EDEric Dimla

Eric Dimla

*This is an algorithmically generated author record based on publicly available information.

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


Eric Dimla has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Predicting Phase-field Behavior of Brittle Fracture Model based on LSTM Time Series Forecasting Model

    by Chien Vo Trung, Minh Ngoc Dinh, Eric Dimla

    Predicting cracks in a structure requires engineers to understand the material properties of the structure and to design appropriate equations for the crack model. Furthermore, solving the system of equations of the model is often computationally expensive. Therefore, we combine a mathematical model with a forecasting method for finding results faster when utilizing numerical methods to solve equations with a dense mesh density. In which, the Isotropic Brittle Fracture Model (BFM) is combined with Long Short Term Memory-Time Series Forecasting Model (LTSFM). In particular, the crack propagation based on the change of phase-field variable is approximated using the Finite Element Method (FEM) where the staggered Scheme and Master-Slave Method for establishing Dirichlet boundary conditions in the crack model are applied. The data, after created by the crack model, are used to train and predict by LTSFM for the propagation of cracks in the structure via the change of the value of phase-field variables. As a result, the combination of the analytical mathematical model and forecasting model reduces the computational time while ensuring correct trends of crack propagation based on the value of phase-field variables.


  • Open Access

    Online Tool Condition Monitoring Based on Parsimonious Ensemble+

    by Mahardhika Pratama, Eric Dimla, Edwin Lughofer, Witold Pedrycz, Tegoeh Tjahjowidowo

    Accurate diagnosis of tool wear in metal turning process remains an open challenge for both scientists and industrial practitioners because of inhomogeneities in workpiece material, nonstationary machining settings to suit production requirements, and nonlinear relations between measured variables and tool wear. Common methodologies for tool condition monitoring still rely on batch approaches which cannot cope with a fast sampling rate of metal cutting process. Furthermore they require a retraining process to be completed from scratch when dealing with a new set of machining parameters. This paper presents an online tool condition monitoring approach based on Parsimonious Ensemble+, pENsemble+. The unique feature of pENsemble+ lies in its highly flexible principle where both ensemble structure and base-classifier structure can automatically grow and shrink on the fly based on the characteristics of data streams. Moreover, the online feature selection scenario is integrated to actively sample relevant input attributes. The paper presents advancement of a newly developed ensemble learning algorithm, pENsemble+, where online active learning scenario is incorporated to reduce operator labelling effort. The ensemble merging scenario is proposed which allows reduction of ensemble complexity while retaining its diversity. Experimental studies utilising real-world manufacturing data streams and comparisons with well known algorithms were carried out. Furthermore, the efficacy of pENsemble was examined using benchmark concept drift data streams. It has been found that pENsemble+ incurs low structural complexity and results in a significant reduction of operator labelling effort.

  • Open Access

    Analysis of Chip Morphology in Drilling Ti-6Al-4V by Using Graphene Oxide Nanofluids

    by Xuanyu Mao, Shuang Yi, John Mo, Eric Dimla, Songlin Ding

    Titanium and its alloys have been widely used in various areas due to their superior mechanical properties. However, Titanium and its alloys have low elastic modulus and low thermal conductivity, which lead to extreme high temperature during the machining process and result in poor workpiece quality. The main objective of this paper is to investigate the effectiveness of graphene oxide (GO) nanofluids in drilling process of Ti-6Al-4V by using tungsten carbide tools. The spiral chips were obtained when GO nanofluid was used and squeezed string chips were obtained when conventional coolant was applied. By analysing the back surface of the chips, it was found that the high coolant pressure resulted in better chip formation, which had less scratch and plunking. In addition, by using higher concentration of GO nanofluids, the adhesion phenomenon was found significantly reduced.

  • Offline Handwritten Text Recognition using Convolutional Recurrent Neural Network

    by Hong-Phuong Tran, Andrew Smith, Eric Dimla

    Offline handwriting recognition is an image-based sequence recognition task within computer vision. Traditional approaches rely on lexical segmentation, complex feature extraction techniques and considerable knowledge in the domain of linguistics. This paper presents a novel approach to handwriting recognition by using Convolutional Recurrent Neural Network combined with Connectionist Temporal Classification. The implemented method has the advantage of not being dependent on lexical segmentation and manual feature extraction. Moreover, applied methods are symbolic and character independent, making the model globally trainable and suitable to be applied to multiple languages.


  • Innovative Path Planning Algorithm for an Autonomous Robot with Low Computational Cost

    by Sachintha Balasooriya, Ilya Kavalchuk, Eric Dimla

    The processing of data maps in order to find the best solution to transverse between two points is a key task of an autonomous robot. The algorithm often used for this task must also define the computational power requirements of the embedded processor in the system to optimise the solution with the least number of steps. Low end processors can be used contrary to traditional computers. This paper presents a simplified path solving algorithm for known and unknown environments where the robot range is limited to the size of the map created within the computer internal memory. The map can be preloaded with obstacles expected to be encountered. Alternatively, the robot can be switched to discover mode, where information about its environment is gathered on-the-fly using a range sensor. Two path planning algorithms have been simulated in this study to analyse the most efficient execution to be implemented on the platform with a micro-controller with the A* algorithm showing the superior performance and lower computational cost in comparison with Djickstra

  • Open Access

    Toward Interference Aware IoT Framework: Energy and Geo-Location-Based-Modeling

    by Laith Farhan, Omprakash Kaiwartya, Laith Alzubaidi, Waled Gheth, Eric Dimla, Rupak Kharel

    In multi-hop wireless communication, a sensor node should consume its energy efficiently for relaying of data packets. However, most IoT-devices are equipped with limited battery power and computing resources for wireless communications, and thus energy optimization becomes one of the major concerns in wireless sensors routing design. The wireless technologies usually use unlicensed frequency bands of 2.4 GHz to transmit the data. Due to the broadcasting medium, the wireless transmission interferes with the reception of surrounding radios. As a result, data transmission failure increases resulting in low-communication quality. Therefore, one of the best solutions to this problem is to select the hop distance node that has a few neighbor nodes to disseminate packets until it reaches the ultimate receiver. The proposed routing selects the node that has few neighboring nodes and thus less interference. In another word, the scheme finds a better load balancing, and thus minimizes the probability of overload on a sensor node. It also introduces a new clustering algorithm around a single base station to shorten the transmission distances. This approach periodically selects the cluster heads (CHs) according to its location based distance from the final destination. The extensive simulation studies reveal that the proposed algorithm finds the best routing node and clustering formation to forward the traffic and thereby minimizes the interference ratio. In addition, the proposed protocol achieves low-energy consumption and longer network lifetime than other popular protocols.


  • Online Tool Condition Monitoring Based on Parsimonious Ensemble+

    by Mahardhika Pratama, Eric Dimla, Tegoeh Tjahjowidodo, Witold Pedrycz, Edwin Lughofer

    Existing methodologies for tool condition monitoring (TCM) still rely on batch approaches which cannot cope with a fast sampling rate of a metal cutting process. Furthermore, they require a retraining process to be completed from scratch when dealing with a new set of machining parameters. This paper presents an online TCM approach based on Parsimonious Ensemble+ (pENsemble+). The unique feature of pENsemble+ lies in its highly flexible principle where both the ensemble structure and base-classifier structure can automatically grow and shrink on the fly based on the characteristics of data streams. Moreover, the online feature selection scenario is integrated to actively sample relevant input attributes. This paper presents advancement of a newly developed ensemble learning algorithm, pENsemble, where the online active learning scenario is incorporated to reduce the operator's labeling effort. The ensemble merging scenario is proposed which allows reduction of ensemble complexity while retaining its diversity. Experimental studies utilizing two real-world manufacturing data streams: 1) metal turning and 2) 3-D-printing processes and comparisons with well-known algorithms were carried out. Furthermore, the efficacy of pENsemble+ was examined using benchmark concept drift data streams. It has been found that pENsemble+ incurs low structural complexity and results in a significant reduction of the operator's labeling effort.


  • A review of tidal current energy resource assessment: Current status and trend

    by Roslynna Rosli, Eric Dimla

    Renewable energy resources is one of the alternative energy source identified to address the issue of climate change, energy security and economic growth. Tidal energy is a predictable and reliable source of energy where the exploitable capacity is potentially huge, dispersed in different locations globally. The focus of extracting energy from tides has shifted from the traditional tidal barrages to tidal current energy converters. This paper looks into the different aspects that could be considered for tidal current turbines deployment focusing on site specific matters. Identifying the tidal velocity and mean kinetic energy flux is one of the first aspects of resource assessment when identifying a potential site. This ensures that any device deployed would be able to operate optimally. Different installation schemes are considered where currently, seabed installation is the preferred method. Another factor that needs to be considered is the distance of the tidal power plant from shore where the more remote the location the more power transmission cables needed. This reflects on the costs incurred where therefore a balance between the technical and site optimization has to be the most economical as well.


  • Thermal Comparison of Conventional and Conformal Cooling Channel Designs for a Non-Constant Thickness Screw Cap

    by Eric Dimla, Josep Rull-Trinidad, Andres Amador Garcia-Granada, Guillermo Reyes

    Complex parts are manufactured with high production rates using plastic injection. Defects in injection moulded parts are typically caused by non-uniform cooling. The design of cooling channels is a key step in the mould tool design process. Laser sintering allows for the direct fabrication at reasonable price, complex 3D tools with integrated cooling channels without the need of fixtures. This technique allows the designer to optimise the position of cooling channels relative to the heat source. This paper presents a simulation study for a non-constant thickness threaded screw cap. Results comparing conventional to conformal cooling channel show that the range between the highest and the lowest part surface temperatures is reduced by 18.8%. On the other hand, there is only a decrease of 3.9% for the maximum temperature in the interior of the threaded screw cap. Conformal cooling using laser sintering in tool manufacturing achieves an improved heat transfer leading to a better part quality.