A Methodology for Prognostics Under the Conditions of Limited Failure Data Availability

Abstract

When failure data are limited, data-driven prognostics solutions underperform since the number of failure data samples is insufficient for training prognostics models effectively. In order to address this problem, we present a novel methodology for generating failure data which allows training datasets to be augmented so that the number of failure data samples is increased. In contrast to existing data generation techniques which duplicate or randomly generate data, the proposed methodology is capable of generating new and realistic failure data samples. The methodology utilises the conditional generative adversarial network and auxiliary information pertaining to failure modes to control and direct the failure data generation process. The theoretical foundation of the methodology in a non-parametric setting is presented and we show that it holds in practice using empirical results. The methodology is evaluated in a real-world case study involving the prediction of air purge valve failures in heavy-trucks. Two prognostics models are developed using the gradient boosting machine and random forest classifiers. When these models are trained on the augmented training dataset, they outperformed the best solution previously proposed in the literature for the case study by a large margin. More specifically, costs due to breakdowns and false alarms are reduced by 44%. INDEX TERMS Equipment prognostics, expert knowledge, generative modeling, limited failure data, physics of failure.

Learning With Imbalanced Data in Smart Manufacturing: A Comparative Analysis

“…In Case I experiments, XGBoost achieves the best results with a total cost of A C12,230 as highlighted in Table. 2. Our results are aligned with the work in [49] where a boosting-based method achieves less total cost than RF.…”

“…We evaluate these techniques for creating high-quality minority data samples and measure their effectiveness in conjunction with cost-sensitive learning algorithms on improving the classification performance when presented with an imbalanced dataset. There are very few works that use some of these presented techniques as data augmentation such as [26], [49] while learning from an imbalanced dataset, especially in industrial settings. To the best of our knowledge, this is the first comprehensive evaluation of different data augmentation and cost-sensitive methods for predictive analytics in manufacturing applications.…”

“…On the other hand, SMOTE improves the predictive analytics (using random forest) and offers higher gain comparing with the original data (with no augmentation) with a cost reduction up to 3% in Case II with existing similar studies. Most of the studies including, [49], [86] do not report the parameter settings of each chosen classifier which makes it a challenging task to reproduce their experiments. For instance, authors in [49] achieve a total cost of A C11,090 using RF as a binary classifier on the original data; however, they do not report parameter settings, imputation technique, whether a decision threshold is applied and its value or other evaluation metrics including precision and recall.…”

Secure and communications‐efficient collaborative prognosis

“…The performance of data‐driven prognosis relies heavily on the historical failure data used for training the prediction models [24]. For prognosis, just like other ML applications, the prediction models tend to learn faster and be more accurate if its training data is statistically homogeneous, i.e.…”

“…Recently popularised distributed computing architectures for industrial systems enable every asset in the fleet to have its own corresponding prediction model [8, 9, 11, 16]. However, the individualised models would require assets to fail a certain number of times so that necessary training data is available [17, 24]. The collaborative prognosis technique aims at reducing these asset failures by enabling assets to identify other similar assets in the fleet and learn from their failures as well [7].…”