Designing predictive maintenance systems using decision tree-based machine learning techniques

Predictive maintenance in Industry 4.0: a survey of planning models and machine learning techniques

Equipment downtime resulting from maintenance in various sectors around the globe has become a major concern. The effectiveness of conventional reactive maintenance methods in addressing interruptions and enhancing operational efficiency has become inadequate. Therefore, acknowledging the constraints associated with reactive maintenance and the growing need for proactive approaches to proactively detect possible breakdowns is necessary. The need for optimisation of asset management and reduction of costly downtime emerges from the demand for industries. The work highlights the use of Internet of Things (IoT)-enabled Predictive Maintenance (PdM) as a revolutionary strategy across many sectors. This article presents a picture of a future in which the use of IoT technology and sophisticated analytics will enable the prediction and proactive mitigation of probable equipment failures. This literature study has great importance as it thoroughly explores the complex steps and techniques necessary for the development and implementation of efficient PdM solutions. The study offers useful insights into the optimisation of maintenance methods and the enhancement of operational efficiency by analysing current information and approaches. The article outlines essential stages in the application of PdM, encompassing underlying design factors, data preparation, feature selection, and decision modelling. Additionally, the study discusses a range of ML models and methodologies for monitoring conditions. In order to enhance maintenance plans, it is necessary to prioritise ongoing study and improvement in the field of PdM. The potential for boosting PdM skills and guaranteeing the competitiveness of companies in the global economy is significant through the incorporation of IoT, Artificial Intelligence (AI), and advanced analytics.

Analysis of barriers affecting Industry 4.0 implementation: An interpretive analysis using total interpretive structural modeling (TISM) and Fuzzy MICMAC

The purpose of this study is to build a structural relationship model based on total interpretive structural modeling (TISM) and fuzzy input-based cross-impact matrix multiplication applied to classification (MICMAC) for analysis and prioritization of the barriers influencing the implementation of Industry 4.0 technologies. 10 crucial barriers that affect the deployment of Industry 4.0 techniques are identified in the literature. Also, the Fuzzy MICMAC approach is applied to classify the barriers. The importance of TISM over traditional interpretive structural modeling (ISM) is shown in this work. Results proved that the barriers, namely IT infrastructure, lack of cyber physical systems, and improper communication models, are identified as the most dependent barriers, and the barriers of lack of top management commitment and inadequate training are identified as the most driving barriers. This study makes it easier for decision-makers to take the necessary steps to mitigate the barriers. The bottom level of the TISM hierarchy is occupied by barriers that need more attention from top management in order to be effectively monitored and managed. This study explains the steps to execute TISM in detail, making it easy for researchers and practitioners to comprehend its principles.

Analysis of maintenance outsourcing challenges for belt conveyors in the Industry 4.0 era

Purpose

There is an increasing trend of outsourcing maintenance activities of heavy equipment, including belt conveyor installations. However, there are numerous challenges in maintenance outsourcing. This paper aims to identify and analyze various challenges of outsourcing maintenance activities associated with belt conveyor installations.

Design/methodology/approach

This paper identifies maintenance outsourcing challenges of belt conveyor installations through literature review, field visits and expert opinion. An integrated structural hierarchical framework of the identified challenges is developed through analytic hierarchy process and decision-making trial and evaluation laboratory.

Findings

The paper has identified eight challenges, namely, attainment of organizational strength by contractors, legal and financial challenges for contractors, attainment of necessary technician skills by contractors, maintenance data acquisition and analysis challenges, facilitation with modern equipment, gadgets and instrumentation, service quality challenges, health, safety and environment-related challenges and spares supply chain management challenges. The segregation of driver and dependent challenges, including their hierarchical framework had been established in this work.

Research limitations/implications

A comprehensive list of challenges and their prioritization in maintenance outsourcing of belt conveyor installations had been established. This will help the organizations who own and operate these installations to make judicious decisions regarding outsourcing maintenance.

Originality/value

This paper significantly contributes to the literature on maintenance outsourcing of heavy machinery installations like a belt conveyor system based on the input of different stakeholders. This study will lead to the development of frameworks for maintenance contractor selection for such installations.

Maintenance 4.0: implementation challenges and its analysis

Purpose

The purpose of this paper is to identify and analyze the challenges associated with the implementation of the concept of Maintenance 4.0 in industries.

Design/methodology/approach

The challenges in the implementation of Maintenance 4.0 are identified through a literature survey and interaction with professionals from the industry and academia. A structural hierarchy framework that integrates the methodologies of ISM and MICMAC is used for the analysis of Maintenance 4.0 implementation challenges. The framework establishes the interrelationship among challenges and segregates them into driving, linkage, dependent and autonomous groups.

