Elayaraja Subbaiah, Manykandaprebou Vaitinadin, E. Kesavan· International Journal of Sci...· 0 citations