A fusion data preprocessing method and its application in complex industrial power consumption prediction

Xiao, Xiong; Yuxiong, Xiao; Zhang, Yongjun; Qiu, Jing; Zhang, Jiawei; Yildirim, Tanju

doi:10.1016/j.mechatronics.2021.102520

Cited by 15 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, the research [63] stresses the importance of data preprocessing because: (1) real-world data is impure; (2) high-performance mining systems require quality data; and (3) quality data yields concentrative patterns. Moreover, many preprocessing techniques have been reviewed in the scientific literature [64][65][66], but the lack of data preprocessing methodologies still remains. Further, in the reviewed scientific literature, the cross-industry standard process for data mining (CRISP-DM) [67,68] methodology, in which researchers focus on big data [69][70][71], is most often used as a basis for data preprocessing [72,73].…”

Section: Discussionmentioning

confidence: 99%

Edge Computing Data Optimization for Smart Quality Management: Industry 5.0 Perspective

et al. 2023

View full text Add to dashboard Cite

In the last decade, researchers have focused on digital technologies within Industry 4.0. However, it seems the Industry 4.0 hype did not fulfil industry expectations due to many implementation challenges. Today, Industry 5.0 proposes a human-centric approach to implement digital sustainable technologies for smart quality improvement. One important aspect of digital sustainability is reducing the energy consumption of digital technologies. This can be achieved through a variety of means, such as optimizing energy efficiency, and data centres power consumption. Complementing and extending features of Industry 4.0, this research develops a conceptual model to promote Industry 5.0. The aim of the model is to optimize data without losing significant information contained in big data. The model is empowered by edge computing, as the Industry 5.0 enabler, which provides timely, meaningful insights into the system, and the achievement of real-time decision-making. In this way, we aim to optimize data storage and create conditions for further power and processing resource rationalization. Additionally, the proposed model contributes to Industry 5.0 from a social aspect by considering the knowledge, not only of experienced engineers, but also of workers who work on machines. Finally, the industrial application was done through a proof-of-concept using manufacturing data from the process industry, where the amount of data was reduced by 99.73% without losing significant information contained in big data.

show abstract

Section: Discussionmentioning

confidence: 99%

Edge Computing Data Optimization for Smart Quality Management: Industry 5.0 Perspective

et al. 2023

View full text Add to dashboard Cite

show abstract

“…An important stage of classification is the data preparation stage [32,33]. The main purpose is to identify the essential features.…”

Section: Methodsmentioning

confidence: 99%

Identification of the Technical Condition of Induction Motor Groups by the Total Energy Flow

2021

View full text Add to dashboard Cite

The paper discusses the method of identifying the technical condition of induction motors by classifying the energy data coming from the main common power bus. The work shows the simulation results of induction motor operation. The correlation between occurring defects and current diagrams is presented. The developed simulation model is demonstrated. The general algorithm for conducting experiments is described. Five different experiments to develop an algorithm for the classification are conducted: determination of the motors number in operation with different power; determination of the motors number in operation with equal power; determination of the mode and load of induction electric motor; determination of the fault and its magnitude with regard to operation and load of induction motor; determination of the fault and its magnitude with regard to operation and load of induction motor with regard to non-linear load in the flow. The article also presents an algorithm for preprocessing data to solve the classification problem. In addition, the classification results are shown and recommendations for testing and using the classification algorithm on a real object are made.

show abstract

“…Pre-processing may also involve feature extraction to reduce the dimensionality of the data and to identify the most relevant features for fusion. Inappropriate data pre-procesing tends to impact fusion outcomes, leading to inaccurate or unreliable results [15,16].…”

Section: Pre-processing and Fusion Of Imagesmentioning

confidence: 99%

Fusion Insights from Ultrasonic and Thermographic Inspections for Impact Damage Analysis

Torbali

Alhammad

Zolotas

et al. 2023

AIAA AVIATION 2023 Forum

View full text Add to dashboard Cite

Low energy impact damage in composite materials may be more concerning than it appears visually, often requiring a detailed examination for accurate assessment to ensure safe and sustainable operation. Non-destructive testing (NDT) methods provide such inspection techniques, and in this paper, NDT-based fusion is explored for enhanced identification of defect size and location compared to indepdently using individual NDT methods separately. Three Carbon Fiber Reinforced Polymer (CFRP) specimens are examined, each with an impact damage of a given energy level, using pulsed thermography (PT) and phased array (PA) ultrasonic methods. Following the extraction of binary defect shapes from source images, a decision-level fusion approach is performed. The results indicate that combining ultrasonic and infrared thermography (IRT) inspections for CFRP composite materials is promising to achieve enhanced and improved detection traceability.

show abstract

A fusion data preprocessing method and its application in complex industrial power consumption prediction

Cited by 15 publications

References 12 publications

Edge Computing Data Optimization for Smart Quality Management: Industry 5.0 Perspective

Edge Computing Data Optimization for Smart Quality Management: Industry 5.0 Perspective

Identification of the Technical Condition of Induction Motor Groups by the Total Energy Flow

Fusion Insights from Ultrasonic and Thermographic Inspections for Impact Damage Analysis

Contact Info

Product

Resources

About