Zhi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhi Li has a total of 67 co-authors. Here are the top co-authors by number of shared publications:
- Ali Vatankhah Barenji
School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA
5 shared publications W. M. Wang
Guangdong Provincial Key Laboratory of Computer Integrated Manufacturing System, Guangdong University of Technology
3 shared publications- Wai Ming Wang
Guangdong Provincial Key Laboratory of Computer Integrated Manufacturing Systems, School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, People’s Republic of China
3 shared publications - Eric Tsui
Educational Research Centre, The Hong Kong Polytechnic University, Hung Hom, Hong Kong
2 shared publications - George Q. Huang
The Hong Kong Polytechnic University
2 shared publications - Hanyang Guo
Sun Yat-sen University, Zhuhai, China
2 shared publications
Latest Publications
- Open Access
- 7 October 2023
- Published by Atlantis Press SARL
- p. 430-437
Anchor Characteristics and Consumer Purchasing Behavior: Based on Perceived Value Theory
- 7 October 2023
- Published by Atlantis Press SARL
- p. 430-437
Open AccessAnchor Characteristics and Consumer Purchasing Behavior: Based on Perceived Value Theory
- 15 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 999-1009
Measurement Data Complement of Power Distribution System Based on Clustering-BayesLSTM Combined Model
To address the problems of missing measurement data and low efficiency of large-scale measurement data complement in power distribution system, a measurement data complement method based on Clustering-BayesLSTM combined model is proposed. Firstly, K-mediods clustering is utilized to categorize all the quantity measurements, select the main/standby crucial measurements in each category, and calculate their average deviation from other measurements in order to effectively reduce the solution size of the long short-term memory (LSTM) neural network model. Then, through the LSTM prediction model based on Bayesian optimization, the missing main/standby crucial measurements are complemented. In addition, the average deviations from the primary/backup crucial quantity measurements are used to supplement the other missing measurements. Finally, the effectiveness of the proposed method is verified based on the real measurement data of a local power distribution system.
- 15 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 999-1009
Measurement Data Complement of Power Distribution System Based on Clustering-BayesLSTM Combined Model
To address the problems of missing measurement data and low efficiency of large-scale measurement data complement in power distribution system, a measurement data complement method based on Clustering-BayesLSTM combined model is proposed. Firstly, K-mediods clustering is utilized to categorize all the quantity measurements, select the main/standby crucial measurements in each category, and calculate their average deviation from other measurements in order to effectively reduce the solution size of the long short-term memory (LSTM) neural network model. Then, through the LSTM prediction model based on Bayesian optimization, the missing main/standby crucial measurements are complemented. In addition, the average deviations from the primary/backup crucial quantity measurements are used to supplement the other missing measurements. Finally, the effectiveness of the proposed method is verified based on the real measurement data of a local power distribution system.
- Open Access
- 25 May 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (11) , 8578
Blockchain-Based and Value-Driven Enterprise Data Governance: A Collaborative Framework
The traditional mode of cooperation between enterprises still suffers from major problems, including data privacy leakage, data falsification, and inefficient collaboration in data sharing. These challenges make it difficult for enterprises to ensure that their cooperative suppliers adopt sustainable practices in standards identification and operation processes. This paper proposes a “Value–Standard–Process” collaborative framework for blockchain-based enterprise data governance that helps ensure a high degree of data security, a high reliability of collaborative tasks, and a high transparency of value transformation. First, this paper proposes a new collaborative mode for blockchain-based manufacturing in the sharing economy, including the non-linear dynamic evaluation and value balancing mechanism of data with multiple attributes, a trusted data governance mechanism for blockchain-based manufacturing, and a smart contract generation mechanism for value-driven collaboration. Second, this paper explains these three components and the implementation of the overall framework. Third, this paper verifies the applicability and achievability of the proposed framework through experiments. Establishing the value-driven multi-level blockchain-based collaboration mode facilitates the effective flow of production factors and promotes trust in the digital economy of sustainability.
- 25 May 2023
- Published by MDPI AG in Sustainability
- Vol. 15 (11) , 8578
Open AccessBlockchain-Based and Value-Driven Enterprise Data Governance: A Collaborative Framework
The traditional mode of cooperation between enterprises still suffers from major problems, including data privacy leakage, data falsification, and inefficient collaboration in data sharing. These challenges make it difficult for enterprises to ensure that their cooperative suppliers adopt sustainable practices in standards identification and operation processes. This paper proposes a “Value–Standard–Process” collaborative framework for blockchain-based enterprise data governance that helps ensure a high degree of data security, a high reliability of collaborative tasks, and a high transparency of value transformation. First, this paper proposes a new collaborative mode for blockchain-based manufacturing in the sharing economy, including the non-linear dynamic evaluation and value balancing mechanism of data with multiple attributes, a trusted data governance mechanism for blockchain-based manufacturing, and a smart contract generation mechanism for value-driven collaboration. Second, this paper explains these three components and the implementation of the overall framework. Third, this paper verifies the applicability and achievability of the proposed framework through experiments. Establishing the value-driven multi-level blockchain-based collaboration mode facilitates the effective flow of production factors and promotes trust in the digital economy of sustainability.
