1,720,984 research outputs found
Efficiency measurement based on novel performance measures in total productive maintenance (TPM) using a fuzzy integrated COPRAS and DEA method
Get PDFTotal Productive Maintenance (TPM) has been widely recognized as a strategic tool and lean manufacturing practice for improving manufacturing performance and sustainability, and therefore it has been successfully implemented in many organizations. The evaluation of TPM efficiency can assist companies in improving their operations across a variety of dimensions. This paper aims to propose a comprehensive and systematic framework for the evaluation of TPM performance. The proposed total productive maintenance performance measurement system (TPM PMS) is divided into four phases (e.g., design, evaluate, implement, and review): i) the design of new performance measures, ii) the evaluation of the new performance measures, iii) the implementation of the new performance measures to evaluate TPM performance, and iv) the reviewing of the TPM PMS. In the design phase, different types of performance measures impacting TPM are defined and analyzed by decision-makers. In the evaluation phase, novel performance measures are evaluated using the Fuzzy COmplex Proportional Assessment (FCOPRAS) method. In the implementation phase, a modified fuzzy data envelopment analysis (FDEA) is used to determine efficient and inefficient TPM performance with novel performance measures. In the review phase, TPM performance is periodically monitored, and the proposed TPM PMS is reviewed for successful implementation of TPM. A real-world case study from an international manufacturing company operating in the automotive industry is presented to demonstrate the applicability of the proposed TPM PMS. The main findings from the real-world case study showed that the proposed TPM PMS allows measuring TPM performance with different indicators especially soft ones, e.g., human-related, and supports decision makers by comparing the TPM performances of production lines and so prioritizing the most important preventive/predictive decisions and actions according to production lines, especially the ineffective ones in TPM program implementation. Therefore, this system can be considered a powerful monitoring tool and reliable evidence to make the implementation process of TPM more efficient in the real-world production environment
Involving students in engineering course design: a combined approach based on constructive alignment and multi-criteria decision-making
Get PDFEmpowering students to actively shape their learning is essential. Various student involvement models, such as design-based research, participatory design, and co-creation, emphasise students’ growing role in shaping educational activities. Engaging students in course design, as seen in student co-creation, can enhance agency, improve the student experience, and boost outcomes. Considering this, we propose a systematic approach combining multi-criteria decision-making with constructive alignment theory to involve students as co-creators in course design. This approach aims to engage students in the course design process and co-create intended learning outcomes, which can be regarded as the primary participatory phase in developing a co-created course. By involving students, our approach aims to gain insight into their needs, prioritise their views, and guide the formulation of appropriate course specifications throughout the course design process. The approach is applied to a new multi-disciplinary engineering course, and the results are summarised following its corresponding steps. Students’ feedback indicates that the approach positively influenced their motivation, engagement with course objectives, collaboration with teachers, and overall achievement of intended learning outcomes. This study’s significance lies in its contribution to higher education, offering a more integrated and systematic approach to support co-creation between educators and learners in academic course design
An intelligent approach for data pre-processing and analysis in predictive maintenance with an industrial case study
Get PDFRecent development in the predictive maintenance field has focused on incorporating artificial intelligence techniques in the monitoring and prognostics of machine health. The current predictive maintenance applications in manufacturing are now more dependent on data-driven Machine Learning algorithms requiring an intelligent and effective analysis of a large amount of historical and real-time data coming from multiple streams (sensors and computer systems) across multiple machines. Therefore, this article addresses issues of data pre-processing that have a significant impact on generalization performance of a Machine Learning algorithm. We present an intelligent approach using unsupervised Machine Learning techniques for data pre-processing and analysis in predictive maintenance to achieve qualified and structured data. We also demonstrate the applicability of the formulated approach by using an industrial case study in manufacturing. Data sets from the manufacturing industry are analyzed to identify data quality problems and detect interesting subsets for hidden information. With the approach formulated, it is possible to get the useful and diagnostic information in a systematic way about component/machine behavior as the basis for decision support and prognostic model development in predictive maintenance