Findings

A novel concept of Maintenance 4.0 under the aegis of Industry 4.0 is gaining appreciation worldwide. However, there are challenges in the adaptation of Maintenance 4.0 concepts among industries. The various challenges as well as their impact on the objective of implementation of Maintenance 4.0 are identified.

Practical implications

The practicing engineers, academicians, researchers and the concerned industries can infer from the results to improve upon the causes of such challenges and promote the implementation of Maintenance 4.0 most efficiently and effectively.

Originality/value

This paper is a novel, unique and first of its kind that addresses the most contemporary challenges in the implementation of Maintenance 4.0 concepts in industries.

Machine learning-based failure prediction in industrial maintenance: improving performance by sliding window selection

Purpose

Machine learning (ML) models are increasingly being used in industrial maintenance to predict system failures. However, less is known about how the time windows for reading data and making predictions affect performance. Therefore, the purpose of this research is to assess the impact of different sliding windows on prediction performance.

Design/methodology/approach

The authors conducted a factorial experiment using high dimensional machine data covering two years of operation, taken from a real industrial case for the production of high-precision milled and turned parts. The impacts of different reading and prediction windows were tested for three ML algorithms (random forest, support vector machines and logistic regression) and four metrics (accuracy, precision, recall and F-score).

Findings

The results reveal (1) the critical role of the prediction window contingent upon the application domain, (2) a non-monotonic relationship between the reading window and performance, and (3) how sliding window selection can systematically be used to improve different facets of performance.

Originality/value

The study's findings advance the knowledge of ML-based failure prediction, by highlighting how systematic variation of two important but yet understudied factors contributes to the development of more useful prediction models.

Examining the impact of deep learning technology capability on manufacturing firms: moderating roles of technology turbulence and top management support

Data science can create value by extracting structured and unstructured data using an appropriate algorithm. Data science operations have undergone drastic changes because of accelerated deep learning progress. Deep learning is an advanced process of machine learning algorithm. Its simple process of presenting data to the system is sharply different from other machine learning processes. Deep learning uses advanced analytics to solve complex problems for accurate business decisions. Deep leaning is considered a promising area for creating additional value in firms' productivity and sustainability as they develop their smart manufacturing activities. Deep learning capability can help a manufacturing firm's predictive maintenance, quality control, and anomaly detection. The impact of deep learning technology capability on manufacturing firms is an underexplored area in the literature. With this background, the purpose of this study is to examine the impact of deep learning technology capability on manufacturing firms with moderating roles of deep learning related technology turbulence and top management support of the manufacturing firms. With the help of literature review and theories, a conceptual model has been prepared, which is then validated with the PLS-SEM technique analyzing 473 responses from employees of manufacturing firms. The study shows the significance of deep learning technology capability on smart manufacturing systems. Also, the study highlights the moderating impacts of top management team (TMT) support as well as the moderating impacts of deep learning related technology turbulence on smart manufacturing systems.

Principal component analysis technique for early fault detection

Online condition monitoring and predictive maintenance are crucial for the safe operation of equipments. This paper highlights an unsupervised statistical algorithm based on principal component analysis (PCA) for the predictive maintenance of industrial induced draft (ID) fan. The high vibration issues in ID fans cause the failure of the impellers and, sometimes, the complete breakdown of the fan-motor system. The condition monitoring system of the equipment should be reliable and avoid such a sudden breakdown or faults in the equipment. The proposed technique predicts the fault of the ID fan-motor system, being applicable for other rotating industrial equipment, and also for which the failure data, or historical data, is not available. The major problem in the industry is the monitoring of each and every machinery individually. To avoid this problem, three identical ID fans are monitored together using the proposed technique. This helps in the prediction of the faulty part and also the time left for the complete breakdown of the fan-motor system. This helps in forecasting the maintenance schedule for the equipment before breakdown. From the results, it is observed that the PCA-based technique is a good fit for early fault detection and getting alarmed under fault condition as compared with the conventional methods, including signal trend and fast Fourier transform (FFT) analysis.

Data-driven approach to predict the sequence of component failures: a framework and a case study on a process industry

Purpose

The research approach is based on the concept that a failure event is rarely random and is often generated by a chain of previous events connected by a sort of domino effect. Thus, the purpose of this study is the optimal selection of the components to predictively maintain on the basis of their failure probability, under budget and time constraints.

Design/methodology/approach

Assets maintenance is a major challenge for any process industry. Thanks to the development of Big Data Analytics techniques and tools, data produced by such systems can be analyzed in order to predict their behavior. Considering the asset as a social system composed of several interacting components, in this work, a framework is developed to identify the relationships between component failures and to avoid them through the predictive replacement of critical ones: such relationships are identified through the Association Rule Mining (ARM), while their interaction is studied through the Social Network Analysis (SNA).