- Open Access
- 1 September 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2337 (1) , 012006
A Real-Time Automated Defect Classification System Based on Two-Step Convolutional Neural Network
The increasing amount of defect images in semiconductor manufacturing process imposes the demand of classifying these images in real-time. In this paper we adopt a two-step deep learning based Convolutional Neural Network (CNN) to detect and classify the defect images from clean ones. The proposed method integrates the detection and classification process into one forward step, which takes image-level feature as well as empirical defect classification rules into account. In practice, the Real-Time Automated Defect Classification (RT-ADC) system was deployed in inline production process, which brings high efficiency; better wafer analysis and root cause determination for yield enhancement.
- 1 September 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2337 (1) , 012006
Open AccessA Real-Time Automated Defect Classification System Based on Two-Step Convolutional Neural Network
The increasing amount of defect images in semiconductor manufacturing process imposes the demand of classifying these images in real-time. In this paper we adopt a two-step deep learning based Convolutional Neural Network (CNN) to detect and classify the defect images from clean ones. The proposed method integrates the detection and classification process into one forward step, which takes image-level feature as well as empirical defect classification rules into account. In practice, the Real-Time Automated Defect Classification (RT-ADC) system was deployed in inline production process, which brings high efficiency; better wafer analysis and root cause determination for yield enhancement.
- Open Access
Research on the Blue Carbon Trading Market System under Blockchain Technology
To combat global warming, “carbon neutrality” has gradually become a consensus. Some countries have constructed domestic and regional carbon trading markets, and links to global carbon markets are receiving increasing attention. Blue carbon, an important component of nature-based solutions (NbS), has not received the attention it deserves and is still isolated from the carbon trading market. Based on summarizing the existing achievements of blockchain application in carbon trading, this paper analyzes how to make each participating body provide services in the process of blue carbon production, circulation and trading, and designs the architectural diagram of the blue carbon system under peer-to-peer (P2P) transactions based on the theoretical framework of blockchain 3.0. Utilizing the advantages of decentralization, high transparency and non-tamperability of blockchain, we can realize a highly efficient, low-cost and intelligent blue carbon trading management system. Thus, we can make the world pay more attention to the development and utilization of marine resources and increase investment in blue carbon sink projects; and promote the development of blue carbon market, enrich the carbon trading market, and help achieve “emission reduction without reduction in production”.
Open AccessResearch on the Blue Carbon Trading Market System under Blockchain Technology
To combat global warming, “carbon neutrality” has gradually become a consensus. Some countries have constructed domestic and regional carbon trading markets, and links to global carbon markets are receiving increasing attention. Blue carbon, an important component of nature-based solutions (NbS), has not received the attention it deserves and is still isolated from the carbon trading market. Based on summarizing the existing achievements of blockchain application in carbon trading, this paper analyzes how to make each participating body provide services in the process of blue carbon production, circulation and trading, and designs the architectural diagram of the blue carbon system under peer-to-peer (P2P) transactions based on the theoretical framework of blockchain 3.0. Utilizing the advantages of decentralization, high transparency and non-tamperability of blockchain, we can realize a highly efficient, low-cost and intelligent blue carbon trading management system. Thus, we can make the world pay more attention to the development and utilization of marine resources and increase investment in blue carbon sink projects; and promote the development of blue carbon market, enrich the carbon trading market, and help achieve “emission reduction without reduction in production”.
- 1 February 2022
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 61 (14) , 4934-4950
Applying blockchain technology to ensure compliance with sustainability standards in the PPE multi-tier supply chain
Because of the Covid-19 pandemic, urgent surging demand for healthcare products such as personal protective equipment (PPE) has caused significant challenges for multi-tier supply chain management. Although a given firm may predominantly focus on an arms-length solution by targeting the first-tier supplier, the firm can still struggle with extended multi-tier suppliers it cannot choose which use unsustainable practices. One key goal is compliance across various dimensions with production, environmental and labour standards across the multi-tier supply chain, a goal that blockchain technology can be applied to manage. Based on a comprehensive literature review, this research develops a system architecture of blockchain-based multi-tier sustainable supply chain management in the PPE industry designed to identify and coordinate standards in production and social and environmental sustainability in multi-tier PPE supply chains. The architecture was validated by theoretical basis, expert opinions and technical solutions. We conclude with managerial implications for implementing blockchain technology to advance sustainable multi-tier supply chain practices.
