Geok-Soon Hong

Geok-Soon Hong
National University of Singapore | NUS · Department of Mechanical Engineering

About

164
Publications
34,363
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,311
Citations
Additional affiliations
July 1987 - present
National University of Singapore
Position
  • Professor (Associate)

Publications

Publications (164)
Article
Purpose This study aims to develop a data fusion method for powder-bed fusion (PBF) process monitoring based on process image information. The data fusion method can help improve process condition identification performance, which can provide guidance for further PBF process monitoring and control system development. Design/methodology/approach De...
Article
Battery/Ultracapacitor (UC) Hybrid Energy Storage Systems (HESS) for Electric Vehicles (EVs) have been frequently proposed in the literature to increase battery cycle life. The HESS consists of a Power Management Strategy (PMS) and an Energy Management Strategy (EMS). Existing EMS are quite empirical, such as setting constant target UC energy level...
Article
A method of hybrid convolutional neural networks (CNNs) was proposed for powder-bed fusion (PBF) process monitoring in this work. The proposed method can learn both the spatial and temporal representative features from the raw images automatically based on the advantages of the CNN architecture. The results demonstrated the superior performance of...
Article
Full-text available
3D printing and particularly fused deposition modelling (FDM) is widely used for prototyping and fabricating low-cost customised parts. However, present fused deposition modelling 3D printers have limited nozzle condition monitoring techniques to minimize nozzle clogging errors. Nozzle clogging is one of the significant process errors in fused depo...
Article
3D printing and particularly fused filament fabrication is widely used for prototyping and fabricating low-cost customized parts. However, current fused filament fabrication 3D printers have limited nozzle condition monitoring techniques to minimize nozzle clogging errors. Nozzle clogging is one of the most significant process errors in current fus...
Article
Full-text available
Defects among the selective laser melting(SLM) part hinder the development of the SLM process. This work provides an approach to conduct the monitoring and defect diagnosis by support vector machines (SVM) model using extracted features from acoustic signals. After training and testing with the linear SVM model, the result from the Fisher discrimin...
Article
A strategy to improve industrial finishing applications using commercial robotic arms is presented in this paper. An end-effector is designed and prototyped as the mini manipulator, and is mounted at the end-point of a commercial robotic arm to form a macro-mini manipulator system. The developed end-effector has properties of fast response and high...
Article
With the development of powder bed fusion (PBF) additive manufacturing technique for functional parts production, process monitoring and diagnosis is highly demanded to ensure its process reliability and repeatability. An off-axis vision monitoring method using high-speed camera is proposed in this paper. An optical filter with 350 nm–800 nm cut-of...
Article
The automation of the polishing process is essential to improve the production efficiency and the quality of the part surfaces. The control strategy, which involves the position/force control, is a big bottleneck for the automated polishing process. This paper focuses on the precise control of the pneumatic force in polishing. Firstly, a position/f...
Conference Paper
Tool condition monitoring (TCM) is prerequisite to ensure high finishing quality of workpiece in manufacturing automation. One of the most important parts of TCM is tool wear estimation. How to achieve high accurate estimation is still an open question. In the past few decades, recurrent neural network (RNN) has shown a great success in learning lo...
Article
With the continuous development of additive manufacturing technique, the issue on built quality has caught increasing attentions. To improve the quality of built parts, the process monitoring and control has been emphasized as a promising solution. Despite a large number of studies on the development of sensors and instrumentations, the investigati...
Article
Full-text available
Critical quality issues such as high porosity, cracks, and delamination are common in current selective laser melting (SLM) manufactured components. This study provides a flexible and integrated method for in situ process monitoring and melted state recognition during the SLM process, and it is useful for process optimization to decrease part quali...
Article
Full-text available
Selective laser melting (SLM) is one of the most important and successfully additive manufacturing processes in 3D metal printing technologies. Critical quality issues such as porosity, surface roughness, crack, and delamination continue to present challenges within SLM-manufactured parts. Monitoring and in-process defect diagnosis are the key to i...
