Ray zhong - Academia.edu (original) (raw)

articles by Ray zhong

Papers by Ray zhong

International Journal of Production Research

In the past decade, many organisations have become much more conscious of sustainability with inn... more In the past decade, many organisations have become much more conscious of sustainability with innovation in their manufacturing and supply chain management (Kusi-Sarpong, Gupta, and Sarkis 2019). T...

The 19th International Conference on Industrial Engineering and Engineering Management

Lead time estimation (LTE) is difficult to carry out, especially within the RFID-enabled real-tim... more Lead time estimation (LTE) is difficult to carry out, especially within the RFID-enabled real-time manufacturing shopfloor environment since large number of factors may greatly affect its precision. This paper proposes a data mining approach with four steps each of which is equipped with suitable mathematical models to analysis the LTE from a real-life case and then to quantitatively examine its key impact factors such as processing routine, batching strategy, scheduling rules and critical parameters of specification. Experiments are carried out for this purpose and results imply that batching strategy, scheduling rules and two specification parameters largely influence the LTE, while, processing routine has less impact in this case. Keywords Data mining Á Lead time Á Radio frequency identification (RFID) Á Real-time Á Shopfloor production 33.1 Introduction Lead time estimation (LTE) is significant since it exclusively influences customer relations and shopfloor management practices (Alexander 1980). The direct outcome of LTE is due data quoting which indicates the commitment to meet

The International Journal of Advanced Manufacturing Technology

Peculiar characteristics of squeeze casted hybrid aluminum matrix composites (AMCs) enable it as ... more Peculiar characteristics of squeeze casted hybrid aluminum matrix composites (AMCs) enable it as an appropriate candidate for various manufacturing applications but also make their machining challenging. For that reason, wire electric discharge machining (WEDM) has been preferred over conventional machining processes for the cutting squeeze casted Al2024/Al 2 O 3 /W hybrid composite in this study. The presence of nanoparticles in the material affects the machining performance of wire electrodes. Therefore, molybdenum and zinc-coated wires have been chosen, and cryogenic treatment has been applied to improve their machining performance. To analyze the effects of cryogenic treatment, the machining efficiency of cryogenic treated (CT) wire has been compared with non-treated (NT) wire. Besides wire type, four key input variables including pulse duration (T ON), wire feed rate (F R), wire runoff speed (S W), and wire tension (T W) have also been optimized to improve the imperative response measures including cutting speed (CS), surface roughness (SR), and kerf width (KW). Microstructural analysis of NT wire depicts a high concentration of micro-voids, micro-cracks, and deep craters, while the surface of CT wire has been observed relatively fine after the machining. Comparative analysis of both wire electrodes has declared that CT wire yields 26.96% and 15.10% superior results for CS and SR respectively, and 6.92% deprived results for KW than NT wire. Grey relational analysis (GRA) has been practiced for multi-objective optimization and presented T ON = 3 μs, F R = 13 m/min, S W = 11 m/min, and T W = 10 g as an optimal set of input variables to achieve 75.1% and 72.5% overall results with NT and CT wire, respectively.

2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom), 2015

This paper proposes a job-shop scheduling model which converts the real-time captured data as fee... more This paper proposes a job-shop scheduling model which converts the real-time captured data as feedbacks into the model for more precise and reasonable decision-makings. The experiment shows that, from practice implementations, the proposed model is able to achieve good performance though comparing the concerned WIP inventory, Production Cycle, and Product Ratio from the case company. The lessons and key findings are converted into managerial implications for supporting decisions in PI-enabled production shop floors.

The inherent complexity and uncertainty of planning and scheduling problems in production managem... more The inherent complexity and uncertainty of planning and scheduling problems in production management have plagued researchers and practitioners for decades, especially when confronted with more diversified customer demand, fast-changing supply chain and market. Physical Internet (PI) enabled manufacturing shows the potential to revolutionize the way production and operations are managed and done in factories. Massive production data and information are real-timely accessible for decision-makers thanks to the application of various frontier sensing, networking, and computing technologies in PI. Thus, it is imperative to study how to leverage the strengths of real-time data and information to support production planning and scheduling in PI-enabled manufacturing environment. This paper proposes a fivephase framework of the Graduation Intelligent Manufacturing System (GiMS) to facilitate decision-making in the PI-enabled fixed-position assembly islands. GiMS divides space and time scop...

