Pub Date : 2022-05-27DOI: 10.1108/jqme-10-2021-0077
Seyed Hesam Hosseinizadeh Mazloumi, A. Moini, Mehrdad Agha Mohammad Ali Kermani
PurposeNew maintenance hypotheses such as lean smart maintenance emphasized internal integration. Since the maintenance process is not fully integrated with other business processes, it indicates that some of the problems in the maintenance process are caused by other departments. Additionally, nothing can be managed or improved without first measuring it. In order to enhance internal integration, this study developed a model that makes use of information systems data to examine synchronization and collaboration across departments engaged in maintenance operations.Design/methodology/approachThis research connects maintenance management and business process management through information systems. A conceptual module model based on CMMS is proposed that will use data which are already available in CMMS and, using process mining, will assess the level of synchronization between departments within an organization.FindingsThis conceptual model will serve as a roadmap for creating better value-added CMMS software. This system operates as a performance measurement tool in three majors, including organizational analysis, workflow analysis and eventually, a future simulation of maintenance processes. This module will serve as a decision support system, highlighting opportunities for improvement in maintenance processes.Originality/valueA practical guideline is provided for the future development of CMMSs and their enhancement to intelligence. All assumptions are based on maintenance theories, techniques for measuring maintenance performance and business process management and process mining.
{"title":"Designing synchronizer module in CMMS software based on lean smart maintenance and process mining","authors":"Seyed Hesam Hosseinizadeh Mazloumi, A. Moini, Mehrdad Agha Mohammad Ali Kermani","doi":"10.1108/jqme-10-2021-0077","DOIUrl":"https://doi.org/10.1108/jqme-10-2021-0077","url":null,"abstract":"PurposeNew maintenance hypotheses such as lean smart maintenance emphasized internal integration. Since the maintenance process is not fully integrated with other business processes, it indicates that some of the problems in the maintenance process are caused by other departments. Additionally, nothing can be managed or improved without first measuring it. In order to enhance internal integration, this study developed a model that makes use of information systems data to examine synchronization and collaboration across departments engaged in maintenance operations.Design/methodology/approachThis research connects maintenance management and business process management through information systems. A conceptual module model based on CMMS is proposed that will use data which are already available in CMMS and, using process mining, will assess the level of synchronization between departments within an organization.FindingsThis conceptual model will serve as a roadmap for creating better value-added CMMS software. This system operates as a performance measurement tool in three majors, including organizational analysis, workflow analysis and eventually, a future simulation of maintenance processes. This module will serve as a decision support system, highlighting opportunities for improvement in maintenance processes.Originality/valueA practical guideline is provided for the future development of CMMSs and their enhancement to intelligence. All assumptions are based on maintenance theories, techniques for measuring maintenance performance and business process management and process mining.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48126854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1108/jqme-09-2021-0067
Lijun Shang, Qingan Qiu, Cang Wu, Yongjun Du
PurposeThe study aims to design the limited number of random working cycle as a warranty term and propose two types of warranties, which can help manufacturers to ensure the product reliability during the warranty period. By extending the proposed warranty to the consumer's post-warranty maintenance model, besides the authors investigate two kinds of random maintenance policies to sustain the post-warranty reliability, i.e. random replacement first and random replacement last. By integrating depreciation expense depending on working time, the cost rate is constructed for each random maintenance policy and some special cases are provided by discussing parameters in cost rates. Finally, sensitivities on both the proposed warranty and random maintenance policies are analyzed in numerical experiments.Design/methodology/approachThe working cycle of products can be monitored by advanced sensors and measuring technologies. By monitoring the working cycle, manufacturers can design warranty policies to ensure product reliability performance and consumers can model the post-warranty maintenance to sustain the post-warranty reliability. In this article, the authors design a limited number of random working cycles as a warranty term and propose two types of warranties, which can help manufacturers to ensure the product reliability performance during the warranty period. By extending a proposed warranty to the consumer's post-warranty maintenance model, the authors investigate two kinds of random replacement policies to sustain the post-warranty reliability, i.e. random replacement first and random replacement last. By integrating a depreciation expense depending on working time, the cost rate is constructed for each random replacement and some special cases are provided by discussing parameters in the cost rate. Finally, sensitivities to both the proposed warranties and random replacements are analyzed in numerical experiments.FindingsIt is shown that the manufacturer can control the warranty cost by limiting number of random working cycle. For the consumer, when the number of random working cycle is designed as a greater warranty limit, the cost rate can be reduced while the post-warranty period can't be lengthened.Originality/valueThe contribution of this article can be highlighted in two key aspects: (1) the authors investigate early warranties to ensure reliability performance of the product which executes successively projects at random working cycles; (2) by integrating random working cycles into the post-warranty period, the authors is the first to investigate random maintenance policy to sustain the post-warranty reliability from the consumer's perspective, which seldom appears in the existing literature.