Preprint
Full-text available
In this paper, a multi-state diagnosis and prognosis (MDP) framework is proposed for tool condition monitoring via a deep belief network based multi-state approach (DBNMS). For fault diagnosis, a cost-sensitive deep belief network (namely ECS-DBN) is applied to deal with the imbalanced data problem for tool state estimation. An appropriate prognost...
Preprint
Full-text available
Imbalanced data with a skewed class distribution are common in many real-world applications. Deep Belief Network (DBN) is a machine learning technique that is effective in classification tasks. However, conventional DBN does not work well for imbalanced data classification because it assumes equal costs for each class. To deal with this problem, co...
Article
Imbalanced data with a skewed class distribution are common in many real-world applications. Deep Belief Network (DBN) is a machine learning technique that is effective in classification tasks. However, conventional DBN does not work well for imbalanced data classification because it assumes equal costs for each class. To deal with this problem, co...
Article
Purpose Fused deposition modelling (FDM) is one of the most popular additive manufacturing processes, and is widely used for prototyping and fabricating low-cost customized parts. Current FDM machines have limited techniques to monitor process conditions to minimize process errors, such as nozzle clogging. Nozzle clogging is one of the most signif...
Conference Paper
In force control applications where a robot end-effector is required to interact with the environment or the workpiece, the dynamic of the environment plays an important role. The environment dynamic may influence the performance of the controlled system, especially the performance in transient period. In order to avoid tuning the controller consta...
Conference Paper
A parallel mechanism has advantages such as high stiffness, low inertia and compact in size. It is a desired mechanical structure to be used as the mini manipulator in a macro-mini manipulator system. In this paper, a 3-DOF parallel mechanism is presented. The end-effector module will serve as the mini manipulator in a macro-mini system for in-cont...
Conference Paper
Battery/Ultracapacitor (UC) Hybrid Energy Storage Systems for Electric Vehicles have been proposed to increase battery cycle life and driving range. Existing works focus on power management strategies of the battery and UC, while energy management strategies are still relatively empirical. We propose a more rigorous method of setting the target UC...
Article
Full-text available
In the micro-electro discharge machining (micro-EDM) process the machined surface consists of tiny overlapping craters. The shape of the crater has significant influence on the characteristics of the machined surface. However, existing models on crater shapes generally do not represent characteristic features of the craters, such as the bulging rim...
Article
Full-text available
This study introduces the first generation food printer concept designs and workable prototypes that target to revolutionize customized food fabrication by 3D printing (3DP). Different from robotics-based food manufacturing technologies designed to automate manual processes for mass production, 3D food printing integrates 3DP and digital gastronomy...
Conference Paper
Ball nose milling is most commonly used in computer-controlled sculpture surface machining using computer numerical control (CNC) machines. Tool condition monitoring (TCM) for the ball nose milling by CNC machines will significantly improve machining efficiency, minimize inaccuracy, minimize machine down time, and maximize tool life utilization. Ce...
Chapter
Rapid prototyping or referred as layered manufacturing has been widely used in fabricating 3D components from CAD data. It has evolved from liquid, plastic, powder to metal-based systems in the past two decades. Recently, 3D printing using polymeric material has caught much attention in many industry applications including in micro- and bio-fabrica...
Article
Different from robotics-based food manufacturing, three-dimensional (3D) food printing integrates 3D printing and digital gastronomy to revolutionize food manufacturing with customized shape, color, flavor, texture, and even nutrition. Hence, food products can be designed and fabricated to meet individual needs through controlling the amount of pri...
Conference Paper
In recent years, open architecture motion controllers, including those for CNC machines and robots, have received much interest and support among the global control and automation community. This paper presents work done in extending a well-known and supported open-source control software called LinuxCNC for the control of a Delta robot, a translat...
Article
About 15-25% of aging population suffers from swallowing difficulties, and this creates an increasing market need for food mass customization. Food industry is investigating mass customization techniques to meet individual needs on taste, nutrition and mouthfeel. Three dimensional (3D) food printing is a potential solution to overcome drawbacks of...