ANFIS Modeling for Forecasting Oil Consumption of Turkey
No full textIn this study, the interrelationship between oil consumption and economic growth is examined via ANFIS modeling that is used to obtain long term forecasting results for oil consumption of Turkey through predetermined inputs, which are specified as population, gross domestic product (GDP), import and export. The data samples from 1965 to 2000 are conducted for developing the ANFIS model indicating the relationship between the oil consumption and the four inputs. Triangular types of membership functions are defined as low, medium and high for each input parameter in the ANFIS prediction system. Afterwards, oil consumption of Turkey is predicted from 2012 to 2030 using double exponential forecasting technique. Hence, this study can act as a guideline for long term forecasting of future oil consump-tion of any other country
Challenges in Data Life Cycle Management for Sustainable Cyber-Physical Production Systems
No full textRapid technological advances present new opportunities to use industrial Big Data to monitor and improve performance more systematically and more holistically. The on-going fourth industrial revolution, aka Industrie 4.0, holds the promise to support the implementation of sustainability principles in manufacturing. However, much of these opportunities are missed as social and environmental performance are still largely considered as an afterthought or add-on to business as usual. This paper reviews existing data life cycle models and discusses their usefulness for sustainable manufacturing performance management. Finally, we suggest possible directions for further research to promote more sustainable cyber-physical production systems
ANFIS Modeling for Forecasting Oil Consumption of Turkey
No full textIn this study, the interrelationship between oil consumption and economic growth is examined via ANFIS modeling that is used to obtain long term forecasting results for oil consumption of Turkey through predetermined inputs, which are specified as population, gross domestic product (GDP), import and export. The data samples from 1965 to 2000 are conducted for developing the ANFIS model indicating the relationship between the oil consumption and the four inputs. Triangular types of membership functions are defined as low, medium and high for each input parameter in the ANFIS prediction system. Afterwards, oil consumption of Turkey is predicted from 2012 to 2030 using double exponential forecasting technique. Hence, this study can act as a guideline for long term forecasting of future oil consump-tion of any other country
An ANFIS Algorithm for Forecasting Overall Equipment Effectiveness Parameter in Total Productive Maintenance
No full textotal Productive Maintenance (TPM) is a successful technique used for corrective, preventive and predictive maintenance policies. It is important in identifying the success and overall effectiveness of the manufacturing process for long term economic viability of business. Overall equipment effectiveness (OEE) is commonly used and well-accepted metric for TPM implementation in many manufacturing industries. In this study, Adaptive Neuro-Fuzzy Inference System (ANFIS) is used to obtain forecasted results for OEE parameter in TPM through some predetermined inputs such as availability, performance efficiency and rate of quality. Triangular type of membership functions was determined as low, medium, and high for each input parameter in the ANFIS model. Fuzzy c-means clustering algorithm was used for determining of the membership degrees of membership functions for each input parameter. This study is important to forecast the risk by OEE in the TPM. With the predicted results of OEE performance an appropriate maintenance strategy can be developed and the production can be improved. This can also help reducing the risk level of breakdowns or failures at any critical equipment
Using Adaptive Neuro-Fuzzy Inference System, Artificial Neural Network and Response Surface Method to Optimize Overall Equipment Effectiveness for An Automotive Supplier Company
No full textTotal Productive Maintenance (TPM) is a successful technique that is important in identifying the success and overall effectiveness of the manufacturing process for long term economic viability of business. Overall equipment effectiveness (OEE) is commonly used and well-accepted metric for TPM implementation in many manufacturing industries. As OEE is an important performance measure for effectiveness of any equipment, careful analysis is required to know the effect of various components. An attempt has been done in this research to predict the OEE by using simulation software. The objective is to identify an optimal OEE level to maximize the time between failures and simultaneously minimize the mean repair time. The process of OEE is optimized by using Response Surface Methodology (RSM), Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference system (ANFIS) to identify optimized zone for maximizing output. Finally it is determined the feasible values of inputs using Sequential Quadratic Programming (SQP) algorithm based on trained ANFIS predictive model. The result from this study can be used the inconvenient impact of the failures on the production process, it is strongly recommended to upgrade the operation management, i.e. TPM program, capacity analysis, parts replacement decisions, training programs for technicians/operators, spare parts requirement etc