Logistics sustainability plays a critical role in our daily life since logistics involves in larg... more Logistics sustainability plays a critical role in our daily life since logistics involves in large number of resources such as manpower, transportation vehicles, warehouses, and products which should be sustainably leveraged. One possible way to achieve the sustainability is to make the coordinated development of logistics and economy. Due to the complexity of the logistics industry, better coordination among all relevant parties are challenging. The purpose of this research is to analyze the key factors on the coordinated development between metropolitan economy and logistics. This paper uses a Bayesian Network to examine their impacts. Several contributions are significant. Firstly, it is observed that the coordinated development of metropolitan economy and logistics heavily relies on their development levels as their posterior probability values are both over 80%. Secondly, two causation chains greatly affected the coordinated development are found. Scientific value of this resea...

Computers & Industrial Engineering, 2012

This research is motivated by a practical fastener company which is a supplier for most major aut... more This research is motivated by a practical fastener company which is a supplier for most major automobile factories in China. Each month it receives more than 150 new orders, including 4000+ kinds of fasteners, and the production volume usually keeps in billion-level. As the managers suffer from the bottleneck of collecting the real-time shop-floor information, it is difficult to evaluate the available machine capacity, estimate the latest start time, and release appropriate amount of production orders. This paper presents a real-life case study to describe how to implement Auto-ID technology on a manufacturing shop-floor and use the collected real-time information to support decision-making processes. Meanwhile, the lessons like how to institutionalize a project team, how to defuse the resistance from the personnel will be discussed. We hope the experiences and insights learned from this project can be shared with other fastener manufacturers which are contemplating to adopt Auto-ID...

International Journal of Production Economics

2020 IEEE 18th International Conference on Industrial Informatics (INDIN), 2020

Aiming to improve the adaptability of fabric defect detection, this paper proposes an “edge-cloud... more Aiming to improve the adaptability of fabric defect detection, this paper proposes an “edge-cloud” collaborative fabric defect detection architecture that contains edge layer, platform layer, and application layer. In the edge layer, the fabric defect detection machine is able to realize the collection and detection of fabric images data. In the platform layer, the cloud platform that integrates memory computing, parallel storage, and a relational library is designed to realize the efficient storage and analysis of fabric data. In the application layer, a deep learning fabric defect detection algorithm is designed to recognize the defect patterns. The interaction between the cloud platform and the detection device is designed to adaptively adjust the detection algorithm. The closed-loop optimization is achieved by implementing “edge-cloud” architecture that the fabric pictures are captured and analyzed for fast detection algorithm in edge devices. The captured data is stored and mon...

2018 World Symposium on Digital Intelligence for Systems and Machines (DISA)

One of the main characteristics of Industry 4.0 is the impact of technology as an accelerant or c... more One of the main characteristics of Industry 4.0 is the impact of technology as an accelerant or catalyst that allows individualized solutions, flexibility and cost savings in industrial processes. Manufacturing companies will require considering various technologies including Internet of Things (IoT) and analytics platforms, enterprise resource planning systems, requirements for edge processing and cloud storage. While understanding the potential of these modern notions, manufacturing organizations experience severe challenges in bringing ideas down to the shop floor. Results of various studies indicate that there is an increasing demand for technology selection approach for guided support in developing an organization-specific Industry 4.0 vision and roadmap. This paper proposes a decision-making framework for manufacturing technology selection by incorporating technological, social and business considerations in a single loop.

Supply Hub in Industrial Park (SHIP) is a public depot which provides shared warehouses and fleet... more Supply Hub in Industrial Park (SHIP) is a public depot which provides shared warehouses and fleets for enterprises to reduce their logistics costs through economy of scale. SHIP normally adopts milk-run logistics for material collection and distribution. Instead of once processing a full order, smaller-lot orders from multiple suppliers/manufacturers are mixed and fulfilled in a milk-run round. Milk runs go in parallel with the production processes of all manufacturers, cutting down the shop-floor stocks. However, such lean logistics is subject to failure if production dynamics cannot be timely and accurately considered in arranging the milk-run resources and routes. This paper introduces a RFID-based small-lot and high-frequency JIT production logistics management system . Real-time materials outputs and consumptions are captured by RFID-enabled manufacturing execution systems deployed at both suppliers and manufacturers, generating adaptive materials collection and distribution or...