Conference Paper
Mid-ranging control is an established control approach developed for systems with more than one manipulated inputs controlling a single target output. In this paper, the application of a mid-ranging control approach, Valve Position Control (VPC), in the control of a macro/mini manipulator is presented. The results from simulation studies show that...
Article
Among techniques used in condition monitoring, those for prognostics are the most challenging. This paper presents a Hidden Markov Model (HMM) based approach for prognostics in TCM. A HMM model usually employs a typical working condition for establishing and verifying the model. However, in tool condition monitoring (TCM), the cutting tool encounte...
Conference Paper
In the micro-electro discharge machining (micro EDM) process the machined surface consists of tiny overlapping craters. The shape of the crater has significant influence on the characteristics of the machined surface. However, existing models on crater shapes generally do not represent characteristic features of the craters, such as the bulging rim...
Article
Biodegradable polymeric scaffolds have been widely used in tissue engineering as a platform for cell proliferation and subsequent tissue regeneration. Conventional microextrusion methods for three-dimensional (3D) scaffold fabrication were limited by their low resolution. Electrospinning, a form of electrohydrodynamic (EHD) printing, is an attracti...
Article
This paper addresses the problem of material removal in free abrasive polishing (FAP) with the sub-aperture pad both theoretically and experimentally. The effects of some polishing conditions upon the material removal are analyzed, including not only the process parameters, which refer to the normal force, angular spindle velocity and angular feed...
Article
Tool condition monitoring (TCM) system serves as the link between the cutting tool condition and the maintenance decision. The recent prognostic system employs highly complex models, which might need long calculation time. This long calculation time is acceptable for machine health prognostics, as machines' maintenance interval is in the unit of mo...
Article
In most of our daily motion tasks, the coordination between limbs is very crucial for successful execution of the tasks. In this paper, coordination among oscillators controlling in Cartesian space is studied to control bipedal walking. In our method, phase adjustment among oscillators is considered as one of the key issues to achieve coordination....
Article
The deterministic polishing process is usually used as the final step to produce part surfaces of high surface finish and form accuracy. This article presents the models of the local and the global polished profiles for the deterministic polishing process when a surface is polished by a spherical polisher. The local polished profile is modeled by i...
Article
Closed-loop insulin delivery systems often implement glucose measurement and insulin administration in the subcutis. However some existing models for glucose-insulin system ignored the dynamics of subcutaneous glucose and subcutaneously-injected insulin. This paper reports a two-compartment model that includes glucose and insulin dynamics in subcut...
Chapter
Full-text available
This paper reports our investigation on a model predictive control (MPC) with constraints for continuous diabetes management, and its implementation on the microcontroller of our artificial pancreas. The operational constraints for the MPC are rate of change, amplitude and output constraints, while the associated optimization problem is solved usin...
Chapter
Signal processing plays an important role in manufacturing automation and industrial control. In CNC machining, by utilising the monitored information from the platform to direct the further actions, the signal processing bridges the gap of human instruction and full automation. One of the main problems related to CNC machining productivity and saf...
Article
Fast tool servo (FTS) diamond turning is a promising machining process for fabricating ultra-precision micro-structured surfaces which have already gained wide application especially in the optics industry. However, most research focused on designing different types of FTSs for better performance, including bandwidth, stroke, stiffness, acceleratio...
Article
Bio-inspired composite coating, which resembles the unique nano-structured composite bone tissue, is greatly needed in biomedical implant applications. The target of this coating is to create a continuous transition from tissue to implant surface, and modulate the biological response between the implant and host tissue. Our study on this bio-inspir...
Article
Due to the rapid wear of the cutting tools when machining titanium alloy, tool condition monitoring (TCM) is most useful to avoid workpiece damage and maximise machining productivity. This paper uses sensor signals and feature analysis to identify a feature set for effective TCM. Firstly, basic requirements of sensor signals in tool condition ident...
