Browsing by Author "Oleghe, Omogbai"

Now showing 1 - 10 of 10
  • Thumbnail Image
    ItemOpen Access
    Analysis of lean manufacturing strategy using system dynamics modelling of a business model
    (Emerald, 2019-08-22) Gomez Segura, Miguel; Oleghe, Omogbai; Salonitis, Konstantinos
    A system dynamics-based methodology is described for analysing the impact of lean manufacturing strategies on a company's business performance, using Business Model Canvas perspective. A case study approach is used to describe the methodology which consists of conceptualizing a system dynamics model on the basis of Business Model Canvas. The base system dynamics model is elaborated to include variables and concepts that consider the effects of lean manufacturing metrics on business performance. In the modelling experimentation, the lean manufacturing metrics are made to take on likely values one would expect if certain lean practices are initiated or improved. The experimental results provide one with the likely impact on business performance, if one were to improve lean manufacturing practices. The simulation results for the case study show that lean improvements, on the short-run, have a significant impact on business performance, but on the long-run, the impact is only marginal. The described methodology provides one with a structured format for investigating the impact of lean practices on business performance. Although the developed system dynamics model was built with generality in mind, it remains to be reproduced in other settings to test its replicability. The methodology enables an organization target which lean improvements to initiate based on their strategic impact on the business. Limited studies exist where system dynamics and business models are combined to test the strategic impact of lean manufacturing.
  • Thumbnail Image
    ItemOpen Access
    The application of a hybrid simulation modelling framework as a decision-making tool for TPM improvement
    (Emerald, 2019-03-01) Oleghe, Omogbai
    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.
  • Thumbnail Image
    ItemOpen Access
    Feature reduction and selection for use in machine learning for manufacturing
    (IOS Press, 2022-09-08) Alrufaihi, Duaa; Oleghe, Omogbai; Almanei, Mohammed; Jagtap, Sandeep; Salonitis, Konstantinos
    In a complex manufacturing system such as the multistage manufacturing system, maintaining the quality of the products becomes a challenging task. It is due to the interconnectivity and dependency of factors that can affect the final product. With the increasing availability of data, Machine Learning (ML) approaches are applied to assess and predict quality-related issues. In this paper, several ML algorithms, including feature reduction/selection methods, were applied to a publicly available multistage manufacturing dataset to predict the characteristic of the output measurements in (mm). A total of 24 prediction models were produced. The accuracy of the prediction models and the execution time were the evaluation metrics. The results show that uncontrolled variables are the most common features that have been selected by the selection/reduction methods suggesting their strong relationship to the quality of the product. The performance of the prediction models was heavily dependent on the ML algorithm.
  • Thumbnail Image
    ItemOpen Access
    A framework for designing data pipelines for manufacturing systems
    (Elsevier, 2020-09-22) Oleghe, Omogbai; Salonitis, Konstantinos
    Data pipelines describe the path through which big data is transmitted, stored, processed and analyzed. Designing an appropriate data pipeline for a specific data driven manufacturing project can be challenging, whereas there is a paucity of frameworks to guide one in the design. In this research we develop a framework for designing data pipelines for manufacturing systems. The framework consists of a template for selecting key layers and components that make up big data pipelines in manufacturing systems. A use case is presented to provide an illustrative guideline for its application. Benefits of the framework and future directions are discussed
  • Thumbnail Image
    ItemOpen Access
    Hybrid simulation modelling of the human-production process interface in lean manufacturing systems
    (Emerald, 2018-12-31) Oleghe, Omogbai; Salonitis, Konstantinos
    Purpose This study aims to seek to advance a system dynamics-discrete event hybrid simulation modelling concept useful for taking improvement decisions where one needs to consider the interactions between human factors and process flow elements in lean manufacturing systems. Design/methodology/approach A unique approach is taken to hybrid simulation modelling where the whole problem situation is first conceptualized using a causal loop diagram and stock and flow diagram, before transmitting to a hybrid simulation model. The concept is intended to simplify the simulation modelling process and make the concept pliable for use in various types of lean manufacturing problem situations. Findings The hybrid simulation modelling concept was applied to a lean manufacturing case where quality performance was sporadic mainly because of production pressures. The hybrid modelling concept revealed a solution that advanced full compliance with lean and one that required changes in job scheduling policies to promote both continuous improvement and throughput increases. Research limitations/implications Because non-tangible aspects of lean were objectively assessed using the hybrid modelling concept, the study is an advancement towards establishing a credible link between human resource aspects of lean and the performance of an organization. Practical implications The applied hybrid model enabled managers in the plant navigate the trade-off decision they often face when choosing to advance production output ahead of continuous improvement practices. Originality/value System dynamics-discrete event hybrid simulation modelling is a rarity in lean manufacturing systems.