In typical enterprises quipped with RFID technology, different manufacturing parties are facing c... more In typical enterprises quipped with RFID technology, different manufacturing parties are facing challenges when collaboratively making decisions such as conflicting objectives as well as gaps between high-synchronized information flow and unstandardized decision-making procedures. In order to facilitate different parties’ decision-making behaviors, for example planning, scheduling and execution bodies, this paper introduces an RFID-enabled real-time advanced planning and scheduling shell (RAPShell in short) to enable real-time coordinate with each other. In RAPShell, customer orders are converted into production order in planning level, then scheduled in scheduling level and finally carried out in execution level. It uses RFID technology in execution level to real-time capture the production data, which are fed back to scheduling level for real-time rescheduling and finally to meet the constrains set in planning level. That forms a closed-loop within the entire manufacturing environ...

Industrial Management & Data Systems

PurposeThe purpose of this paper is to develop an intelligent manufacturing system for transformi... more PurposeThe purpose of this paper is to develop an intelligent manufacturing system for transforming production management and operations to an Industry 4.0 manufacturing paradigm.Design/methodology/approachA manufacturing mode-Graduation Manufacturing System is designed for organizing and controlling production operations. An Industrial Internet of Things (IIoT) and digital twin-enabled Graduation Intelligent Manufacturing System (GiMS) with real-time task allocation and execution mechanisms is proposed to achieve real-time information sharing and production planning, scheduling, execution and control with reduced complexity and uncertainty.FindingsThe implementation of GiMS in an industrial company illustrates the potential advantages for real-time production planning, scheduling, execution and control with reduced complexity and uncertainty. For production managers and onsite operators, effective tools, such as cloud services integrates effective production and operations manageme...

Journal of Manufacturing Systems

IEEE Transactions on Industrial Informatics

Object segmentation for 3-D point clouds plays a critical role in autonomous driving, robotic nav... more Object segmentation for 3-D point clouds plays a critical role in autonomous driving, robotic navigation, and other computer version applications. In object segmentation, all points are considered to be equal of importance in the literature. However, unequal cases exist and a segmentation boundary is mainly determined by neighbor points. To investigate point inequivalence, in this article, an unequal learning approach is proposed to integrate gene expression programming (GEP) and a deep neural network (DNN). GEP is designed to discover the inequivalent function, which measures the importance of different points according to the distances to the segmentation boundary. A cost sensitive learning method is improved to guide the DNN to obtain the loss of different points unequally with the discovered inequivalent function during model training. The experimental results reveal that point inequivalence with respect to boundary distance exists and is helpful to improve the accuracy of object segmentation.

Industrial Management & Data Systems

PurposeThis paper proposes an evaluation model for prefabricated construction to guide a supply c... more PurposeThis paper proposes an evaluation model for prefabricated construction to guide a supply chain with controllable costs. Prefabricated construction is prevalent due to area limitations. Nevertheless, the development is limited by budget control and identifying the factors affecting cost. The degree of close collaboration in the supply chain is closely interconnected with cost performance that includes direct and indirect factors. This paper not only quantizes these factors but also distinguishes the degree of influence of various factors.Design/methodology/approachSystem dynamics is applied to simulate and analyze the construction cost factors through Vensim software. It can also clarify the relationship between cost and other influencing factors. The input data are collected from an Internet of Things (IoT)-enabled system under a Building Information Modeling (BIM) system and Hong Kong government reports.FindingsSimulation results indicate that prefabricated construction cost...

Micromachines

Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in... more Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in manufacturing industry, is a nontraditional machining method using discharge energy which is transformed into thermal energy to efficiently remove materials. A great amount of research has been conducted based on pulse characteristics. However, the spark image-based approach has little research reported. This paper proposes a discharge spark image-based approach. A model is introduced to predict the discharge status using spark image features through a synchronous high-speed image and waveform acquisition system. First, the relationship between the spark image features (e.g., area, energy, energy density, distribution, etc.) and discharge status is explored by a set of experiments). Traditional methods have claimed that pulse waveform of “short” status is related to the status of non-machining while through our research, it is concluded that this is not always true by conducting experim...