- 1 February 2022
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 61 (14) , 4934-4950
Applying blockchain technology to ensure compliance with sustainability standards in the PPE multi-tier supply chain
Because of the Covid-19 pandemic, urgent surging demand for healthcare products such as personal protective equipment (PPE) has caused significant challenges for multi-tier supply chain management. Although a given firm may predominantly focus on an arms-length solution by targeting the first-tier supplier, the firm can still struggle with extended multi-tier suppliers it cannot choose which use unsustainable practices. One key goal is compliance across various dimensions with production, environmental and labour standards across the multi-tier supply chain, a goal that blockchain technology can be applied to manage. Based on a comprehensive literature review, this research develops a system architecture of blockchain-based multi-tier sustainable supply chain management in the PPE industry designed to identify and coordinate standards in production and social and environmental sustainability in multi-tier PPE supply chains. The architecture was validated by theoretical basis, expert opinions and technical solutions. We conclude with managerial implications for implementing blockchain technology to advance sustainable multi-tier supply chain practices.
- 25 August 2020
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 59 (7) , 2229-2249
A blockchain-based evaluation approach for customer delivery satisfaction in sustainable urban logistics
The rapid development of urbanisation and the ever-changing consumers’ demands are constantly changing the urban logistics industry, imposing challenges on logistics service providers to improve customer satisfaction which is one of the indicators for the sustainability of urban logistics. Existing customer satisfaction evaluations are based on a questionnaire survey, which is time-consuming and labour intensive. Moreover, the logistics data are confidential and can only be accessed by the stakeholders in existing logistics models, causing the problem of information non-transparency among logistics enterprises and the third authorities like banks and governments, which may hinder the sustainable development of urban logistics. In this paper, we propose a blockchain-based evaluation approach for customer satisfaction in the context of urban logistics. Four criteria affecting customer satisfaction in urban logistics are identified. A machine learning algorithm Long Short-Term Memory (LSTM) is adopted to predict customer satisfaction in the future period. The implementation is demonstrated to illustrate the proposed approach. A smart contract is designed for compensation and/or refund to customers when their satisfaction with the delivery services is at a low level.
- 25 August 2020
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 59 (7) , 2229-2249
A blockchain-based evaluation approach for customer delivery satisfaction in sustainable urban logistics
The rapid development of urbanisation and the ever-changing consumers’ demands are constantly changing the urban logistics industry, imposing challenges on logistics service providers to improve customer satisfaction which is one of the indicators for the sustainability of urban logistics. Existing customer satisfaction evaluations are based on a questionnaire survey, which is time-consuming and labour intensive. Moreover, the logistics data are confidential and can only be accessed by the stakeholders in existing logistics models, causing the problem of information non-transparency among logistics enterprises and the third authorities like banks and governments, which may hinder the sustainable development of urban logistics. In this paper, we propose a blockchain-based evaluation approach for customer satisfaction in the context of urban logistics. Four criteria affecting customer satisfaction in urban logistics are identified. A machine learning algorithm Long Short-Term Memory (LSTM) is adopted to predict customer satisfaction in the future period. The implementation is demonstrated to illustrate the proposed approach. A smart contract is designed for compensation and/or refund to customers when their satisfaction with the delivery services is at a low level.
- 10 June 2020
- Published by Taylor & Francis in International Journal of Computer Integrated Manufacturing
- Vol. 34 (7-8) , 844-859
A digital twin-driven approach towards smart manufacturing: reduced energy consumption for a robotic cell
One of the significant trends in smart manufacturing is the idea of industrial digitalization, which is enabled through the use of new information technologies, such as the Internet of Things, big data, cloud computing, and artificial intelligence. However, manufacturing industries can only be achieved by combining the physical manufacturing world and digital world, to realize a series of smart manufacturing activities, such as active perception, real-time interaction, automatic processing, intelligent control, and real-time optimization, etc. In this paper, a digital twin-driven approach combines with agent-based decision-making for real-time optimization of motion planning in robotic cellular is proposed, with optimizing the physical and virtual layer at the manufacturing facility. Accordingly, an architecture of the digital twin-driven facility is design, and its operational mechanisms and implementation methods are explained in detail. Moreover, qualitative analysis and a quantitative comparison based on a real robotic cell are provided. Several key findings and observations are generated relating to managerial implications, which are valuable for various users to make manufacturing decisions under the digital twin-driven environment.
