MBMichael P. Brundage

Michael P. Brundage

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Michael P. Brundage has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Online Maintenance Prioritization Via Monte Carlo Tree Search and Case-Based Reasoning

    by Michael Hoffman, Eunhye Song, Michael Brundage, Soundar Kumara

    When maintenance resources in a manufacturing system are limited, a challenge arises in determining how to allocate these resources among multiple competing maintenance jobs. This work formulates an online prioritization problem to tackle this challenge using a Markov decision process (MDP) to model the system behavior and Monte Carlo tree search (MCTS) to seek optimal maintenance actions in various states of the system. Further, case-based reasoning (CBR) is adopted to retain and reuse search experience gathered from MCTS to reduce the computational effort needed over time and to improve decision-making efficiency. The proposed method results in increased system throughput when compared to existing methods of maintenance prioritization while also reducing the computation time needed to identify optimal maintenance actions as more information is gathered. This is especially beneficial in manufacturing settings where maintenance decisions must be made quickly to minimize the negative performance impact of machine downtime.


  • Open Access

    Adapting natural language processing for technical text

    by Alden Dima, Sarah Lukens, Melinda Hodkiewicz, Thurston Sexton, Michael P. Brundage

    Despite recent dramatic successes, natural language processing (NLP) is not ready to address a variety of real‐world problems. Its reliance on large standard corpora, a training and evaluation paradigm that favors the learning of shallow heuristics, and large computational resource requirements, makes domain‐specific application of even the most successful NLP techniques difficult. This paper proposes technical language processing (TLP) which brings engineering principles and practices to NLP specifically for the purpose of extracting actionable information from language generated by experts in their technical tasks, systems, and processes. TLP envisages NLP as a socio‐technical system rather than as an algorithmic pipeline. We describe how the TLP approach to meaning and generalization differs from that of NLP, how data quantity and quality can be addressed in engineering technical domains, and the potential risks of not adapting NLP for technical use cases. Engineering problems can benefit immensely from the inclusion of knowledge from unstructured data, currently unavailable due to issues with out of the box NLP packages. We illustrate the TLP approach by focusing on maintenance in industrial organizations as a case‐study.


  • Discovering critical KPI factors from natural language in maintenance work orders

    by Madhusudanan Navinchandran, Michael E. Sharp, Michael P. Brundage, Thurston B. Sexton


  • A Visual Analytics Approach for the Diagnosis of Heterogeneous and Multidimensional Machine Maintenance Data

    by Xiaoyu Zhang, Takanori Fujiwara, Senthil Chandrasegaran, Michael P. Brundage, Thurston Sexton, Alden Dima, Kwan-Liu Ma

    Analysis of large, high-dimensional, and heterogeneous datasets is challenging as no one technique is suitable for visualizing and clustering such data in order to make sense of the underlying information. For instance, heterogeneous logs detailing machine repair and maintenance in an organization often need to be analyzed to diagnose errors and identify abnormal patterns, formalize root-cause analyses, and plan preventive maintenance. Such real-world datasets are also beset by issues such as inconsistent and/or missing entries. To conduct an effective diagnosis, it is important to extract and understand patterns from the data with support from analytic algorithms (e.g., finding that certain kinds of machine complaints occur more in the summer) while involving the human-in-the-loop. To address these challenges, we adopt existing techniques for dimensionality reduction (DR) and clustering of numerical, categorical, and text data dimensions, and introduce a visual analytics approach that uses multiple coordinated views to connect DR + clustering results across each kind of the data dimension stated. To help analysts label the clusters, each clustering view is supplemented with techniques and visualizations that contrast a cluster of interest with the rest of the dataset. Our approach assists analysts to make sense of machine maintenance logs and their errors. Then the gained insights help them carry out preventive maintenance. We illustrate and evaluate our approach through use cases and expert studies respectively, and discuss generalization of the approach to other heterogeneous data.


