Sensors

Research

12 pages, 3177 KB

Open AccessArticle

High-Precision Centroid Measurement Method Based on 3D Scanning and Hooke’s Law

by Xin He, Zhen Li, Xin Pan and Yong Yang

Sensors 2025, 25(23), 7210; https://doi.org/10.3390/s25237210 - 26 Nov 2025

Viewed by 357

The accurate determination of an object’s centroid is a critical requirement in fields such as aerospace engineering and advanced manufacturing, where it is essential for quality control and system performance. Traditional methods, such as multi-point weighing, are often limited by restricted measurement ranges, [...] Read more.

The accurate determination of an object’s centroid is a critical requirement in fields such as aerospace engineering and advanced manufacturing, where it is essential for quality control and system performance. Traditional methods, such as multi-point weighing, are often limited by restricted measurement ranges, inaccuracies from mechanical alignment tolerances, and susceptibility to lateral force interference from uneven platforms, which collectively constrain measurement precision. To address these challenges, a novel measurement framework is proposed that synergizes high-precision 3D scanning with Hooke’s law-based mechanical sensing. This methodology eliminates dependencies on mechanical positioning and offers enhanced compatibility with various object geometries through its non-contact 3D scanning. The system also integrates linear spring-based force transduction for enhanced load adaptability and incorporates active anti-tilt compensation using 3D scanning and motor leveling. Experimental validation demonstrated sub-millimeter accuracy compared to the multi-point weighing method, with measured centroid deviations of 0.01 mm (X-axis), 0.06 mm (Y-axis), and 0.03 mm (Z-axis), achieving a composite spatial precision of 0.07 mm. This methodological innovation not only expands the operational envelope of centroid measurement systems but also provides new theoretical insights and a robust methodology for measuring complex parts and systems. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Figure 1

13 pages, 1996 KB

Open AccessArticle

Automatic Calibration and Update of a Digital Twin for Plug & Produce

by Mattias Bennulf, Sudha Ramasamy, Xiaoxiao Zhang, Fredrik Danielsson and Janardhanan Swathanandan

Sensors 2025, 25(22), 6885; https://doi.org/10.3390/s25226885 - 11 Nov 2025

Viewed by 453

Abstract

This article presents a system for automatically updating a digital twin model, used for automated path planning of an industrial robot. The digital twin needs to be accurately calibrated in relation to the resource locations due to the physical limitations of placing resources [...] Read more.

This article presents a system for automatically updating a digital twin model, used for automated path planning of an industrial robot. The digital twin needs to be accurately calibrated in relation to the resource locations due to the physical limitations of placing resources out precisely. The process considered is a surface roughness measurement of aerospace metal parts that requires high positional accuracy. The scenario takes place in a robot cell that is a Plug & Produce system, where resources can be added and removed in minutes, allowing fast reconfiguration of the production resources. This means that an automated path planner is required for the robot to adapt to new locations of these resources automatically. A digital twin is proposed, consisting of a robot path planner and a simulation model that is updated when resources are added to the system. The resources should automatically appear in the simulation and be placed at an accurate location. The purpose of automating these steps is to make the update of the digital twin faster during production and remove the requirement for expert knowledge. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Figure 1

20 pages, 3687 KB

Open AccessArticle

A Multimodal Large Language Model Framework for Intelligent Perception and Decision-Making in Smart Manufacturing

by Tianyu Wang, Bowen Zhang, Daqi Jiang and Dong Li

Sensors 2025, 25(10), 3072; https://doi.org/10.3390/s25103072 - 13 May 2025

Cited by 2 | Viewed by 5528

Abstract

In modern manufacturing, making accurate and timely decisions requires the ability to effectively handle multiple types of data. This paper presents a multimodal system designed specifically for smart manufacturing applications. The system combines various data sources including images, sensor data, and production records, [...] Read more.

In modern manufacturing, making accurate and timely decisions requires the ability to effectively handle multiple types of data. This paper presents a multimodal system designed specifically for smart manufacturing applications. The system combines various data sources including images, sensor data, and production records, using advanced multimodal large language models. This approach addresses common limitations of traditional single-modal methods, such as isolated data analysis and poor integration between different data types. Key contributions include a unified method for representing different data types, dynamic semantic tokenization for better data processing, strong alignment strategies across modalities, and a practical two-stage training method involving initial large-scale pretraining and later fine-tuning for specific tasks. Additionally, a novel Transformer-based model is introduced for generating both images and text, significantly improving real-time decision-making capabilities. Experiments on relevant industrial datasets show that this method consistently performs better than current state-of-the-art approaches in tasks like image–text retrieval and visual question answering. The results demonstrate the effectiveness and versatility of the proposed methods, offering important insights and practical solutions to enhance intelligent manufacturing, predictive maintenance, and anomaly detection, thus supporting the development of more efficient and reliable industrial systems. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Figure 1

