Metamodel-assisted optimization is a frequently applied approach for structural design optimization problems. Here, a data-driven metamodel approximates the computationally expensive simulation results of first princi...
详细信息
Metamodel-assisted optimization is a frequently applied approach for structural design optimization problems. Here, a data-driven metamodel approximates the computationally expensive simulation results of first principle models, e.g., finite element analyses. A significant drawback of typical metamodels is the limited amount of information that can be predicted due to their generally low-dimensional model output. Consequently, the metamodel usually does not predict the distribution of the desired quantity. This work presents a metamodel approach capable of predicting the spatial and temporal distribution of quantities for structural processes. This increases the modeling capability and makes more information available for the optimization. The autoencoder compresses the spatial distribution into a couple of features. The proposed methodology is applied to a three-stage forming process. Copyright (c) 2024 The Authors.
Alarm systems are commonly deployed in modern industrial facilities to monitor process operations. However, due to the presence of nuisance alarms and alarm floods, their efficiencies are much degraded. Especially, al...
详细信息
Alarm systems are commonly deployed in modern industrial facilities to monitor process operations. However, due to the presence of nuisance alarms and alarm floods, their efficiencies are much degraded. Especially, alarm floods are among the most difficult issues in industrial alarm management and recognised as the main causes of many industrial accidents. To address alarm floods, this paper proposes a Root Cause Identification method (RCI) for industrial alarm floods based on word embedding and few-shot learning. The contributions are threefold: 1) A textual encoding method based on word embedding is proposed to convert alarm messages into numerical word vectors that can be used in the modeling of RCI;2) an alarm priority based adaptive weighting strategy is designed to make the RCI more sensitive to alarms of higher priorities and appearing earlier;3) a few-shot learning method based on the long short-term memory is adapted to identify root causes of alarm floods based on limited instances of labeled data. The effectiveness and superiority of the proposed method are demonstrated by a case study based on data from the Vinyl Acetate Monomer (VAM) public model.
In recent years, BIM (Building Information modeling) because of its unified and efficient digitalization, visualization, synergistic and other engineering advantages is being widely concerned and researched and applie...
详细信息
ISBN:
(纸本)9798400718144
In recent years, BIM (Building Information modeling) because of its unified and efficient digitalization, visualization, synergistic and other engineering advantages is being widely concerned and researched and applied in various fields related to construction all over the world. In particular, it has played a huge coordination and optimization benefit for project cost management, construction resource deployment, and full life cycle control. As a typical resource-, technology- and manpower-intensive project, infrastructure engineering involves a large amount of complex and heterogeneous building information and real-time dynamic Internet of Things information. The traditional information control mode based on drawings often shows the disadvantages of information lag or even fragmentation. By analyzing the common information standard system of Building Information modeling (BIM), specifically the Industry Foundation Classes (IFC), this study establishes the correlation between the IFC standard system and its application in grid infrastructure projects. Subsequently, it conducts an assessment of the necessity and feasibility of extending IFC for grid engineering purposes. The current buildingSMART latest technical report emphasizes the general principles of IFC extensions, and the IFC grid engineering extensions are carried out on the basis of following this guideline. Finally, combined with ubiquitous power IoT technology, a set of BIM+IoT-based grid infrastructure whole process information management technology route program is initially proposed.
As electrical devices take on more life-critical roles, such as in autonomous driving, ensuring the quality of solder joints during production becomes increasingly important. Recently, there has been a growing interes...
详细信息
As electrical devices take on more life-critical roles, such as in autonomous driving, ensuring the quality of solder joints during production becomes increasingly important. Recently, there has been a growing interest in using machine learning techniques for this purpose. However, current research lacks a comprehensive overview that categorizes and analyzes relevant studies based on their specific intervention points within the production process. This literature review aims to examine and evaluate research coverage along three dimensions: intervention points in the process, non-destructive testing methods, and machine learning techniques employed. For this review, 112 conference papers and journal articles published since 2010 were selected from three databases using the PRISMA methodology. These publications were classified into the three dimensions previously mentioned, summarized, and analyzed. Furthermore, the literature core is critically evaluated to identify research gaps and limitations. The analysis shows that most studies focus on solder joint control, with few addressing intervention points in solder paste and component placement. Visual imaging and neural networks are the dominant techniques for non-destructive testing and machine learning, respectively. Despite a variety of literature that uses high-performance neural networks, meeting industrial detection standards often requires tolerating high false alarm rates. The findings contribute to structuring existing research and identifying research needs, particularly in validating these systems and integrating data from various testing methods and intervention points.
The initial stage in the cement production process is the preparation of raw materials. This crucial step significantly influences the overall quality of the final cement product. In this paper, we investigate the eff...
详细信息
作者：
Fu, JiayingHe, YingchaoCheng, FangZhejiang Univ
Coll Biosyst Engn & Food Sci 866 Yuhangtang Rd Hangzhou 310058 Zhejiang Peoples R China Zhejiang Univ
Key Lab Intelligent Equipment & Robot Agr Zhejiang Hangzhou 310058 Zhejiang Peoples R China
Fish processing is an indispensable part of fish food production. It mainly involves de-heading, gutting, filleting, skinning, trimming, and slicing, with the cutting operations holding a critical role. Unfortunately,...