Findings

A case example of a process industry is presented to explain and test the proposed model and to discuss its applicability. The proposed framework provides an approach to expand upon previous work in the areas of prediction of fault events and monitoring strategy of critical components.

Originality/value

The novel combined adoption of ARM and SNA is proposed to identify the hidden interaction among events and to define the nature of such interactions and communities of nodes in order to analyze local and global paths and define the most influential entities.

Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis

Accurately predicting the remaining useful life (RUL) of the turbofan engine is of great significance for improving the reliability and safety of the engine system. Due to the high dimension and complex features of sensor data in RUL prediction, this paper proposes four data-driven prognostic models based on deep neural networks (DNNs) with an attention mechanism. To improve DNN feature extraction, data are prepared using a sliding time window technique. The raw data collected after normalizing is simply fed into the suggested network, requiring no prior knowledge of prognostics or signal processing and simplifying the proposed method’s applicability. In order to verify the RUL prediction ability of the proposed DNN techniques, the C-MAPSS benchmark dataset of the turbofan engine system is validated. The experimental results showed that the developed long short-term memory (LSTM) model with attention mechanism achieved accurate RUL prediction in both scenarios with a high degree of robustness and generalization ability. Furthermore, the proposed model performance outperforms several state-of-the-art prognosis methods, where the LSTM-based model with attention mechanism achieved an RMSE of 12.87 and 11.23 for FD002 and FD003 subset of data, respectively.

IDENTIFYING START-UP PARTNERS: WHICH SEARCH PRACTICES AND COMBINATION STRATEGIES ARE EFFECTIVE?

Start-ups are an important source of novel knowledge and product ideas for incumbents. We investigate which search strategies are positively related to the successful search for start-ups. We identify search instruments and their various uses: intensive or broad; stand-alone or combinatory. Finding 11 search practices in the literature, we evaluate how these practices were used by 97 respondents from a cross-industry and cross-national sample. Our results show that searching broadly and intensively is positively related to a successful search for start-ups and to firms’ radical innovation capability. Specific tools that are positively related to search success are online contacts, desk research, external scouting partners, and start-up pitch events. Decision tree analysis provides effective combinations of search practices that innovation managers and purchasing managers can use. Employing these search practice combinations, we make incumbents aware of the routines used in distant knowledge search. These practices are dynamic capabilities that help them to remain successful in high-velocity markets. In identifying these search practices, we contribute to the literature on innovation routines and dynamic capability research.

ISO 21500 and success management: an integrated model for project management

Purpose

Projects are one of the main ways used to develop organisations and turn their strategic initiatives into a reality. To support project management, several entities (e.g. associations, institutes, etc.) provide standards, guides and project management methodologies. However, despite its wide coverage of project management knowledge areas, standards currently have no specific processes focused on planning and evaluating success. The absence of these processes can limit the vision of managers and their teams on what most contributes to the success of a project. Aiming at contributing to fill this gap, this paper proposes the integration of success management processes in the ISO 21500 standard.

Design/methodology/approach

To develop the integration model, a Design Science Research approach was adopted for the construction and evaluation of the resulting artefact.

Findings

The result is an integrated model and insights for its application in practice. The model aims to help managers and their teams to identify which success management activities need to carry out and how to integrate them with the other processes of the ISO 21500 standard.

Research limitations/implications

The integrated model was applied in only one project. Another limitation is the difficulty in comparing the results obtained due to the small number of works focused on success management (namely related to planning, measuring, controlling and reporting success in practice) and its integration with project management standards, guides and methodologies.

Originality/value

The integrated model, based on success management and the ISO 21500 standard, is an important and original contribution to understand and achieve success in projects. This promotes a new vision of balanced management, directing the management effort to the areas that effectively contribute to success in each project.

A systematic review of machine learning in logistics and supply chain management: current trends and future directions

Purpose

This paper presents a review of the existing state-of-the-art literature on machine learning (ML) in logistics and supply chain management (LSCM) by analyzing the current literature, contemporary concepts, data and gaps and suggesting potential topics for future research.

Design/methodology/approach

A systematic/structured literature review in the subject discipline and a bibliometric analysis were organized. Information regarding industry involvement, geographic location, research design and methods, data analysis techniques, university, affiliation, publishers, authors, year of publications is documented. A wide collection of eight databases from 1994 to 2019 were explored using the keywords “Machine Learning” and “Logistics“, “Transportation” and “Supply Chain” in the title and/or abstract. A total of 110 articles were found, and information on a chain of variables was gathered.