International Journal of Production Research

In the past decade, many organisations have become much more conscious of sustainability with inn... more In the past decade, many organisations have become much more conscious of sustainability with innovation in their manufacturing and supply chain management (Kusi-Sarpong, Gupta, and Sarkis 2019). T...

The 19th International Conference on Industrial Engineering and Engineering Management

Lead time estimation (LTE) is difficult to carry out, especially within the RFID-enabled real-tim... more Lead time estimation (LTE) is difficult to carry out, especially within the RFID-enabled real-time manufacturing shopfloor environment since large number of factors may greatly affect its precision. This paper proposes a data mining approach with four steps each of which is equipped with suitable mathematical models to analysis the LTE from a real-life case and then to quantitatively examine its key impact factors such as processing routine, batching strategy, scheduling rules and critical parameters of specification. Experiments are carried out for this purpose and results imply that batching strategy, scheduling rules and two specification parameters largely influence the LTE, while, processing routine has less impact in this case. Keywords Data mining Á Lead time Á Radio frequency identification (RFID) Á Real-time Á Shopfloor production 33.1 Introduction Lead time estimation (LTE) is significant since it exclusively influences customer relations and shopfloor management practices (Alexander 1980). The direct outcome of LTE is due data quoting which indicates the commitment to meet

The International Journal of Advanced Manufacturing Technology

Peculiar characteristics of squeeze casted hybrid aluminum matrix composites (AMCs) enable it as ... more Peculiar characteristics of squeeze casted hybrid aluminum matrix composites (AMCs) enable it as an appropriate candidate for various manufacturing applications but also make their machining challenging. For that reason, wire electric discharge machining (WEDM) has been preferred over conventional machining processes for the cutting squeeze casted Al2024/Al 2 O 3 /W hybrid composite in this study. The presence of nanoparticles in the material affects the machining performance of wire electrodes. Therefore, molybdenum and zinc-coated wires have been chosen, and cryogenic treatment has been applied to improve their machining performance. To analyze the effects of cryogenic treatment, the machining efficiency of cryogenic treated (CT) wire has been compared with non-treated (NT) wire. Besides wire type, four key input variables including pulse duration (T ON), wire feed rate (F R), wire runoff speed (S W), and wire tension (T W) have also been optimized to improve the imperative response measures including cutting speed (CS), surface roughness (SR), and kerf width (KW). Microstructural analysis of NT wire depicts a high concentration of micro-voids, micro-cracks, and deep craters, while the surface of CT wire has been observed relatively fine after the machining. Comparative analysis of both wire electrodes has declared that CT wire yields 26.96% and 15.10% superior results for CS and SR respectively, and 6.92% deprived results for KW than NT wire. Grey relational analysis (GRA) has been practiced for multi-objective optimization and presented T ON = 3 μs, F R = 13 m/min, S W = 11 m/min, and T W = 10 g as an optimal set of input variables to achieve 75.1% and 72.5% overall results with NT and CT wire, respectively.

2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom), 2015

This paper proposes a job-shop scheduling model which converts the real-time captured data as fee... more This paper proposes a job-shop scheduling model which converts the real-time captured data as feedbacks into the model for more precise and reasonable decision-makings. The experiment shows that, from practice implementations, the proposed model is able to achieve good performance though comparing the concerned WIP inventory, Production Cycle, and Product Ratio from the case company. The lessons and key findings are converted into managerial implications for supporting decisions in PI-enabled production shop floors.

The inherent complexity and uncertainty of planning and scheduling problems in production managem... more The inherent complexity and uncertainty of planning and scheduling problems in production management have plagued researchers and practitioners for decades, especially when confronted with more diversified customer demand, fast-changing supply chain and market. Physical Internet (PI) enabled manufacturing shows the potential to revolutionize the way production and operations are managed and done in factories. Massive production data and information are real-timely accessible for decision-makers thanks to the application of various frontier sensing, networking, and computing technologies in PI. Thus, it is imperative to study how to leverage the strengths of real-time data and information to support production planning and scheduling in PI-enabled manufacturing environment. This paper proposes a fivephase framework of the Graduation Intelligent Manufacturing System (GiMS) to facilitate decision-making in the PI-enabled fixed-position assembly islands. GiMS divides space and time scop...