详细信息
Fish processing is an indispensable part of fish food production. It mainly involves de-heading, gutting, filleting, skinning, trimming, and slicing, with the cutting operations holding a critical role. Unfortunately, inefficiency, low quality, and poor safety are the primary problems facing the fish processing industry today, dramatically hindering the automation and intelligence of fish processing. Consequently, it is vital to develop intelligent cutting in current fish processing in an efficient, high-quality, and safe manner. This review summarizes the main cutting techniques for fish processing. The critical techniques to achieve intelligent cutting in fish processing from imaging, image processing, and modeling dimensions are outlined, with their applications in practical fish processing. Fish characteristics, cutting mechanisms, and cutting processcontrol are emphasized. In addition, Industry 4.0 technologies, especially the Internet of Things (IoT), big data analytics, and digital twins (DT), are emphasized. Finally, challenges and future work are highlighted, which will serve as references for subsequent researchers and enterprises engaged in this field to promote the automation and intelligence of fish processing production, ultimately realizing the high-efficiency, high-quality, and safe production of fish food products.
The development of an accurate soft sensor modeling method in the process industry remains a great challenge because the coupling relationship between variables is always intricate and difficult to model. In this work...
详细信息
ISBN:
(纸本)9798350321050
The development of an accurate soft sensor modeling method in the process industry remains a great challenge because the coupling relationship between variables is always intricate and difficult to model. In this work, a dynamic graph learning (DGL) soft sensor is proposed to alleviate this problem. The proposed model realizes the ability of the soft sensor to perceive the coupling relationship in real time by automatically learning the dynamic graph. Then, a causal convolutional mechanism and a multi-hop graph attention mechanism are used to systematically construct the dependencies of variables in the spatial-temporal dimension and model their variation patterns effectively. Finally, the proposed method is tested on the penicillin fermentation process and shown to be feasible and effective. The results showed that the change of the dynamic graph in the spatial-temporal dimension was in line with the process mechanism.
This study provides a comparative analysis for predicting Vicat softening temperatures of Low-Density Polyethylene (LDPE), which is one of the versatile polymers used extensively across various industrial sectors. LDP...
详细信息
ISBN:
(数字)9783031585616
ISBN:
(纸本)9783031585609;9783031585616
This study provides a comparative analysis for predicting Vicat softening temperatures of Low-Density Polyethylene (LDPE), which is one of the versatile polymers used extensively across various industrial sectors. LDPE exhibits unique properties, such as flexibility, electrical insulating characteristics, and low melting point. The manufacturing process demands rigorous quality controls, involving extensive laboratory product testing, requiring significant time, labor, and cost investments. In this study, we explored the potential ofmachine-learning-based predictors to alleviate or reduce these challenges. Our analysis focused on the accuracy and processing time of predicting models based on three prominent boostingmethods: Gradient BoostingMachines (GBM), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost). We collected the laboratory testing results from one of the largest polymer manufacturers in Southeast Asia: our data set comprised 71 features. Based on the comparison results, we concluded that XGBoost exhibits superior predictive performance (in terms of MAE, MSE, and RMSE) compared to GBM and AdaBoost, indicating its potential in time saving, labor, and cost reduction in the manufacturing process. Both XGBoost and AdaBoost incurred maximum errors below 2.9, aligning with the industry testing standard. Notably, Adaboost incurred slightly lower maximum errors in comparison to XGBoost. Furthermore, we presented the top 10 significant features highlighted by the XGBoost models.
This article introduces a methodology for modeling and parameter identification of the quadrotor systems, which obviates the need for external devices. The model parameters and inherent system disturbances can be iden...
详细信息
ISBN:
(纸本)9798350373707;9798350373691
This article introduces a methodology for modeling and parameter identification of the quadrotor systems, which obviates the need for external devices. The model parameters and inherent system disturbances can be identified via flight data acquisition through closed-loop system flight testing of an unmanned aerial vehicle (UAV). This study initially simplifies the model for each axis into second-order systems with disturbances, which necessitates the identification of only three characteristic parameters, thereby alleviating the complexity of the identification process. Subsequently, the identification of optimal model parameters is achieved via closed-loop measurement data. The subsequent physical experiment validates that the accurancy of Normalized Mean Square Error (NMSE) for the three-axis angles and angular velocities exceeds 90%. The proposed algorithm constructs an inner-loop controlled object model for quadrotor systems, facilitating the design of closed-loop control system for both angular velocity and outer loops.
An accurate magnetic model for electric motors is essential for high performance control strategies. The magnetic model is typically acquired by massive experiments of measuring magnetic flux data throughout the opera...
详细信息
ISBN:
(纸本)9798350360875;9798350360868
An accurate magnetic model for electric motors is essential for high performance control strategies. The magnetic model is typically acquired by massive experiments of measuring magnetic flux data throughout the operating current range, and then applied in the controlprocess via a look-up table of measurements. Both the acquisition and the application processes are time-consuming and not suitable for low-latency controls. To address this issue, we propose a novel compressed sensing-based method to recover a high-fidelity flux map from limited randomly sampled data points, and further infer an analytical magnetic model of the recovered flux map. This analytical model can then be used to efficiently compute the magnetic flux instead of looking up measurement data, given the stator current in the control loop. The proposed approach is validated on data simulated by finite element analysis (FEA).
暂无评论