- 10 June 2020
- Published by Taylor & Francis in International Journal of Computer Integrated Manufacturing
- Vol. 34 (7-8) , 844-859
A digital twin-driven approach towards smart manufacturing: reduced energy consumption for a robotic cell
One of the significant trends in smart manufacturing is the idea of industrial digitalization, which is enabled through the use of new information technologies, such as the Internet of Things, big data, cloud computing, and artificial intelligence. However, manufacturing industries can only be achieved by combining the physical manufacturing world and digital world, to realize a series of smart manufacturing activities, such as active perception, real-time interaction, automatic processing, intelligent control, and real-time optimization, etc. In this paper, a digital twin-driven approach combines with agent-based decision-making for real-time optimization of motion planning in robotic cellular is proposed, with optimizing the physical and virtual layer at the manufacturing facility. Accordingly, an architecture of the digital twin-driven facility is design, and its operational mechanisms and implementation methods are explained in detail. Moreover, qualitative analysis and a quantitative comparison based on a real robotic cell are provided. Several key findings and observations are generated relating to managerial implications, which are valuable for various users to make manufacturing decisions under the digital twin-driven environment.
- Top Cited PapersOpen Access
- 9 March 2020
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 17 (5) , 1784
A Content-Analysis Based Literature Review in Blockchain Adoption within Food Supply Chain
According to the World Health Organization (WHO), one out of 10 people get sick from eating contaminated food. Complex food production process and globalization make food supply chain more delicate. Many technologies have been investigated in recent years to address food insecurity and achieve efficiency in dealing with food recalls. One of the most promising technologies is Blockchain, which has already been used successfully in financial aspects, such as bitcoin, and it is attracting interests from food supply chain organizations. As blockchain has characteristics, such as decentralization, security, immutability, smart contract, it is therefore expected to improve sustainable food supply chain management and food traceability. This paper applies a content-analysis based literature review in blockchain adoption within food supply chain. We propose four benefits. Blockchain can help to improve food traceability, information transparency, and recall efficiency; it can also be combined with Internet of things (IoT) to achieve better efficiency. We also propose five potential challenges, including lack of deeper understanding of blockchain, technology difficulties, raw data manipulation, difficulties of getting all stakeholders on board, and the deficiency of regulations.
- 9 March 2020
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 17 (5) , 1784
Top Cited PapersOpen AccessA Content-Analysis Based Literature Review in Blockchain Adoption within Food Supply Chain
According to the World Health Organization (WHO), one out of 10 people get sick from eating contaminated food. Complex food production process and globalization make food supply chain more delicate. Many technologies have been investigated in recent years to address food insecurity and achieve efficiency in dealing with food recalls. One of the most promising technologies is Blockchain, which has already been used successfully in financial aspects, such as bitcoin, and it is attracting interests from food supply chain organizations. As blockchain has characteristics, such as decentralization, security, immutability, smart contract, it is therefore expected to improve sustainable food supply chain management and food traceability. This paper applies a content-analysis based literature review in blockchain adoption within food supply chain. We propose four benefits. Blockchain can help to improve food traceability, information transparency, and recall efficiency; it can also be combined with Internet of things (IoT) to achieve better efficiency. We also propose five potential challenges, including lack of deeper understanding of blockchain, technology difficulties, raw data manipulation, difficulties of getting all stakeholders on board, and the deficiency of regulations.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5299-5302
A New Word Discovery Method Based on Constrainted and DSG
Accurate identification of risk places is of great significance for risk identification, risk analysis, risk response planning and other work in risk areas. Therefore, we will combine the word formation features of risk place and statistical algorithms to discover new words in this paper. Firstly, we preprocess the data based on conditional random field (CRF), and develop a professional dictionary with the help of expert. Secondly, segment the test set, and form a set of new words to be selected based on segmentations and their left-right words. Finally, we make word vectors based on directional skip-gram (DSG), and calculate the distance between two words to discover new words. The results show that the algorithm can accurately identify new places, and it is suitable for discovering professional vocabulary which word-formation features is compound.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5299-5302
A New Word Discovery Method Based on Constrainted and DSG
Accurate identification of risk places is of great significance for risk identification, risk analysis, risk response planning and other work in risk areas. Therefore, we will combine the word formation features of risk place and statistical algorithms to discover new words in this paper. Firstly, we preprocess the data based on conditional random field (CRF), and develop a professional dictionary with the help of expert. Secondly, segment the test set, and form a set of new words to be selected based on segmentations and their left-right words. Finally, we make word vectors based on directional skip-gram (DSG), and calculate the distance between two words to discover new words. The results show that the algorithm can accurately identify new places, and it is suitable for discovering professional vocabulary which word-formation features is compound.