{"title":"Random replacement policies to sustain the post-warranty reliability","authors":"Lijun Shang, Qingan Qiu, Cang Wu, Yongjun Du","doi":"10.1108/jqme-09-2021-0067","DOIUrl":"https://doi.org/10.1108/jqme-09-2021-0067","url":null,"abstract":"PurposeThe study aims to design the limited number of random working cycle as a warranty term and propose two types of warranties, which can help manufacturers to ensure the product reliability during the warranty period. By extending the proposed warranty to the consumer's post-warranty maintenance model, besides the authors investigate two kinds of random maintenance policies to sustain the post-warranty reliability, i.e. random replacement first and random replacement last. By integrating depreciation expense depending on working time, the cost rate is constructed for each random maintenance policy and some special cases are provided by discussing parameters in cost rates. Finally, sensitivities on both the proposed warranty and random maintenance policies are analyzed in numerical experiments.Design/methodology/approachThe working cycle of products can be monitored by advanced sensors and measuring technologies. By monitoring the working cycle, manufacturers can design warranty policies to ensure product reliability performance and consumers can model the post-warranty maintenance to sustain the post-warranty reliability. In this article, the authors design a limited number of random working cycles as a warranty term and propose two types of warranties, which can help manufacturers to ensure the product reliability performance during the warranty period. By extending a proposed warranty to the consumer's post-warranty maintenance model, the authors investigate two kinds of random replacement policies to sustain the post-warranty reliability, i.e. random replacement first and random replacement last. By integrating a depreciation expense depending on working time, the cost rate is constructed for each random replacement and some special cases are provided by discussing parameters in the cost rate. Finally, sensitivities to both the proposed warranties and random replacements are analyzed in numerical experiments.FindingsIt is shown that the manufacturer can control the warranty cost by limiting number of random working cycle. For the consumer, when the number of random working cycle is designed as a greater warranty limit, the cost rate can be reduced while the post-warranty period can't be lengthened.Originality/valueThe contribution of this article can be highlighted in two key aspects: (1) the authors investigate early warranties to ensure reliability performance of the product which executes successively projects at random working cycles; (2) by integrating random working cycles into the post-warranty period, the authors is the first to investigate random maintenance policy to sustain the post-warranty reliability from the consumer's perspective, which seldom appears in the existing literature.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49167862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-22DOI: 10.1108/jqme-01-2021-0007
Suleyman Muftuoglu, E. Çevikcan, B. Durmuşoğlu
PurposeThe purpose of this paper is to support total productive maintenance implementers by providing a roadmap for autonomous maintenance (AM) preparation phase.Design/methodology/approachThe authors use the axiomatic design (AD) methodology with lean philosophy as a paradigm.FindingsThis is an exploratory research to find the most important factors in AM preparation phase. A decoupled AD design ensures an effective usage of training within industry (TWI) and the introduction of standardized work (SW). TWI provides value in importance it assigns to leaders, with its “train the trainers” approach and in preparing a training program. Besides being an effective training method, TWI job instruction (TWI JI) provides needed information infrastructure to front load operators SW and equipment trainings.Research limitations/implicationsAlthough AD, TWI and lean artifacts are generally field proven, the research is limited due to the lack of an industrial application.Practical implicationsIn many real-life projects, companies do not know where to start and how to proceed, which leads to costly iterations. The proposed roadmap minimizes iterations and increases the chance of project success.Originality/valueThe authors apply AD for the first time to AM preparation phase despite it is used in the analysis of lean manufacturing. AD permits to structure holistically the most relevant lean manufacturing solutions to obtain a risk free roadmap. TWI has emerged as a training infrastructure; TWI JI-based operator SW training and the adaptation of JI structure to equipment training are original additions.
