Refine
Document Type
- Journal article (1)
- Conference proceeding (1)
Language
- English (2) (remove)
Has full text
- yes (2)
Is part of the Bibliography
- yes (2)
Institute
Publisher
In recent years, machine learning algorithms have made a huge development in performance and applicability in industry and especially maintenance. Their application enables predictive maintenance and thus offers efficiency increases. However, a successful implementation of such solutions still requires high effort in data preparation to obtain the right information, interdisciplinarity in teams as well as a good communication to employees. Here, small and medium sized enterprises (SME) often lack in experience, competence and capacity. This paper presents a systematic and practice-oriented method for an implementation of machine learning solutions for predictive maintenance in SME, which has already been validated.
Process risks are omnipresent in the corporate world and repeatedly present organizations with the challenge of how to deal with these risks. Efforts in trying to analyze and prevent these risks are costly and require many resources, which do not always bring the desired added value. The goal of this work is to determine how a benefit-oriented resource allocation can be made for risk-oriented process management. For this purpose, the following research question is posed: "How can systematic prioritization decisions regarding risk-oriented process management be made?” To answer it, an evaluation procedure is developed which assesses processes based on their characteristics regarding potential risk disposition as well as entrepreneurial relevance. For this purpose, requirements for such a procedure are first collected and used to define selection criteria for it. After the detailed analysis of known selection and evaluation procedures, one of them is selected and used for further development. Next steps include the definition of relevant criteria for the evaluation of the processes by examining process characteristics regarding their suitability for process evaluation. The focus here lies on characteristics that provide indications of the risk disposition and business relevance of processes. The result of this approach is a scoring model with a criteria catalog consisting of 15 criteria according to which a process is evaluated. The evaluation result is presented both numerically and in a matrix. This enables the comparison of several processes and a derived prioritization of those for a more in-depth risk analysis. The application of this approach will ensure a benefit-oriented allocation of resources in the management of process risks and increased process reliability.