Logistics sustainability plays a critical role in our daily life since logistics involves in larg... more Logistics sustainability plays a critical role in our daily life since logistics involves in large number of resources such as manpower, transportation vehicles, warehouses, and products which should be sustainably leveraged. One possible way to achieve the sustainability is to make the coordinated development of logistics and economy. Due to the complexity of the logistics industry, better coordination among all relevant parties are challenging. The purpose of this research is to analyze the key factors on the coordinated development between metropolitan economy and logistics. This paper uses a Bayesian Network to examine their impacts. Several contributions are significant. Firstly, it is observed that the coordinated development of metropolitan economy and logistics heavily relies on their development levels as their posterior probability values are both over 80%. Secondly, two causation chains greatly affected the coordinated development are found. Scientific value of this resea...

Computers & Industrial Engineering, 2012

This research is motivated by a practical fastener company which is a supplier for most major aut... more This research is motivated by a practical fastener company which is a supplier for most major automobile factories in China. Each month it receives more than 150 new orders, including 4000+ kinds of fasteners, and the production volume usually keeps in billion-level. As the managers suffer from the bottleneck of collecting the real-time shop-floor information, it is difficult to evaluate the available machine capacity, estimate the latest start time, and release appropriate amount of production orders. This paper presents a real-life case study to describe how to implement Auto-ID technology on a manufacturing shop-floor and use the collected real-time information to support decision-making processes. Meanwhile, the lessons like how to institutionalize a project team, how to defuse the resistance from the personnel will be discussed. We hope the experiences and insights learned from this project can be shared with other fastener manufacturers which are contemplating to adopt Auto-ID...

International Journal of Production Economics

2020 IEEE 18th International Conference on Industrial Informatics (INDIN), 2020

Aiming to improve the adaptability of fabric defect detection, this paper proposes an “edge-cloud... more Aiming to improve the adaptability of fabric defect detection, this paper proposes an “edge-cloud” collaborative fabric defect detection architecture that contains edge layer, platform layer, and application layer. In the edge layer, the fabric defect detection machine is able to realize the collection and detection of fabric images data. In the platform layer, the cloud platform that integrates memory computing, parallel storage, and a relational library is designed to realize the efficient storage and analysis of fabric data. In the application layer, a deep learning fabric defect detection algorithm is designed to recognize the defect patterns. The interaction between the cloud platform and the detection device is designed to adaptively adjust the detection algorithm. The closed-loop optimization is achieved by implementing “edge-cloud” architecture that the fabric pictures are captured and analyzed for fast detection algorithm in edge devices. The captured data is stored and mon...

2018 World Symposium on Digital Intelligence for Systems and Machines (DISA)

One of the main characteristics of Industry 4.0 is the impact of technology as an accelerant or c... more One of the main characteristics of Industry 4.0 is the impact of technology as an accelerant or catalyst that allows individualized solutions, flexibility and cost savings in industrial processes. Manufacturing companies will require considering various technologies including Internet of Things (IoT) and analytics platforms, enterprise resource planning systems, requirements for edge processing and cloud storage. While understanding the potential of these modern notions, manufacturing organizations experience severe challenges in bringing ideas down to the shop floor. Results of various studies indicate that there is an increasing demand for technology selection approach for guided support in developing an organization-specific Industry 4.0 vision and roadmap. This paper proposes a decision-making framework for manufacturing technology selection by incorporating technological, social and business considerations in a single loop.

Supply Hub in Industrial Park (SHIP) is a public depot which provides shared warehouses and fleet... more Supply Hub in Industrial Park (SHIP) is a public depot which provides shared warehouses and fleets for enterprises to reduce their logistics costs through economy of scale. SHIP normally adopts milk-run logistics for material collection and distribution. Instead of once processing a full order, smaller-lot orders from multiple suppliers/manufacturers are mixed and fulfilled in a milk-run round. Milk runs go in parallel with the production processes of all manufacturers, cutting down the shop-floor stocks. However, such lean logistics is subject to failure if production dynamics cannot be timely and accurately considered in arranging the milk-run resources and routes. This paper introduces a RFID-based small-lot and high-frequency JIT production logistics management system . Real-time materials outputs and consumptions are captured by RFID-enabled manufacturing execution systems deployed at both suppliers and manufacturers, generating adaptive materials collection and distribution or...