{"title":"Autonomous maintenance preparation system design with axioms","authors":"Suleyman Muftuoglu, E. Çevikcan, B. Durmuşoğlu","doi":"10.1108/jqme-01-2021-0007","DOIUrl":"https://doi.org/10.1108/jqme-01-2021-0007","url":null,"abstract":"PurposeThe purpose of this paper is to support total productive maintenance implementers by providing a roadmap for autonomous maintenance (AM) preparation phase.Design/methodology/approachThe authors use the axiomatic design (AD) methodology with lean philosophy as a paradigm.FindingsThis is an exploratory research to find the most important factors in AM preparation phase. A decoupled AD design ensures an effective usage of training within industry (TWI) and the introduction of standardized work (SW). TWI provides value in importance it assigns to leaders, with its “train the trainers” approach and in preparing a training program. Besides being an effective training method, TWI job instruction (TWI JI) provides needed information infrastructure to front load operators SW and equipment trainings.Research limitations/implicationsAlthough AD, TWI and lean artifacts are generally field proven, the research is limited due to the lack of an industrial application.Practical implicationsIn many real-life projects, companies do not know where to start and how to proceed, which leads to costly iterations. The proposed roadmap minimizes iterations and increases the chance of project success.Originality/valueThe authors apply AD for the first time to AM preparation phase despite it is used in the analysis of lean manufacturing. AD permits to structure holistically the most relevant lean manufacturing solutions to obtain a risk free roadmap. TWI has emerged as a training infrastructure; TWI JI-based operator SW training and the adaptation of JI structure to equipment training are original additions.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43832577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-19DOI: 10.1108/jqme-10-2020-0107
D. Divya, Bhasi Marath, M. B. Santosh Kumar
PurposeThis study aims to bring awareness to the developing of fault detection systems using the data collected from sensor devices/physical devices of various systems for predictive maintenance. Opportunities and challenges in developing anomaly detection algorithms for predictive maintenance and unexplored areas in this context are also discussed.Design/methodology/approachFor conducting a systematic review on the state-of-the-art algorithms in fault detection for predictive maintenance, review papers from the years 2017–2021 available in the Scopus database were selected. A total of 93 papers were chosen. They are classified under electrical and electronics, civil and constructions, automobile, production and mechanical. In addition to this, the paper provides a detailed discussion of various fault-detection algorithms that can be categorised under supervised, semi-supervised, unsupervised learning and traditional statistical method along with an analysis of various forms of anomalies prevalent across different sectors of industry.FindingsBased on the literature reviewed, seven propositions with a focus on the following areas are presented: need for a uniform framework while scaling the number of sensors; the need for identification of erroneous parameters; why there is a need for new algorithms based on unsupervised and semi-supervised learning; the importance of ensemble learning and data fusion algorithms; the necessity of automatic fault diagnostic systems; concerns about multiple fault detection; and cost-effective fault detection. These propositions shed light on the unsolved issues of predictive maintenance using fault detection algorithms. A novel architecture based on the methodologies and propositions gives more clarity for the reader to further explore in this area.Originality/valuePapers for this study were selected from the Scopus database for predictive maintenance in the field of fault detection. Review papers published in this area deal only with methods used to detect anomalies, whereas this paper attempts to establish a link between different industrial domains and the methods used in each industry that uses fault detection for predictive maintenance.