Article
Hydroxyapatite (HA) and titanium oxide (TiO2) suspensions were utilized to fabricate the functionally graded coating via the Drop-on-Demand (DOD) micro-dispensing technique. A three-layered structure was formed, with a bottom 100% TiO2 layer, an intermediate layer consisting of 50% TiO2 and 50% HA, and a top 100% HA layer. The coating was then subj...
Article
It is known now that the dynamics of the motor drives of mechanical manipulators is of utmost importance and it is necessary to take this into account in achieving high control performance. At the same time, it is also known that the cross-coupled motor-manipulator dynamics is more complex and hence more difficult to be controlled than when only th...
Article
nanohydroxyapatite (nHA) and collagen were utilized to fabricate the bio-inspired organic-inorganic composite coating (OICC) via the Drop-on-Demand (DoD) micro-dispensing technique, which could flexibly construct multi-layer structures with varied materials composition within a layer and /or among layers reliably. This technique has been further in...
Article
Micro-structured surfaces on brittle materials, e.g. ceramic and glass, are gaining increasing application in a range of areas. In this paper, fast tool servo (FTS) diamond turning has been applied to machine micro-structured surfaces on brittle materials and the machined surfaces has been observed to study its machining mechanism. A machining mode...
Conference Paper
Full-text available
This paper presents a study of the sparking process of micro WEDM and its influence on the wire motion and the workpiece surface. A model is developed to describe the wire vibration under the influence of sparks and spark locations and its influence on the material removal on the workpiece surface. The spark location is determined by the gap distan...
Article
There is increasing use of ultra-precision components with micro-structured surfaces in a range of areas such as optical, biological, medical, metrology artifacts and data storage. Fast tool servo (FTS) diamond turning is superior in machining precision and complicated micro-structured surfaces with wavelength above tens of microns. However, the co...
Article
Full-text available
Micro-structured surfaces on brittle materials, e.g. ceramic and glass, are gaining increasing industrial applications such as optics, semiconductor and biomedical. However, these materials tend to be damaged with brittle fracture in machining. To generate crack-free surfaces, ductile-regime machining should be maintained for the entire micro-struc...
Article
Ultraprecision machined components with micro-structured surfaces in micrometer or nanometer range have gained wide applications especially in optical industry. A technique called fast tool servo (FTS) diamond turning is superior in fabricating precision and complicated micro-structured surfaces with wavelength above tens of microns. However, in or...
Conference Paper
The kernel problem of modular dynamic modeling of autonomous underwater vehicle (AUV) which is the modularization of the hydrodynamic coefficients of the hull is studied in this paper. The hydrodynamic coefficients of the hull are transformed from the lift axis system into the normal-force axis system, where they satisfy the superposition property...
Article
Ultraprecision micro-structured functional surfaces on hard and brittle materials, e.g. ceramic and glass, are gaining increasing application in a range of areas such as engineering optics and semiconductor and biomedical products. However, due to their tendency of being damaged in brittle fracture in machining, it is challenging to achieve both a...
Article
This paper introduces a novel approach for tool condition monitoring (TCM) in micromilling, which is based on the analysis of singularity of cutting force waveforms and the statistical distribution of the singularity measure. It is a multiscale approach with both localized and global cutting force analyses. The local singularity characteristics of...
Article
In this paper, a new model-based Taylor series expansion error compensation (TSEEC) strategy is proposed to improve the contouring accuracy for computer numerically controlled (CNC) machines. In TSEEC, the contour error compensation problem is formulated as a Taylor series expansion problem, in which the value of the contour error is expanded aroun...
Article
In artificial pancreas, glucose level measurement and insulin infusion are often implemented in the subcutaneous tissues. Understanding the dynamics of glucose and insulin in the subcutaneous tissues is important in the regulation of blood glucose level. We propose a new two-compartmental model of glucose-insulin interaction with two explicit delay...