Findings

Over the last few decades, the application of emerging technologies has attracted significant interest all around the world. Analysis of the collected data shows that only nine literature reviews have been published in this area. Further, key findings show that 53.8 per cent of publications were closely clustered on transportation and manufacturing industries and 54.7 per cent were centred on mathematical models and simulations. Neural network is applied in 22 papers as their exclusive algorithms. Finally, the main focuses of the current literature are on prediction and optimization, where detection is contributed by only seven articles.

Research limitations/implications

This review is limited to examining only academic sources available from Scopus, Elsevier, Web of Science, Emerald, JSTOR, SAGE, Springer, Taylor and Francis and Wiley which contain the words “Machine Learning” and “Logistics“, “Transportation” and “Supply Chain” in the title and/or abstract.

Originality/value

This paper provides a systematic insight into research trends in ML in both logistics and the supply chain.

Application of fuzzy DEMATEL and fuzzy CODAS for analysis of workforce attributes pertaining to Industry 4.0: a case study

Purpose

The aim of this study is to analyze workforce attributes related to Industry 4.0 using fuzzy decision-making trial and evaluation laboratory (DEMATEL) and fuzzy combinative distance-based assessment (CODAS).

Design/methodology/approach

Technological trends stipulate various revolution in industries. Industry 4.0 is a vital challenge for modern manufacturing industries. Workforce adoption to such challenge is gaining vital importance. Therefore, such workforce-related attributes need to be identified for enhancing their performance in Industry 4.0 environment. In this context, this article highlights the analysis of 20 workforce attributes for Industry 4.0. Relevant criteria are prioritized using fuzzy DEMATEL. Workforce attributes are prioritized using fuzzy CODAS.

Findings

The key attributes are “Skills/training in decision-making (WA2)”, “Competences in complex system modelling and simulation (WA1)” and “Coding skills (WA20)”.

Research limitations/implications

In the present study, 20 workforce attributes are being considered. In future, additional workforce attributes could be considered.

Practical implications

The study has been conducted based on inputs from industry experts. Hence, the inferences have practical relevance.

Originality/value

The analysis of workforce attributes for Industry 4.0 using MCDM methods is the original contribution of the authors.

The after-sales strategy of an industrial equipment manufacturer: evaluation and control

Purpose

The purpose of this study is to evaluate the after-sales strategy of an industrial equipment manufacturer.

Design/methodology/approach

The research study’s object is the Brazilian operation of a company belonging to a multinational group that designs, manufactures and installs technology-based equipment. The research method is qualitative modeling with a quantitative analysis. A literature review and a focus group with managers organized the after-sales strategy of the company in four constructs measured by 24 indicators. The constructs are technical assistance (TA), reliability management (RM), customer relationships (CRs) and spare part logistics (SL). A total of seven managers evaluated the importance and performance of the indicators.

Findings

TA, RM and CRs are lagging constructs (the importance is greater than the performance), whereas SL is a leading construct (the opposite). The study proposed four strategic actions that change the type of emphasis that the company poses to service: from in-house to field maintenance service, from correction to prevention reliability improvement, from technical- to customer-focused relationships and from direct to integrated logistics service.

Research limitations/implications

The study limits to the case of a technology-based manufacturing company.

Practical implications

The strategic movement reallocates resources from leading indicators to lagging indicators in a sharp, clear movement of forces in the company.

Originality/value

The main contribution is a structured method to evaluate and control the strategic performance of an industrial equipment manufacturer in after-sales activities.

Machine Learning in Predictive Maintenance towards Sustainable Smart Manufacturing in Industry 4.0

Recently, with the emergence of Industry 4.0 (I4.0), smart systems, machine learning (ML) within artificial intelligence (AI), predictive maintenance (PdM) approaches have been extensively applied in industries for handling the health status of industrial equipment. Due to digital transformation towards I4.0, information techniques, computerized control, and communication networks, it is possible to collect massive amounts of operational and processes conditions data generated form several pieces of equipment and harvest data for making an automated fault detection and diagnosis with the aim to minimize downtime and increase utilization rate of the components and increase their remaining useful lives. PdM is inevitable for sustainable smart manufacturing in I4.0. Machine learning (ML) techniques have emerged as a promising tool in PdM applications for smart manufacturing in I4.0, thus it has increased attraction of authors during recent years. This paper aims to provide a comprehensive review of the recent advancements of ML techniques widely applied to PdM for smart manufacturing in I4.0 by classifying the research according to the ML algorithms, ML category, machinery, and equipment used, device used in data acquisition, classification of data, size and type, and highlight the key contributions of the researchers, and thus offers guidelines and foundation for further research.