26 pages, 10620 KB

Open AccessArticle

Tool Wear State Identification Method with Variable Cutting Parameters Based on Multi-Source Unsupervised Domain Adaptation

by Zhigang Cai, Wangyang Li, Jianxin Song, Hongyu Jin and Hongya Fu

Sensors 2025, 25(6), 1742; https://doi.org/10.3390/s25061742 - 11 Mar 2025

Cited by 2 | Viewed by 1330

Abstract

Accurately identifying tool wear states with variable cutting parameters can improve machining quality and efficiency. However, existing wear state recognition methods based on unsupervised domain adaptation mostly employ the knowledge transfer learning strategy in a single source domain. They cannot fully utilize the [...] Read more.

Accurately identifying tool wear states with variable cutting parameters can improve machining quality and efficiency. However, existing wear state recognition methods based on unsupervised domain adaptation mostly employ the knowledge transfer learning strategy in a single source domain. They cannot fully utilize the sensor data distribution information of multiple cutting parameters, hindering recognition performance improvement. Thus, this paper proposes a wear-state recognition method for variable cutting parameters based on multi-source unsupervised domain adaptation. First, non-stationary Transformer encoders extract non-stationary common features; then, sliced Wasserstein distance-based domain-specific feature distribution alignment and classifier output alignment scale down the domain shift and make multi-domain distribution synchronous alignment less complex. Finally, the milling experiments with variable cutting parameters are conducted to validate the recognition performance of the proposed method. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Figure 1

23 pages, 958 KB

Open AccessArticle

Recipe Based Anomaly Detection with Adaptable Learning: Implications on Sustainable Smart Manufacturing

by Junhee Lee, Jaeseok Jang, Qing Tang and Hail Jung

Sensors 2025, 25(5), 1457; https://doi.org/10.3390/s25051457 - 27 Feb 2025

Viewed by 1905

Abstract

The advent of Industry 4.0 has significantly transformed the manufacturing sector, bringing advancements in quality control efficiency, environmental sustainability, and production development. These changes have led to the development of intelligent technologies such as artificial intelligence (AI). However, implementing AI solutions in manufacturing [...] Read more.

The advent of Industry 4.0 has significantly transformed the manufacturing sector, bringing advancements in quality control efficiency, environmental sustainability, and production development. These changes have led to the development of intelligent technologies such as artificial intelligence (AI). However, implementing AI solutions in manufacturing processes still presents challenges in many aspects, particularly in handling irregular datasets influenced by diverse manufacturing settings. In the field of injection molding, quality inspection often occurs at the batch level rather than at the individual level, providing only the overall defect ratio of batch production instead of labeling each individual product. These issues limit the general application of AI and data-driven decision-making. To address these limitations and enhance product efficiency, this study proposes a novel anomaly detection framework for a specific manufacturing process. In Recipe-Based Learning, we first apply K-Means clustering to account for the flexible manufacturing process, which relies on diverse settings. The injection molding data are classified into setting-specific recipes to ensure data normality and uniqueness. The Kruskal-Wallis test is conducted to provide statistical evidence of differences in data based on varying settings, further justifying the necessity of Recipe-Based Learning. Then, Autoencoders for anomaly detection are trained with normal data from each recipe. With this data-driven AI approach, 61 defective products are predicted, compared to the existing 41 defects. Meanwhile, the integrated model, which does not consider variations in settings, only predicted 2 defects, indicating poor and distorted quality inspection. For Adaptable Learning, which focuses on new inputs with unseen settings, we apply KL-Divergence to identify the closest trained recipe data and its corresponding model. This approach outperformed both the integrated and additionally trained models in predictive power. As a result, continuous prediction is achieved without the need for further training, successfully enhancing process optimization. In the context of smart factories in the injection molding industry, such improvements in process management can significantly enhance overall productivity and decision-making, primarily through a data-driven AI approach. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Graphical abstract

20 pages, 9783 KB

Open AccessArticle

A Lightweight and Efficient Multimodal Feature Fusion Network for Bearing Fault Diagnosis in Industrial Applications

by Chaoquan Mo, Ke Huang, Wenhan Li and Kaibo Xu

Sensors 2024, 24(22), 7139; https://doi.org/10.3390/s24227139 - 6 Nov 2024

Viewed by 1969

Abstract

To address the issues of single-structured feature input channels, insufficient feature learning capabilities in noisy environments, and large model parameter sizes in intelligent diagnostic models for mechanical equipment, a lightweight and efficient multimodal feature fusion convolutional neural network (LEMFN) method is proposed. Compared [...] Read more.