Article
Fast Tool Servo (FTS) diamond turning is a promising machining process for fabricating high precision micro-structured surfaces. However, the dynamics of FTS affects its performance and causes form error in the machined surfaces, thus shortening the useful bandwidth of the FTS for precision machining. In this paper, an Integral Sliding Mode Control...
Article
Full-text available
Ultra-precision micro-structured surfaces are becoming increasingly important in a range of application areas, including engineering optics, biological products, metrology artifacts, data storage, etc. However, there is a lack of surface characterization methods for the micro-structured surfaces with sub-nanometer accuracy. Although some research s...
Article
Fast tool servo diamond turning is a promising machining method for precision and complex micro-structured surfaces with spatial wavelength above tens of microns. It is crucial to measure and characterize the micro-structured surfaces to sub-micrometer form accuracy. The general purpose measurement instruments are not able to evaluate the true form...
Article
Contour errors usually result from unmatched dynamics, limited axial bandwidth and undesirable nonlinearities. For circular contours, friction, especially static friction, deteriorates the circular contouring accuracy at quadrant positions where there is reversal of velocities or motion from standstill. A two-stage tracking error-based static frict...
Conference Paper
Full-text available
We present a depth controller design for a torpedo-shaped autonomous underwater vehicle (AUV) known as STARFISH. It is common to design an AUV to be positively buoyant, so that it will float to the surface in case of power failure. However, most depth controllers are designed with a neutral buoyancy assumption by regarding the extra buoyancy as a d...
Article
In this paper, an integral sliding mode controller (ISMC), based on input–output models, is proposed as a refinement from a two-degree-of-freedom controller with independent objectives for tracking and regulation. Thus, the knowledge of pole placement can be utilized in ISMC. The robustness is improved by a disturbance estimation, which results in...
Article
Increasing demand for ultraprecision components with micro-structured surfaces has attracted focus on diamond turning research. In this paper, a fast tool servo (FTS) based diamond turning machine is presented for fabricating micro-structured surfaces with high accuracy. A design criterion is established to serve as a guide in choosing or designing...
Article
In this paper, the development of hidden Markov model with explicit state duration (Variable duration HMM) for face milling residual life distribution prognostics is presented. An HMM with explicit state duration is constructed by involving explicit state duration probability. The HMM with explicit state duration offers significant advantages over...
Article
Ball nose milling of complex surfaces is common in the die/mould and aerospace industries. A significant influential factor in complex surface machining by ball nose milling for part accuracy and tool life is the cutting force. There has been little research on cutting force model for ball nose milling on inclined planes. Using such a model ,and by...
Article
A robust and precise medical device is important for blood glucose regulation. We have developed a prototype device to regulate blood glucose. The device is composed of four subsystems: measuring subsystem, pumping subsystem, controller subsystem and power subsystem. Each subsystem plays an important part in the development of an intelligent implan...
Article
Full-text available
Central Pattern Generator (CPG) is used in bipedal locomotion control to provide the basic rhythm signal for actuators. Generally, the CPG is composed of many neural oscillators coupled together. In this paper, the coordination between neural oscillators in CPG is studied to achieve robust rhythm motions. By using the entrainment property of the ne...
Article
Due to their extensive utilization in engineering designs, various vibration controllers have been investigated with design specifications in mind. The optimization of vibration controller designs is a complicated multi-criteria problem. In this paper, the mechatronic design quotient (MDQ) approach and genetic algorithm (GA) are coupled together to...
Article
Full-text available
This paper reviews the state-of-the-art of wavelet analysis for tool condition monitoring (TCM). Wavelet analysis has been the most important non-stationary signal processing tool today, and popular in machining sensor signal analysis. Based on the nature of monitored signals, wavelet approaches are introduced and the superiorities of wavelet analy...
Article
In our previous work, a novel force control actuator, called series damper actuator (SDA), has been proposed. This paper proposes a general design procedure for the SDA system. From design requirements, several key parameters of the SDA plant can be determined. Based on these parameters, the selection or design of the series damper and the motor ca...