  • Thumbnail Image
    ItemOpen Access
    Implementing pull manufacturing in make-to-order environments
    (IOS Press, 2022-12-31) Almanei, Mohammed; Oleghe, Omogbai; Afy-Shararah, Mohamed; Salonitis, Konstantinos
    The demand for increasing product variety and customization has forced many companies to adopt a make-to-order (MTO) strategy. Traditional push-type MTO companies suffer from unstable demands, struggling to deliver on time, making them consider the utilization of pull systems to control production. In the present paper, an overview of pull systems in MTO environments is presented. Moreover, a discrete event simulation (DES) model of an MTO company in the printing and packaging industrial sector was developed and validated, in order to identify areas for improvement. DES was also used in order to evaluate the feasibility of implementing three types of pull systems: kanban, CONstant-Work-In-Process (CONWIP) and Paired Overlapping Loops of Cards with Authorizations (POLCA). The main performance indicators measured were the average WIP and the average throughput time of parts. The key findings of this project for the case study were: a) kanban is inapplicable for the current routing of parts; b) a CONWIP strategy improves the shop floor performance, but only when extra capacity is added to the extrusion workstation; c) production based on POLCA leads to the blockage of the system due to the existence of multi-routes and undirected routing.
  • Thumbnail Image
    ItemOpen Access
    Improving the efficacy of the lean index through the quantification of qualitative lean metrics
    (Elsevier, 2015-10-09) Oleghe, Omogbai; Salonitis, Konstantinos
    Multiple lean metrics representing performance for various aspects of lean can be consolidated into one holistic measure for lean, called the lean index, of which there are two types. In this article it was established that the qualitative based lean index are subjective while the quantitative types lack scope. Subsequently, an appraisal is done on techniques for quantifying qualitative lean metrics so that the lean index is a hybrid of both, increasing the confidence in the information derived using the lean index. This ensures every detail of lean within a system is quantified, allowing daily tracking of lean. The techniques are demonstrated in a print packaging manufacturing case.
  • Thumbnail Image
    ItemOpen Access
    Machine learning algorithms comparison for manufacturing applications
    (IOS Press, 2021-09-07) Almanei, Mohammed; Oleghe, Omogbai; Jagtap, Sandeep; Salonitis, Konstantinos
    With the vast amount of data available, and its increasing complexity in manufacturing processes, traditional statistical approaches have started to fall short. This is where machine learning plays a key role, addressing the challenges by bringing the ability to analyse large and complex datasets from multiple sources, finding non-linear and intricate patterns on data, relationships between several factors and their influence on the manufacturing process outputs. This paper demonstrates the advantages and applications of using supervised machine learning techniques in the manufacturing industry. It focuses on binary classification and compares the performance of three different machine learning algorithms: logistic regression, support vector machine, and neural networks. A case study has been conducted on a manufacturing company, using the techniques and algorithms mentioned. The case study focuses on analysing the relationship between different manufacturing process variables and their impact on one key output variable of a product, which in this case is the result of a quality test that measures product performance. The modelling problem has been oriented towards a Boolean goal to predict whether the parts will pass this test.
  • Thumbnail Image
    ItemOpen Access
    Schedule performance measurement based on statistical process control charts
    (Inderscience, 2014-03-14) Oleghe, Omogbai; Salonitis, Konstantinos
    In a job-shop manufacturing environment, achieving a schedule that is on target is difficult due to the dynamism of factors affecting the system, and this makes schedule performance measurement systems hard to design and implement. In the present paper, Statistical Process Control charts are directly applied to a scheduling process for the purpose of objectively measuring schedule performance. SPC charts provide an objective and timely approach to designing, implementing and monitoring schedule performance. However, the use of Statistical Process Control charts requires an appreciation of the conditions for applying raw data to SPC charts. In the present paper, the Shewart’s Individuals control chart are applied to monitor the deviations of actual process times from the scheduled process times for each job on a process machine. The Individuals control charts are highly sensitive to non-normal data, which increases the rate of false alarms, but this can be avoided using data transformation operations such as the Box-Cox transformation. Statistical Process Control charts have not been used to measure schedule performance in a job shop setting, so this paper uniquely contributes to research in this area. In addition, using our proposed methodology enables a scheduler to monitor how an optimal schedule has performed on the shop floor, study the variations between planned and actual outcomes, seek ways of eliminating these variations and check if process improvements have been effective.
  • Thumbnail Image
    ItemOpen Access
    Variation Modeling of Lean Manufacturing Performance Using Fuzzy Logic Based Quantitative Lean Index
    (Elsevier, 2016-02-19) Oleghe, Omogbai; Salonitis, Konstantinos
    The lean index is the sum of weighted scores of performance variables that describe the lean manufacturing characteristics of a system. Various quantitative lean index models have been advanced for assessing lean manufacturing performance. These models are represented by deterministic variables and do not consider variation in manufacturing systems. In this article variation is modeled in a quantitative fuzzy logic based lean index and compared with traditional deterministic modeling. By simulating the lean index model for a manufacturing case it is found that the latter tend to under or overestimate performance and the former provides a more robust lean assessment.