{"title":"Review of fault detection techniques for predictive maintenance","authors":"D. Divya, Bhasi Marath, M. B. Santosh Kumar","doi":"10.1108/jqme-10-2020-0107","DOIUrl":"https://doi.org/10.1108/jqme-10-2020-0107","url":null,"abstract":"PurposeThis study aims to bring awareness to the developing of fault detection systems using the data collected from sensor devices/physical devices of various systems for predictive maintenance. Opportunities and challenges in developing anomaly detection algorithms for predictive maintenance and unexplored areas in this context are also discussed.Design/methodology/approachFor conducting a systematic review on the state-of-the-art algorithms in fault detection for predictive maintenance, review papers from the years 2017–2021 available in the Scopus database were selected. A total of 93 papers were chosen. They are classified under electrical and electronics, civil and constructions, automobile, production and mechanical. In addition to this, the paper provides a detailed discussion of various fault-detection algorithms that can be categorised under supervised, semi-supervised, unsupervised learning and traditional statistical method along with an analysis of various forms of anomalies prevalent across different sectors of industry.FindingsBased on the literature reviewed, seven propositions with a focus on the following areas are presented: need for a uniform framework while scaling the number of sensors; the need for identification of erroneous parameters; why there is a need for new algorithms based on unsupervised and semi-supervised learning; the importance of ensemble learning and data fusion algorithms; the necessity of automatic fault diagnostic systems; concerns about multiple fault detection; and cost-effective fault detection. These propositions shed light on the unsolved issues of predictive maintenance using fault detection algorithms. A novel architecture based on the methodologies and propositions gives more clarity for the reader to further explore in this area.Originality/valuePapers for this study were selected from the Scopus database for predictive maintenance in the field of fault detection. Review papers published in this area deal only with methods used to detect anomalies, whereas this paper attempts to establish a link between different industrial domains and the methods used in each industry that uses fault detection for predictive maintenance.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42141824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-07DOI: 10.1108/jqme-04-2021-0033
A. Duarte, Marcia Regina Santiago Santiago Scarpin
PurposeThis study aims to identify the relationship between different maintenance practices and productive efficiency in continuous process productive plants as well as the moderating effect of good training practices.Design/methodology/approachThe empirical data were drawn from a database containing 609 observations of 29 productive units. Scales were validated using the Q-sort method. The panel data technique was used as the analysis methodology, with the inclusion of fixed effects for each productive plant.FindingsMaintenance practices can effectively contribute to increasing the overall equipment effectiveness (OEE) of firms. Application of predictive maintenance practices should be considered as the primary training tool.Research limitations/implicationsThis study used a secondary database, limiting the research design and data manipulation.Practical implicationsThe article provides practitioners with an analysis of maintenance practices by category (predictive, preventive and corrective), and the impact of each practice on the OEE of continuous process productive plants. Moreover, it explores the importance of training for extracting more results from maintenance practices.Social implicationsCompanies are investing in new technologies, but it is also essential to invest in training people. There is a demand for Industry 4.0 through the introduction of upskilling and reskilling programs.Originality/valueThis study used practice-based view (PBV) theory to explain how maintenance practices help firms achieve greater OEE. Furthermore, it introduced training practice as a moderating variable in the relationship between maintenance practices and OEE.
{"title":"Maintenance practices and overall equipment effectiveness: testing the moderating effect of training","authors":"A. Duarte, Marcia Regina Santiago Santiago Scarpin","doi":"10.1108/jqme-04-2021-0033","DOIUrl":"https://doi.org/10.1108/jqme-04-2021-0033","url":null,"abstract":"PurposeThis study aims to identify the relationship between different maintenance practices and productive efficiency in continuous process productive plants as well as the moderating effect of good training practices.Design/methodology/approachThe empirical data were drawn from a database containing 609 observations of 29 productive units. Scales were validated using the Q-sort method. The panel data technique was used as the analysis methodology, with the inclusion of fixed effects for each productive plant.FindingsMaintenance practices can effectively contribute to increasing the overall equipment effectiveness (OEE) of firms. Application of predictive maintenance practices should be considered as the primary training tool.Research limitations/implicationsThis study used a secondary database, limiting the research design and data manipulation.Practical implicationsThe article provides practitioners with an analysis of maintenance practices by category (predictive, preventive and corrective), and the impact of each practice on the OEE of continuous process productive plants. Moreover, it explores the importance of training for extracting more results from maintenance practices.Social implicationsCompanies are investing in new technologies, but it is also essential to invest in training people. There is a demand for Industry 4.0 through the introduction of upskilling and reskilling programs.Originality/valueThis study used practice-based view (PBV) theory to explain how maintenance practices help firms achieve greater OEE. Furthermore, it introduced training practice as a moderating variable in the relationship between maintenance practices and OEE.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47503981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-10DOI: 10.1108/jqme-06-2021-0047
