About this Research Topic
In the context of Industry 4.0, real-time big data streams from embedded intelligent sensors, as well as maintenance reports in handwritten or digital spreadsheets and equipment manuals, are commonly found in industrial facilities. Both real-time data streams from production lines and the significant amount of unstructured data are not sufficiently considered for maintenance purposes.
Moreover, imparting maintenance knowledge to new employees is a challenging activity that often hinders business continuity in industrial facilities. State-of-the-art Predictive and Prescriptive maintenance methodologies will enable the enhancement of current industrial maintenance practices utilizing all available information from heterogeneous data sources in the concept of Industry 4.0 and smart manufacturing.
Corrective maintenance strategies perform a run-to-failure strategy focused on repairing equipment or system components after a malfunction has occurred, constituting the safety of machinery shallow due to the enablement of unexpected failures. Preventive maintenance strategies perform periodic inspections and replacements in prespecified time sequences regardless of whether the system is malfunctioning, reducing overall productivity with continuous production interruptions, and increasing overall maintenance costs.
To leverage maintenance strategies in industrial environments, this focused research topic aims to shed light on a holistic approach that introduces predictive and prescriptive methodologies. A predictive maintenance (PdM) methodology answers the question ‘When will a malfunction occur’ by exploiting critical characteristics in big-data volumes. For example, predicting the health state of machinery at a given point and the remaining useful life (RUL) until malfunction.
As a next step, prescriptive maintenance methodologies introduce the concept of root cause analysis, answering the question ‘What are the actions that should be introduced for handling a particular (predicted) malfunction?’.
To this end, text mining, employing a variety of methodologies to process the text, with the most profound being Natural Language Processing (NLP), will enable the examination of large collections of documents to extract useful information and answer relevant research questions. In this light, unstructured data containing maintenance reports in handwritten or digital spreadsheets, equipment manuals, and technicians' feedback can be utilized along with NLP models to extract additional operational and maintenance information and maintenance recommendations.
The research topic focuses on holistic predictive and prescriptive maintenance frameworks leveraging structured and unstructured data to extract useful information and predictive outputs regarding machine conditions and maintenance procedures.
Relevant Research Areas:
• Industry 4.0 and Industry 5.0 AI applications and methodologies
• AI Business Process Reorganization
• Business Process Automation with Machine Learning/Deep learning algorithms
• Machine Learning and Flexible Business Process Management frameworks
• Big Data Analytics in Industries
• Real-Time Sensor based AI Strategies for maintenance
• Predictive Maintenance using historical and real-time data
• Condition Monitoring
• Prognostics and Health Management
• Remaining Useful Life
• Prescriptive Maintenance using technical manuals, operational reports, unstructured data
• Natural Language Processing
• Root Cause Analysis
Moreover, imparting maintenance knowledge to new employees is a challenging activity that often hinders business continuity in industrial facilities. State-of-the-art Predictive and Prescriptive maintenance methodologies will enable the enhancement of current industrial maintenance practices utilizing all available information from heterogeneous data sources in the concept of Industry 4.0 and smart manufacturing.
Corrective maintenance strategies perform a run-to-failure strategy focused on repairing equipment or system components after a malfunction has occurred, constituting the safety of machinery shallow due to the enablement of unexpected failures. Preventive maintenance strategies perform periodic inspections and replacements in prespecified time sequences regardless of whether the system is malfunctioning, reducing overall productivity with continuous production interruptions, and increasing overall maintenance costs.
To leverage maintenance strategies in industrial environments, this focused research topic aims to shed light on a holistic approach that introduces predictive and prescriptive methodologies. A predictive maintenance (PdM) methodology answers the question ‘When will a malfunction occur’ by exploiting critical characteristics in big-data volumes. For example, predicting the health state of machinery at a given point and the remaining useful life (RUL) until malfunction.
As a next step, prescriptive maintenance methodologies introduce the concept of root cause analysis, answering the question ‘What are the actions that should be introduced for handling a particular (predicted) malfunction?’.
To this end, text mining, employing a variety of methodologies to process the text, with the most profound being Natural Language Processing (NLP), will enable the examination of large collections of documents to extract useful information and answer relevant research questions. In this light, unstructured data containing maintenance reports in handwritten or digital spreadsheets, equipment manuals, and technicians' feedback can be utilized along with NLP models to extract additional operational and maintenance information and maintenance recommendations.
The research topic focuses on holistic predictive and prescriptive maintenance frameworks leveraging structured and unstructured data to extract useful information and predictive outputs regarding machine conditions and maintenance procedures.
Relevant Research Areas:
• Industry 4.0 and Industry 5.0 AI applications and methodologies
• AI Business Process Reorganization
• Business Process Automation with Machine Learning/Deep learning algorithms
• Machine Learning and Flexible Business Process Management frameworks
• Big Data Analytics in Industries
• Real-Time Sensor based AI Strategies for maintenance
• Predictive Maintenance using historical and real-time data
• Condition Monitoring
• Prognostics and Health Management
• Remaining Useful Life
• Prescriptive Maintenance using technical manuals, operational reports, unstructured data
• Natural Language Processing
• Root Cause Analysis
Keywords: Industry 4.0, Predictive Maintenance, Prescriptive Maintenance, Artificial Intelligence, Data Mining
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