  • Top Cited Papers
    Open Access

    Technical language processing: Unlocking maintenance knowledge

    by Michael P. Brundage, Thurston Sexton, Melinda Hodkiewicz, Alden Dima, Sarah Lukens


  • Mitigating Disruption in Production Networks through Dynamic Scheduling Enabled by Integrated Enterprise Data

    by Timothy Sprock, Michael P. Brundage, William Z. Bernstein, Thurston Sexton, Michael Sharp

    The coronavirus disease pandemic has caused unprecedented disruptions for manufacturers and supply chains. To respond to these disruptions and potential future disturbances, manufacturers need to be resilient and adapt their production systems to fluctuating production demands. Sudden and large-scale changes in production needs may be best addressed quickly by leveraging multiple smaller existing work units with diverse capabilities and capacities. These facilities frequently produce enormous amounts of data of varying types from various sources and software systems. Manufacturers can more effectively respond to disruptions by deploying dynamic decision-making tools, such as scheduling, that leverage this heterogeneous data. There are many outstanding challenges to quickly and correctly integrating and curating heterogeneous data sources and extracting knowledge from the resulting data sets. This note lays out the challenge, identifies common use cases that can serve as test cases, and describes qualities of good solutions to this problem.

  • Prognostics and Health Management to Improve Resilient Manufacturing

    by Michael P. Brundage, Brian A. Weiss

    Manufacturers need to be resilient to effectively mitigate substantial disruptions to manufacturing operations so they may remain competitive. Disruptions resulting from the coronavirus disease (COVID-19) global pandemic have caused manufacturers to experience new challenges, including (1) working with reduced in-person operations, (2) retasking workers into new roles, and (3) reconfiguring their equipment and processes to yield completely new product lines. Improved monitoring, diagnostic, and prognostic technologies and methods (collectively known as prognostics and health management [PHM]) can help address these challenges and potential future disruptions.


  • Where Do We Start? Guidance for Technology Implementation in Maintenance Management for Manufacturing

    by Michael P. Brundage, Thurston Sexton, Melinda Hodkiewicz, Kc Morris, Jorge Arinez, Farhad Ameri, Jun Ni, Guoxian Xiao

    Recent efforts in smart manufacturing (SM) have proven quite effective at elucidating system behavior using sensing systems, communications, and computational platforms, along with statistical methods to collect and analyze the real-time performance data. However, how do you effectively select where and when to implement these technology solutions within manufacturing operations? Furthermore, how do you account for the human-driven activities in manufacturing when inserting new technologies? Due to a reliance on human problem-solving skills, today’s maintenance operations are largely manual processes without wide-spread automation. The current state-of-the-art maintenance management systems and out-of-the-box solutions do not directly provide necessary synergy between human and technology, and many paradigms ultimately keep the human and digital knowledge systems separate. Decision makers are using one or the other on a case-by-case basis, causing both human and machine to cannibalize each other’s function, leaving both disadvantaged despite ultimately having common goals. A new paradigm can be achieved through a hybridized system approach—where human intelligence is effectively augmented with sensing technology and decision support tools, including analytics, diagnostics, or prognostic tools. While these tools promise more efficient, cost-effective maintenance decisions and improved system productivity, their use is hindered when it is unclear what core organizational or cultural problems they are being implemented to solve. To explicitly frame our discussion about implementation of new technologies in maintenance management around these problems, we adopt well-established error mitigation frameworks from human factors experts—who have promoted human–system integration for decades—to maintenance in manufacturing. Our resulting tiered mitigation strategy guides where and how to insert SM technologies into a human-dominated maintenance management process.


  • Open Access

    An Overview of a Smart Manufacturing System Readiness Assessment

    by Kiwook Jung, Boonserm Kulvatunyou, Sangsu Choi, Michael P. Brundage

    Smart manufacturing, today, is the ability to continuously maintain and improve performance, with intensive use of information, in response to the changing environments. Technologies for creating smart manufacturing systems or factories are becoming increasingly abundant. Consequently, manufacturers, large and small, need to correctly select and prioritize these technologies correctly. In addition, other improvements may be necessary to receive the greatest benefit from the selected technology. This paper proposes a method for assessing a factory for its readiness to implement those technologies. The proposed readiness levels provide users with an indication of their current factory state when compared against a reference model. Knowing this state, users can develop a plan to increase their readiness. Through validation analysis, we show that the assessment has a positive correlation with the operational performance.