To address the issues of single-structured feature input channels, insufficient feature learning capabilities in noisy environments, and large model parameter sizes in intelligent diagnostic models for mechanical equipment, a lightweight and efficient multimodal feature fusion convolutional neural network (LEMFN) method is proposed. Compared with existing models, LEMFN captures rich fault features at multiple scales by combining time-domain and frequency-domain signals, thereby enhancing the model’s robustness to noise and improving data adaptability under varying operating conditions. Additionally, the convolutional block attention module (CBAM) and random overlapping sampling technology (ROST) are introduced, and through a feature fusion strategy, the accurate diagnosis of mechanical equipment faults is achieved. Experimental results demonstrate that the proposed method not only possesses high diagnostic accuracy and rapid convergence but also exhibits strong robustness in noisy environments. Finally, a graphical user interface (GUI)-based mechanical equipment fault detection system was developed to promote the practical application of intelligent fault diagnosis in mechanical equipment. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Figure 1

26 pages, 2880 KB

Open AccessArticle

Dynamic Intelligent Scheduling in Low-Carbon Heterogeneous Distributed Flexible Job Shops with Job Insertions and Transfers

by Yi Chen, Xiaojuan Liao, Guangzhu Chen and Yingjie Hou

Sensors 2024, 24(7), 2251; https://doi.org/10.3390/s24072251 - 31 Mar 2024

Cited by 15 | Viewed by 2693

Abstract

With the rapid development of economic globalization and green manufacturing, traditional flexible job shop scheduling has evolved into the low-carbon heterogeneous distributed flexible job shop scheduling problem (LHDFJSP). Additionally, modern smart manufacturing processes encounter complex and diverse contingencies, necessitating the ability to address [...] Read more.

With the rapid development of economic globalization and green manufacturing, traditional flexible job shop scheduling has evolved into the low-carbon heterogeneous distributed flexible job shop scheduling problem (LHDFJSP). Additionally, modern smart manufacturing processes encounter complex and diverse contingencies, necessitating the ability to address dynamic events in real-world production activities. To date, there are limited studies that comprehensively address the intricate factors associated with the LHDFJSP, including workshop heterogeneity, job insertions and transfers, and considerations of low-carbon objectives. This paper establishes a multi-objective mathematical model with the goal of minimizing the total weighted tardiness and total energy consumption. To effectively solve this problem, diverse composite scheduling rules are formulated, alongside the application of a deep reinforcement learning (DRL) framework, i.e., Rainbow deep-Q network (Rainbow DQN), to learn the optimal scheduling strategy at each decision point in a dynamic environment. To verify the effectiveness of the proposed method, this paper extends the standard dataset to adapt to the LHDFJSP. Evaluation results confirm the generalization and robustness of the presented Rainbow DQN-based method. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Figure 1

15 pages, 6917 KB

Open AccessArticle

Uncertainty Evaluation of a Gas Turbine Model Based on a Nonlinear Autoregressive Exogenous Model and Monte Carlo Dropout

by Armando Cajahuaringa, Rubén Aquize Palacios, Juan M. Mauricio Villanueva, Aurelio Morales-Villanueva, José Machuca, Juan Contreras and Kiara Rodríguez Bautista

Sensors 2024, 24(2), 465; https://doi.org/10.3390/s24020465 - 12 Jan 2024

Cited by 2 | Viewed by 2015

Abstract

Gas turbines are thermoelectric plants with various applications, such as large-scale electricity production, petrochemical industry, and steam generation. In order to optimize the operation of a gas turbine, it is necessary to develop system identification models that allow for the development of studies [...] Read more.

Gas turbines are thermoelectric plants with various applications, such as large-scale electricity production, petrochemical industry, and steam generation. In order to optimize the operation of a gas turbine, it is necessary to develop system identification models that allow for the development of studies and analyses to increase the system’s reliability. Current strategies for modeling complex and non-linear systems can be based on artificial intelligence techniques, using autoregressive neural networks of the NARX and LSTM type. In this context, this work aims to develop a model of a gas turbine capable of estimating the rotation speed of the turbine and simultaneously estimating the uncertainty associated with the estimation. These methodologies are based on artificial neural networks and the Monte Carlo dropout simulation method. The results were obtained from experimental data from a 215 MW gas turbine, getting the best model with a MAPE of 0.02% and an uncertainty associated with the turbine rotation speed of 2.2 RPM. Full article

(This article belongs to the Special Issue Artificial Intelligence and Sensing Technology in Smart Manufacturing)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence and Sensing Technology in Smart Manufacturing

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI