Omogbai Oleghe
Omogbai Oleghe has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Konstantinos Salonitis
University College Dublin
3 shared publications
Latest Publications
- 10 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 84-91
Controller-based IIoT infrastructure and enabling technologies: An overview for design configuration
This article presents an overarching overview of controller-based Industrial Internet of Things (IIoT) infrastructures, with emphasis on the prevalent enabling technologies. Through a critical analysis, the study is used to reveal the determinants for choosing IIoT infrastructure and enabling technologies, given the type of field device whether microcontroller or Programmable Logic Controller. Findings from the analysis motivate proposal for generalized configurations for the design of IIoT systems to harmonize the multitude of conceivable designs.
- 10 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 84-91
Controller-based IIoT infrastructure and enabling technologies: An overview for design configuration
This article presents an overarching overview of controller-based Industrial Internet of Things (IIoT) infrastructures, with emphasis on the prevalent enabling technologies. Through a critical analysis, the study is used to reveal the determinants for choosing IIoT infrastructure and enabling technologies, given the type of field device whether microcontroller or Programmable Logic Controller. Findings from the analysis motivate proposal for generalized configurations for the design of IIoT systems to harmonize the multitude of conceivable designs.
- Open Access
- 1 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 68028-68043
Container Placement and Migration in Edge Computing: Concept and Scheduling Models
Containers are a form of software virtualization, rapidly becoming the de facto way of providing edge computing services. Research on container-based edge computing is plentiful, and this has been buoyed by the increasing demand for single digit, milliseconds latency computations. A container scheduler is part of the architecture that is used to manage and orchestrate multiple container-based applications on heterogenous computing nodes. The scheduler decides how incoming computing requests are allocated to containers, which edge nodes the containers are placed on, and where already deployed containers are migrated to. This paper aims to clarify the concept of container placement and migration in edge servers and the scheduling models that have been developed for this purpose. The study illuminates the frameworks and algorithms upon which the scheduling models are built. To convert the problem to one that can be solved using an algorithm, the container placement problem in mostly abstracted using multi-objective optimization models or graph network models. The scheduling algorithms are predominantly heuristic-based algorithms, which are able to arrive at sub-optimal solutions very quickly. There is paucity of container scheduling models that consider distributed edge computing tasks. Research in decentralized scheduling systems is gaining momentum and the future outlook is in scheduling containers for mobile edge nodes.
- 1 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 68028-68043
Open AccessContainer Placement and Migration in Edge Computing: Concept and Scheduling Models
Containers are a form of software virtualization, rapidly becoming the de facto way of providing edge computing services. Research on container-based edge computing is plentiful, and this has been buoyed by the increasing demand for single digit, milliseconds latency computations. A container scheduler is part of the architecture that is used to manage and orchestrate multiple container-based applications on heterogenous computing nodes. The scheduler decides how incoming computing requests are allocated to containers, which edge nodes the containers are placed on, and where already deployed containers are migrated to. This paper aims to clarify the concept of container placement and migration in edge servers and the scheduling models that have been developed for this purpose. The study illuminates the frameworks and algorithms upon which the scheduling models are built. To convert the problem to one that can be solved using an algorithm, the container placement problem in mostly abstracted using multi-objective optimization models or graph network models. The scheduling algorithms are predominantly heuristic-based algorithms, which are able to arrive at sub-optimal solutions very quickly. There is paucity of container scheduling models that consider distributed edge computing tasks. Research in decentralized scheduling systems is gaining momentum and the future outlook is in scheduling containers for mobile edge nodes.
- Open Access
- 17 October 2020
- Published by Springer Nature in Journal of Big Data
- Vol. 7 (1) , 1-27
A predictive noise correction methodology for manufacturing process datasets
In manufacturing processes, datasets intended for data driven decisions are majorly generated from time-sequenced sensor readings. Industrial sensor systems are prone to transmit inaccurate readings, which result in noisy datasets. Noisy datasets inhibit machine learning and knowledge discovery. Using a multi-stage, multi-output process dataset as an experimental case, this article reports a methodology for replacing erroneous sensor values with their predicted likely values. In the methodology, invalid values specified by process owners are first converted to missing values. Then, ReliefF algorithm is used to select the most relevant features to progress for prediction modelling, and also to boost the performance of the prediction model. A Random Forest classifier model is built to predict replacement values for the missing values. Finally, predicted values are inserted into the dataset to fill in the missing entries. With many attributes having a significant number of erroneous values, the invalid values replacement is done one attribute at a time. To do this systematically, the process flow direction and stages in the manufacturing process are exploited to partition the dataset into subsets for model building. The results indicate that the methodology is able to replace erroneous values with likely true values, to a very high degree of accuracy. There is a paucity of this type of methodology for dealing with invalid entries in process datasets. The methodology is useful for both missing and invalid value correction in process datasets. In the future, the plan is to inject the prediction models into streaming data to simultaneously enable erroneous value correction and predictive process monitoring in real-time.
- 17 October 2020
- Published by Springer Nature in Journal of Big Data
- Vol. 7 (1) , 1-27
Open AccessA predictive noise correction methodology for manufacturing process datasets
In manufacturing processes, datasets intended for data driven decisions are majorly generated from time-sequenced sensor readings. Industrial sensor systems are prone to transmit inaccurate readings, which result in noisy datasets. Noisy datasets inhibit machine learning and knowledge discovery. Using a multi-stage, multi-output process dataset as an experimental case, this article reports a methodology for replacing erroneous sensor values with their predicted likely values. In the methodology, invalid values specified by process owners are first converted to missing values. Then, ReliefF algorithm is used to select the most relevant features to progress for prediction modelling, and also to boost the performance of the prediction model. A Random Forest classifier model is built to predict replacement values for the missing values. Finally, predicted values are inserted into the dataset to fill in the missing entries. With many attributes having a significant number of erroneous values, the invalid values replacement is done one attribute at a time. To do this systematically, the process flow direction and stages in the manufacturing process are exploited to partition the dataset into subsets for model building. The results indicate that the methodology is able to replace erroneous values with likely true values, to a very high degree of accuracy. There is a paucity of this type of methodology for dealing with invalid entries in process datasets. The methodology is useful for both missing and invalid value correction in process datasets. In the future, the plan is to inject the prediction models into streaming data to simultaneously enable erroneous value correction and predictive process monitoring in real-time.
- Open Access
- 30 September 2020
- Published by Springer Nature in Research Square
A predictive noise correction methodology for manufacturing process datasets
In manufacturing processes, datasets intended for data driven decisions are majorly generated from time-sequenced sensor readings. Industrial sensor systems are prone to transmit inaccurate readings, which result in noisy datasets. Noisy datasets inhibit machine learning and knowledge discovery. Using a multi-stage, multi-output process dataset as an experimental case, this article reports a methodology for replacing erroneous sensor values with their predicted likely values. In the methodology, invalid values specified by process owners are first converted to missing values. Then, ReliefF algorithm is used to select the most relevant features to progress for prediction modelling, and also to boost the performance of the prediction model. A Random Forest classifier model is built to predict replacement values for the missing values. Finally, predicted values are inserted into the dataset to fill in the missing entries. With many attributes having a significant number of erroneous values, the invalid values replacement is done one attribute at a time. To do this systematically, the process flow direction and stages in the manufacturing process are exploited to partition the dataset into subsets for model building. The results indicate that the methodology is able to replace erroneous values with likely true values, to a very high degree of accuracy. There is a paucity of this type of methodology for dealing with invalid entries in process datasets. The methodology is useful for both missing and invalid value correction in process datasets. In the future, the plan is to inject the prediction models into streaming data to simultaneously enable erroneous value correction and predictive process monitoring in real-time.
- 30 September 2020
- Published by Springer Nature in Research Square
Open AccessA predictive noise correction methodology for manufacturing process datasets
In manufacturing processes, datasets intended for data driven decisions are majorly generated from time-sequenced sensor readings. Industrial sensor systems are prone to transmit inaccurate readings, which result in noisy datasets. Noisy datasets inhibit machine learning and knowledge discovery. Using a multi-stage, multi-output process dataset as an experimental case, this article reports a methodology for replacing erroneous sensor values with their predicted likely values. In the methodology, invalid values specified by process owners are first converted to missing values. Then, ReliefF algorithm is used to select the most relevant features to progress for prediction modelling, and also to boost the performance of the prediction model. A Random Forest classifier model is built to predict replacement values for the missing values. Finally, predicted values are inserted into the dataset to fill in the missing entries. With many attributes having a significant number of erroneous values, the invalid values replacement is done one attribute at a time. To do this systematically, the process flow direction and stages in the manufacturing process are exploited to partition the dataset into subsets for model building. The results indicate that the methodology is able to replace erroneous values with likely true values, to a very high degree of accuracy. There is a paucity of this type of methodology for dealing with invalid entries in process datasets. The methodology is useful for both missing and invalid value correction in process datasets. In the future, the plan is to inject the prediction models into streaming data to simultaneously enable erroneous value correction and predictive process monitoring in real-time.
- Open Access
- 16 August 2019
- Published by Emerald Publishing in Journal of Quality in Maintenance Engineering
- Vol. 25 (3) , 476-498
The application of a hybrid simulation modelling framework as a decision-making tool for TPM improvement
Purpose: The purpose of this paper is to promote a system dynamics-discrete event simulation (SD-DES) hybrid modelling framework, one that is useful for investigating problems comprising multifaceted elements which interact and evolve over time, such as is found in TPM. Design/methodology/approach: The hybrid modelling framework commences with system observation using field notes which culminate in model conceptualization to structure the problem. Thereafter, an SD-DEShybrid model is designed for the system, and simulated to proffer improvement programmes. The hybrid model emphasises the interactions between key constructs relating to the system, feedback structures and process flow concepts that are the hallmarks of many problems in production. The modelling framework is applied to the TPM operations of a bottling plant where sub-optimal TPM performance was affecting throughput performance. Findings: Simulation results for the case study show that intangible human factors such as worker motivation do not significantly affect TPM performance. What is most critical is ensuring full compliance to routine and scheduled maintenance tasks and coordinating the latter to align with rate of machine defect creation. Research limitations/implications: The framework was developed with completeness, generality and reuse in view. It remains to be applied to a wide variety of TPM and non-TPM-related problems. Practical implications: The developed hybrid model is scalable and can fit into an existing discrete event simulation model of a production system. The case study findings indicate where TPM managers should focus their efforts. Originality/value: The investigation of TPM using SD-DES hybrid modelling is a novelty.
- 16 August 2019
- Published by Emerald Publishing in Journal of Quality in Maintenance Engineering
- Vol. 25 (3) , 476-498
Open AccessThe application of a hybrid simulation modelling framework as a decision-making tool for TPM improvement
Purpose: The purpose of this paper is to promote a system dynamics-discrete event simulation (SD-DES) hybrid modelling framework, one that is useful for investigating problems comprising multifaceted elements which interact and evolve over time, such as is found in TPM. Design/methodology/approach: The hybrid modelling framework commences with system observation using field notes which culminate in model conceptualization to structure the problem. Thereafter, an SD-DEShybrid model is designed for the system, and simulated to proffer improvement programmes. The hybrid model emphasises the interactions between key constructs relating to the system, feedback structures and process flow concepts that are the hallmarks of many problems in production. The modelling framework is applied to the TPM operations of a bottling plant where sub-optimal TPM performance was affecting throughput performance. Findings: Simulation results for the case study show that intangible human factors such as worker motivation do not significantly affect TPM performance. What is most critical is ensuring full compliance to routine and scheduled maintenance tasks and coordinating the latter to align with rate of machine defect creation. Research limitations/implications: The framework was developed with completeness, generality and reuse in view. It remains to be applied to a wide variety of TPM and non-TPM-related problems. Practical implications: The developed hybrid model is scalable and can fit into an existing discrete event simulation model of a production system. The case study findings indicate where TPM managers should focus their efforts. Originality/value: The investigation of TPM using SD-DES hybrid modelling is a novelty.
- Open Access
- 1 January 2016
- Published by Elsevier in Procedia CIRP
- Vol. 41, 608-613
Variation Modeling of Lean Manufacturing Performance Using Fuzzy Logic Based Quantitative Lean Index
- 1 January 2016
- Published by Elsevier in Procedia CIRP
- Vol. 41, 608-613
Open AccessVariation Modeling of Lean Manufacturing Performance Using Fuzzy Logic Based Quantitative Lean Index
- Open Access
- 1 January 2015
- Published by Elsevier in Procedia CIRP
- Vol. 37, 42-47
Improving the Efficacy of the Lean Index through the Quantification of Qualitative Lean Metrics
- 1 January 2015
- Published by Elsevier in Procedia CIRP
- Vol. 37, 42-47
Open AccessImproving the Efficacy of the Lean Index through the Quantification of Qualitative Lean Metrics