In typical enterprises quipped with RFID technology, different manufacturing parties are facing c... more In typical enterprises quipped with RFID technology, different manufacturing parties are facing challenges when collaboratively making decisions such as conflicting objectives as well as gaps between high-synchronized information flow and unstandardized decision-making procedures. In order to facilitate different parties’ decision-making behaviors, for example planning, scheduling and execution bodies, this paper introduces an RFID-enabled real-time advanced planning and scheduling shell (RAPShell in short) to enable real-time coordinate with each other. In RAPShell, customer orders are converted into production order in planning level, then scheduled in scheduling level and finally carried out in execution level. It uses RFID technology in execution level to real-time capture the production data, which are fed back to scheduling level for real-time rescheduling and finally to meet the constrains set in planning level. That forms a closed-loop within the entire manufacturing environ...

Industrial Management & Data Systems

PurposeThe purpose of this paper is to develop an intelligent manufacturing system for transformi... more PurposeThe purpose of this paper is to develop an intelligent manufacturing system for transforming production management and operations to an Industry 4.0 manufacturing paradigm.Design/methodology/approachA manufacturing mode-Graduation Manufacturing System is designed for organizing and controlling production operations. An Industrial Internet of Things (IIoT) and digital twin-enabled Graduation Intelligent Manufacturing System (GiMS) with real-time task allocation and execution mechanisms is proposed to achieve real-time information sharing and production planning, scheduling, execution and control with reduced complexity and uncertainty.FindingsThe implementation of GiMS in an industrial company illustrates the potential advantages for real-time production planning, scheduling, execution and control with reduced complexity and uncertainty. For production managers and onsite operators, effective tools, such as cloud services integrates effective production and operations manageme...

Journal of Manufacturing Systems

IEEE Transactions on Industrial Informatics

Object segmentation for 3-D point clouds plays a critical role in autonomous driving, robotic nav... more Object segmentation for 3-D point clouds plays a critical role in autonomous driving, robotic navigation, and other computer version applications. In object segmentation, all points are considered to be equal of importance in the literature. However, unequal cases exist and a segmentation boundary is mainly determined by neighbor points. To investigate point inequivalence, in this article, an unequal learning approach is proposed to integrate gene expression programming (GEP) and a deep neural network (DNN). GEP is designed to discover the inequivalent function, which measures the importance of different points according to the distances to the segmentation boundary. A cost sensitive learning method is improved to guide the DNN to obtain the loss of different points unequally with the discovered inequivalent function during model training. The experimental results reveal that point inequivalence with respect to boundary distance exists and is helpful to improve the accuracy of object segmentation.

Industrial Management & Data Systems

PurposeThis paper proposes an evaluation model for prefabricated construction to guide a supply c... more PurposeThis paper proposes an evaluation model for prefabricated construction to guide a supply chain with controllable costs. Prefabricated construction is prevalent due to area limitations. Nevertheless, the development is limited by budget control and identifying the factors affecting cost. The degree of close collaboration in the supply chain is closely interconnected with cost performance that includes direct and indirect factors. This paper not only quantizes these factors but also distinguishes the degree of influence of various factors.Design/methodology/approachSystem dynamics is applied to simulate and analyze the construction cost factors through Vensim software. It can also clarify the relationship between cost and other influencing factors. The input data are collected from an Internet of Things (IoT)-enabled system under a Building Information Modeling (BIM) system and Hong Kong government reports.FindingsSimulation results indicate that prefabricated construction cost...

Micromachines

Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in... more Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in manufacturing industry, is a nontraditional machining method using discharge energy which is transformed into thermal energy to efficiently remove materials. A great amount of research has been conducted based on pulse characteristics. However, the spark image-based approach has little research reported. This paper proposes a discharge spark image-based approach. A model is introduced to predict the discharge status using spark image features through a synchronous high-speed image and waveform acquisition system. First, the relationship between the spark image features (e.g., area, energy, energy density, distribution, etc.) and discharge status is explored by a set of experiments). Traditional methods have claimed that pulse waveform of “short” status is related to the status of non-machining while through our research, it is concluded that this is not always true by conducting experim...

Advanced Engineering Informatics