N. Tao
PurposeIn this study, the focus was shifted from repairing durable goods to achieving healthier ecology, making durable goods more secure in turn. This study introduced preventive maintenance behavior to trace the ex-post control of “curling” back to the ex-post control of “self-healing.” This study tries to close the gap between the human repair of machines and their “self-curing.” Finally, the author makes the machines healthier.Design/methodology/approachThe paper constructed a mathematical model of preventive maintenance behavior during a specific period for durable consumer goods. The author builds a simulation function of the two-stage preventative maintenance behavior relations. The study used simulations to analyze the influencing relationship and differences between three preventive maintenance behavior elements to basic warranty preventive maintenance (BWPM) behavior and extended warranty preventive maintenance (EWPM) behavior.FindingsBoth BWPM behavior and EWPM behavior were affected by the preventive maintenance (PM) behavioral components in different ways. The influence paths of the two warranty periods affected by PM behavior were also different.Research limitations/implicationsThis study introduced PM behavior to trace the ex-post control of “curling” back to the ex-post control of “self-healing.” This study adopted the human–machine interaction mode to improve durable goods' self-healing ability during operation and enable a more effective and sustainable development.Practical implicationsThis study’s conclusions may help manufacturers guide PM behavior in a way that achieves “self-healing” of the durable goods.Originality/valueThe author opened a “black box” of PM behaviors and analyzed their components. The internal structure relation of PM behavior is built and the closed-loop system of spatial structure is formed.
{"title":"The self-healing ability of durable consumer goods through preventive maintenance behavior","authors":"N. Tao","doi":"10.1108/jqme-06-2021-0047","DOIUrl":"https://doi.org/10.1108/jqme-06-2021-0047","url":null,"abstract":"PurposeIn this study, the focus was shifted from repairing durable goods to achieving healthier ecology, making durable goods more secure in turn. This study introduced preventive maintenance behavior to trace the ex-post control of “curling” back to the ex-post control of “self-healing.” This study tries to close the gap between the human repair of machines and their “self-curing.” Finally, the author makes the machines healthier.Design/methodology/approachThe paper constructed a mathematical model of preventive maintenance behavior during a specific period for durable consumer goods. The author builds a simulation function of the two-stage preventative maintenance behavior relations. The study used simulations to analyze the influencing relationship and differences between three preventive maintenance behavior elements to basic warranty preventive maintenance (BWPM) behavior and extended warranty preventive maintenance (EWPM) behavior.FindingsBoth BWPM behavior and EWPM behavior were affected by the preventive maintenance (PM) behavioral components in different ways. The influence paths of the two warranty periods affected by PM behavior were also different.Research limitations/implicationsThis study introduced PM behavior to trace the ex-post control of “curling” back to the ex-post control of “self-healing.” This study adopted the human–machine interaction mode to improve durable goods' self-healing ability during operation and enable a more effective and sustainable development.Practical implicationsThis study’s conclusions may help manufacturers guide PM behavior in a way that achieves “self-healing” of the durable goods.Originality/valueThe author opened a “black box” of PM behaviors and analyzed their components. The internal structure relation of PM behavior is built and the closed-loop system of spatial structure is formed.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48735849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-07DOI: 10.1108/jqme-04-2021-0030
Nzita Alain Lelo, P. Stephan Heyns, Johann Wannenburg