Multi-Machine Gaussian Topic Modeling for Predictive Maintenance
Get PDFIn this paper, we propose a coherent framework for multi-machine analysis, using a group clustering model, which can be utilized for predictive maintenance (PdM). The framework benefits from the repetitive structure posed by multiple machines and enables for assessment of health condition, degradation modeling and comparison of machines. It is based on a hierarchical probabilistic model, denoted Gaussian topic model (GTM), where cluster patterns are shared over machines and therefore it allows one to directly obtain proportions of patterns over the machines. This is then used as a basis for cross comparison between machines where identified similarities and differences can lead to important insights about their degradation behavior. The framework is based on aggregation of data over multiple streams by a predefined set of features extracted over a time window. Moreover, the framework contains a clustering schema which takes uncertainty of cluster assignments into account and where one can specify a desirable degree of reliability of the assignments. By using a multi-machine simulation example, we highlight how the framework can be utilized in order to obtain cluster patterns and inherent variations of such patterns over machines. Furthermore, a comparative study with the commonly used Gaussian mixture model (GMM) demonstrates that GTM is able to identify inherent patterns in the data while the GMM fails. Such result is a consequence of the group level being modeled by the GTM while being absent in the GMM. Hence, the GTM are trained with a view on the data that is not available to the GMM with the consequence that the GMM can miss important, possibly even key, cluster patterns. Therefore, we argue that more advanced cluster models, like the GTM, can be key for interpreting and understanding degradation behavior across machines and ultimately for obtaining more efficient and reliable PdM systems
Domain Knowledge in CRISP-DM: An Application Case in Manufacturing
No full textPara seguir el ritmo de las cambiantes tendencias tecnológicas y seguir siendo competitivas, cada vez más empresas manufactureras investigan cómo utilizar la analítica de datos para mejorar sus procesos. Un problema al que estas empresas suelen enfrentarse hoy en día es la necesidad de más competencias para llevar a cabo proyectos de analítica avanzada dentro de sus departamentos. Mediante el uso de un enfoque humano en el bucle y la utilización eficiente del conocimiento actual del dominio en combinación con el análisis de datos, se puede lograr un mayor éxito en la implementación. Un enfoque común hoy en día para llevar a cabo proyectos de análisis de datos es utilizar la metodología general del Proceso Estándar Industrial Cruzado para la Minería de Datos (CRISP-DM). Esta metodología no tiene en cuenta los retos específicos de la industria manufacturera ni cómo incluir la experiencia en el sector. Por lo tanto, este artículo sugiere cómo adaptar la metodología CRISP-DM para compensar estos problemas. La metodología adaptada se demuestra en un estudio de caso para mejorar la calidad en el proceso de mecanizado mediante el uso de modelos interpretables de aprendizaje automático que pueden utilizarse para ayudar a los expertos a la hora de realizar el análisis de la causa raíz. Esto contribuye a mostrar cómo utilizar mejor los conocimientos de los expertos del dominio y cómo puede emplearse la analítica de datos junto con métodos específicos del dominio.To keep up with shifting technology trends and remain competitive, more manufacturing companies are investigating how to utilize data analytics to improve their processes. An issue these companies often face today is the need for more competence to perform advanced analytics projects within their departments. By using a human-in-the-loop approach and efficiently utilizing current domain knowledge in combination with data analytics, the higher success of implementation can be achieved. A common approach today to perform data analytics projects is to use the general Cross Industry Standard Process for Data Mining (CRISP-DM) methodology. This methodology does not consider the challenges specific to manufacturing and how to include domain expertise. This paper, therefore, suggests how the CRISP-DM methodology can be adapted to compensate for these issues. The adapted methodology is demonstrated in a case study for improving quality in the machining process by using interpretable machine learning models that can be used to assist experts when performing root cause analysis. This contributes to showing how to use domain experts’ knowledge better and how data analytics can be used in conjunction with domain-specific methods
- …
