Condition-based maintenance (CBM) of industrial machines depends on the continuous, real-time monitoring of the machine’s operational condition via smart sensors attached to different components on the machine. The problem of regularly spaced missing data, which can occur due to a variety of hardware or software issues, is one that is often overlooked in the literature surrounding CBM in industrial machines. Such missing data can cause issues in interpreting the true operational state of the machine, which can reduce the effectiveness of CBM processes. In this paper, we examine the capabilities of five data imputation techniques for handling this regular missing data and examine the impact these techniques have on machine learning (ML) classification algorithms for machine fault diagnosis. We examine the following techniques: simple mean imputation, mean imputation with outliers removed, best and worst-case imputation, and previous day imputation. Each of these methods is configured with the specific parameters that they will only consider data from the previous 24 hours, to ensure that the data is recent, and adequately represents the current status of the machine. The efficacy of each method at accurately reconstructing the missing data and the impact they have on ML classification is recorded in the results. The models are evaluated on a real-world dataset and are evaluated on a variety of common performance metrics.

Maintenance Quality Function Deployment (MQFD) is a model, which enhances the synergic power of Quality Function Deployment (QFD) and Total Productive Maintenance (TPM). One of the crucial and important steps during the implementation of MQFD is the determination of the importance or weightages of the critical factors (CF) and sub factors (SF). The CFs and SFs have to be compared precisely for the successful implementation of MQFD. The crisp pair-wise comparison in the conventional Analytical Hierarchy Process (AHP) may be insufficient to determine the degree of weightage of CFs and SFs where vagueness and uncetainties are associated. In this paper, a modification of AHP based MQFD by incorporating fuzzy operations is proposed, which can improve the accuracy of determination of the weightages. A case study showing the applicability of this method is illustrated in this paper.