PurposeIndustry decision makers often rely on a risk-based approach to perform inspection and maintenance planning. According to the Risk-Based Inspection and Maintenance Procedure project for the European industry, risk has two main components: probability of failure (PoF) and consequence of failure (CoF). As one of these risk drivers, a more accurate estimation of the PoF will contribute to a more accurate risk assessment. Current methods to estimate the PoF are either time-based or founded on expert judgement. This paper suggests an approach that incorporates the proportional hazards model (PHM), which is a statistical procedure to estimate the risk of failure for a component subject to condition monitoring, into the risk-based inspection (RBI) methodology, so that the PoF estimation is enhanced to optimize inspection policies.Design/methodology/approachTo achieve the overall goal of this paper, a case study applying the PHM to determine the PoF for the real-time condition data component is discussed. Due to a lack of published data for risk assessment at this stage of the research, the case study considered here uses failure data obtained from the simple but readily available Intelligent Maintenance Systems bearing data, to illustrate the methodology.FindingsThe benefit of incorporating PHM into the RBI approach is that PHM uses real-time condition data, allowing dynamic decision-making on inspection and maintenance planning. An additional advantage of the PHM is that where traditional techniques might not give an accurate estimation of the remaining useful life to plan inspection, the PHM method has the ability to consider the condition as well as the age of the component.Research limitations/implicationsThis paper is proposing the development of an approach to incorporate the PHM into an RBI methodology using bearing data to illustrate the methodology. The CoF estimation is not addressed in this paper.Originality/valueThis paper presents the benefits related to the use of PHM as an approach to optimize the PoF estimation, which drives to the optimal risk assessment, in comparison to the time-based approach.
{"title":"Development of an approach to incorporate proportional hazard modelling into a risk-based inspection methodology","authors":"Nzita Alain Lelo, P. Stephan Heyns, Johann Wannenburg","doi":"10.1108/jqme-04-2021-0030","DOIUrl":"https://doi.org/10.1108/jqme-04-2021-0030","url":null,"abstract":"PurposeIndustry decision makers often rely on a risk-based approach to perform inspection and maintenance planning. According to the Risk-Based Inspection and Maintenance Procedure project for the European industry, risk has two main components: probability of failure (PoF) and consequence of failure (CoF). As one of these risk drivers, a more accurate estimation of the PoF will contribute to a more accurate risk assessment. Current methods to estimate the PoF are either time-based or founded on expert judgement. This paper suggests an approach that incorporates the proportional hazards model (PHM), which is a statistical procedure to estimate the risk of failure for a component subject to condition monitoring, into the risk-based inspection (RBI) methodology, so that the PoF estimation is enhanced to optimize inspection policies.Design/methodology/approachTo achieve the overall goal of this paper, a case study applying the PHM to determine the PoF for the real-time condition data component is discussed. Due to a lack of published data for risk assessment at this stage of the research, the case study considered here uses failure data obtained from the simple but readily available Intelligent Maintenance Systems bearing data, to illustrate the methodology.FindingsThe benefit of incorporating PHM into the RBI approach is that PHM uses real-time condition data, allowing dynamic decision-making on inspection and maintenance planning. An additional advantage of the PHM is that where traditional techniques might not give an accurate estimation of the remaining useful life to plan inspection, the PHM method has the ability to consider the condition as well as the age of the component.Research limitations/implicationsThis paper is proposing the development of an approach to incorporate the PHM into an RBI methodology using bearing data to illustrate the methodology. The CoF estimation is not addressed in this paper.Originality/valueThis paper presents the benefits related to the use of PHM as an approach to optimize the PoF estimation, which drives to the optimal risk assessment, in comparison to the time-based approach.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48202600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-01DOI: 10.1108/jqme-11-2021-0087
Nand Gopal, Dilbagh Panchal
PurposeThe proposed hybridized framework provides a new performance optimization-based paradigm for analysing the failure behaviour of paneer unit (PU) in the dairy industry.Design/methodology/approachA novel fuzzy Jaya-based Lambda–Tau Optimization (JBLTO) approach-based mathematical modelling was developed for calculating various reliability indices of the considered unit. Failure mode and effect analysis (FMEA) was carried using qualitative information gathered from system's expert opinions. Fuzzy-complex proportional assessment (FCOPRAS) approach was integrated within FMEA to recognize the most critical failure causes associated with various subsystem/components.FindingsThe availability of the unit falls by 0.053% as the uncertainty level increases from ±15 to ±25% and further decreases to 0.323% as the uncertainty level increases from ±25 to ±60%. Failure causes, namely wearing in gears of gearbox (MST4), an impeller's cavitation and/or corrosion (CFP4), winding failure of electric motor (WS9), were recognized as the most critical failure causes with FCOPRAS final performance scores of 100, 100 and 100 and fuzzy combinative distance-based assessment (FCODAS) resultant assessment score of 0.5997, 1.1898 and 1.6135.Originality/valueJBLTO approach-based reliability results were compared with traditional particle swarm optimization-based Lambda–Tau (PSOBLT) and traditional fuzzy Lambda–Tau (FLT) approaches for confirming the downward trend in the system's availability. The ranking results of qualitative analysis are compared with the implementation of FCODAS technique. Sensitivity analysis was executed to evaluate the robustness of the proposed hybridized framework.
{"title":"A structured framework for performance optimization using JBLTO, FCOPRAS and FCODAS methodologies","authors":"Nand Gopal, Dilbagh Panchal","doi":"10.1108/jqme-11-2021-0087","DOIUrl":"https://doi.org/10.1108/jqme-11-2021-0087","url":null,"abstract":"PurposeThe proposed hybridized framework provides a new performance optimization-based paradigm for analysing the failure behaviour of paneer unit (PU) in the dairy industry.Design/methodology/approachA novel fuzzy Jaya-based Lambda–Tau Optimization (JBLTO) approach-based mathematical modelling was developed for calculating various reliability indices of the considered unit. Failure mode and effect analysis (FMEA) was carried using qualitative information gathered from system's expert opinions. Fuzzy-complex proportional assessment (FCOPRAS) approach was integrated within FMEA to recognize the most critical failure causes associated with various subsystem/components.FindingsThe availability of the unit falls by 0.053% as the uncertainty level increases from ±15 to ±25% and further decreases to 0.323% as the uncertainty level increases from ±25 to ±60%. Failure causes, namely wearing in gears of gearbox (MST4), an impeller's cavitation and/or corrosion (CFP4), winding failure of electric motor (WS9), were recognized as the most critical failure causes with FCOPRAS final performance scores of 100, 100 and 100 and fuzzy combinative distance-based assessment (FCODAS) resultant assessment score of 0.5997, 1.1898 and 1.6135.Originality/valueJBLTO approach-based reliability results were compared with traditional particle swarm optimization-based Lambda–Tau (PSOBLT) and traditional fuzzy Lambda–Tau (FLT) approaches for confirming the downward trend in the system's availability. The ranking results of qualitative analysis are compared with the implementation of FCODAS technique. Sensitivity analysis was executed to evaluate the robustness of the proposed hybridized framework.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45375357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-17DOI: 10.1108/jqme-08-2021-0064
Umama Rahman, Miraj Uddin Mahbub
PurposeThe data created from regular maintenance activities of equipment are stored as text in industrial plants. The size of these data is increasing rapidly nowadays. Text mining provides a chance to handle this huge amount of text data and extract meaningful information to improve various processes of an industrial environment. This paper represents the application of classification models on maintenance text records to classify failure for improving maintenance programs in the industry.Design/methodology/approachThis paper is presented as an implementation study, where text mining approaches are used for binary classification of text data. Naive Bayes and Support Vector Machine (SVM), two classification algorithms are applied for training and testing of the models as per the labeled data. The reason behind this is, these algorithms perform better on text data for classifying failure and they are easy to handle. A methodology is proposed for the development of maintenance programs, including classification of potential failure in advance by analyzing the regular maintenance data as well as comparing the performance of both models on the data.FindingsThe accuracy of both models falls within the acceptable limit, and performance evaluation of the models concludes the validation of the results. Other performance measures exhibit excellent values for both of the models.Practical implicationsThe proposed approach provides the maintenance team an opportunity to know about the upcoming breakdown in advance so that necessary measures can be taken to prevent failure in an industrial environment. As predictive maintenance incurs a high expense, it could be a better replacement for small and medium industrial plants.Originality/valueNowadays, maintenance is preventive-based rather than a corrective approach. The proposed technique is facilitating the concept of a proactive approach by minimizing the cost of additional maintenance steps. As predictive maintenance is efficient but incurs high expenses, this proposed method can minimize unnecessary maintenance operations and keep control over the budget. This is a significant way of developing maintenance programs and will make maintenance personnel ready for the machine breakdown.
{"title":"Application of classification models on maintenance records through text mining approach in industrial environment","authors":"Umama Rahman, Miraj Uddin Mahbub","doi":"10.1108/jqme-08-2021-0064","DOIUrl":"https://doi.org/10.1108/jqme-08-2021-0064","url":null,"abstract":"PurposeThe data created from regular maintenance activities of equipment are stored as text in industrial plants. The size of these data is increasing rapidly nowadays. Text mining provides a chance to handle this huge amount of text data and extract meaningful information to improve various processes of an industrial environment. This paper represents the application of classification models on maintenance text records to classify failure for improving maintenance programs in the industry.Design/methodology/approachThis paper is presented as an implementation study, where text mining approaches are used for binary classification of text data. Naive Bayes and Support Vector Machine (SVM), two classification algorithms are applied for training and testing of the models as per the labeled data. The reason behind this is, these algorithms perform better on text data for classifying failure and they are easy to handle. A methodology is proposed for the development of maintenance programs, including classification of potential failure in advance by analyzing the regular maintenance data as well as comparing the performance of both models on the data.FindingsThe accuracy of both models falls within the acceptable limit, and performance evaluation of the models concludes the validation of the results. Other performance measures exhibit excellent values for both of the models.Practical implicationsThe proposed approach provides the maintenance team an opportunity to know about the upcoming breakdown in advance so that necessary measures can be taken to prevent failure in an industrial environment. As predictive maintenance incurs a high expense, it could be a better replacement for small and medium industrial plants.Originality/valueNowadays, maintenance is preventive-based rather than a corrective approach. The proposed technique is facilitating the concept of a proactive approach by minimizing the cost of additional maintenance steps. As predictive maintenance is efficient but incurs high expenses, this proposed method can minimize unnecessary maintenance operations and keep control over the budget. This is a significant way of developing maintenance programs and will make maintenance personnel ready for the machine breakdown.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43887372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-24DOI: 10.1108/jqme-06-2021-0052
Laura Isabel Alvarez Quiñones, Carlos Arturo Lozano-Moncada, Diego Alberto Bravo Montenegro
PurposeThe purpose of this paper is to describe a methodology that has been set up to schedule predictive maintenance of distribution transformers at Cauca Department (Colombia) using machine learning.Design/methodology/approachThe proposed methodology relies on classification predictive model that finds the minimal number of distribution transformers prone to failure. To verify this, the model was implemented and tested with real data in Cauca Department Colombia.FindingsThe implementation of the methodology allows a saving of 13% in corrective maintenance expenses for the year 2020.Originality/valueThe proposed model is an effective decision-making tool that provides an ideal solution for preventive maintenance scheduling problems for distribution transformers.
{"title":"Machine learning for predictive maintenance scheduling of distribution transformers","authors":"Laura Isabel Alvarez Quiñones, Carlos Arturo Lozano-Moncada, Diego Alberto Bravo Montenegro","doi":"10.1108/jqme-06-2021-0052","DOIUrl":"https://doi.org/10.1108/jqme-06-2021-0052","url":null,"abstract":"PurposeThe purpose of this paper is to describe a methodology that has been set up to schedule predictive maintenance of distribution transformers at Cauca Department (Colombia) using machine learning.Design/methodology/approachThe proposed methodology relies on classification predictive model that finds the minimal number of distribution transformers prone to failure. To verify this, the model was implemented and tested with real data in Cauca Department Colombia.FindingsThe implementation of the methodology allows a saving of 13% in corrective maintenance expenses for the year 2020.Originality/valueThe proposed model is an effective decision-making tool that provides an ideal solution for preventive maintenance scheduling problems for distribution transformers.","PeriodicalId":16938,"journal":{"name":"Journal of Quality in Maintenance Engineering","volume":" ","pages":""},"PeriodicalIF":1.5,"publicationDate":"2022-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49194505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}