Predicting condition monitoring signals has become a critical task for health status assessment and monitoring of industrial systems. It is crucial to incorporate correlated historical data when making predictions for the target signal. As a flexible nonparametric approach, the multi-output Gaussian process (MOGP) model can be employed for this nonlinear regression problem. One effective way to construct MOGP is through convolving a latent function drawn from a Gaussian process. While leveraging the convolution process makes MOGP expressive, there are several challenges that remain to be addressed. First, the scalability of MOGP is always an important issue since the computational demands would increase drastically as the dimension of output variables grows. Besides, the negative transfer should be mitigated when the target variable and the source variable share little commonality. In this study, a pairwise structure is adopted by decomposing the full multivariate model into a group of bi-output models. Furthermore, a Bayesian model averaging approach is utilized to combine the prediction results of the bi-output models. A model selection scheme based on Bayes factor is employed to alleviate negative transfer and facilitate model scalability further by discarding the weakly correlated outputs. The key advantage of the proposed model lies in the improved prediction and uncertainty quantification performance compared with traditional MOGP models. The superiority of the proposed method is validated by numerical studies and a case study.Note to Practitioners—This study addresses the challenge of predicting condition monitoring signals in a high-dimensional setting. Existing nonparametric approaches suffer from high computation complexity or ineffective information integration from different signals. We propose a novel approach using a scalable pairwise MOGP model based on Bayesian model averaging. Our method decomposes the full model into bi-output submodels and averages them in a Bayesian way. We also employ a model selection scheme based on the Bayes factor to alleviate negative transfer by discarding weakly correlated outputs. Numerical experiments suggest that this approach can improve prediction accuracy and uncertainty quantification performance for the prediction of condition monitoring signals. Our approach offers a promising solution for condition monitoring signal prediction in automatic and industrial systems where condition monitoring data are readily available.

Equipment downtime is a significant challenge for many industries. In oil extraction, downtime costs can be as high as $250 000 per day. To prevent downtime, technicians manually interact with the equipment or monitor its health using sensory signals. Sensory data indirectly ascertain equipment health, while manual actions (inspections or repairs) provide a direct and precise insight but are time-consuming and costly. Thus, efficiently leveraging sensory data and outcomes of manual actions to accurately estimate the health of their equipment while finding the critical time points to schedule repairs and minimize the overall downtime is a crucial challenge faced by industries. In this article, we present a novel joint modeling approach called the action specific-input output hidden Markov model (AS-IOHMM) that integrates real-time sensor data and discrete health state information obtained by manual actions to aid prognosis and decision making of industrial equipment. In contrast to existing models that assume nondecreasing degradation without considering maintenance actions, AS-IOHMM estimates the impact of different maintenance actions on equipment health by learning action-specific transition probability matrices. We assess the effectiveness of AS-IOHMM through a numerical case study and validate its performance using mud-pump maintenance and sensory data from an oil rig, demonstrating enhanced prognosis ability and cost reduction of 7–15% over existing methods.

Accurate estimation of remaining useful life (RUL) of a unit is critical to fulfill reliability commitments. In the presence of hard failures (i.e., absence of a predefined failure threshold), accurate prognosis of RUL using condition monitoring (CM) signals becomes challenging. To tackle this problem, we present a prognostic framework by jointly modeling CM signals and failure event data. Development of the presented method depends on the idea that while the unit operates, it continually degrades through a series of hidden states and the CM signals are functionally related to this hidden failure process. The unit fails once the hidden failure process reaches a dead state. Through this modeling, requirement of a failure threshold on CM signals is eliminated. We provide a modified expectation-maximization procedure to estimate parameters, and through a comprehensive set of numerical as well as real-world experiments, we demonstrate superior prognosis performance against some benchmark methods.

Maintenance records of industrial equipment contain rich descriptive information in free-text format, such as involved parts, failure mechanisms, operating conditions, etc. Our objective is to leverage this unstructured textual information to identify groups of similar maintenance jobs. In this article, we use a natural language based approach and propose a novel custom word embedding model, which utilizes two sources of information, first, maintenance records collected from in-field operations and second, industrial taxonomy, to effectively identify clusters. The advantages of our model include combined use of semantic and taxonomic sources of information for clustering, one step/simultaneous training, which enables knowledge sharing between the two information sources and reduces hyperparameters, and no dependence on third-party data. We demonstrate the efficacy of our model for cluster identification using a real-world dataset. The results show that simultaneous incorporation of semantic and taxonomic information enables accurate extraction of contextual insights for improving maintenance decision-making and equipment reliability.

Prediction of events such as part replacement and failure events plays a critical role in reliability engineering. Event stream data are commonly observed in manufacturing and teleservice systems. Designing predictive models for individual units based on such event streams is challenging and an underexplored problem. In this work, we propose a nonparametric prognostic framework for individualized event prediction based on the inhomogeneous Poisson processes with a multivariate Gaussian convolution process (MGCP) prior on the intensity functions. The MGCP prior on the intensity functions of the inhomogeneous Poisson processes maps data from similar historical units to the current unit under study which facilitates sharing of information and allows for analysis of flexible event patterns. To facilitate inference, we derive a variational inference scheme for learning and estimation of parameters in the resulting MGCP modulated Poisson process model. Experimental results are shown on both synthetic data as well as real-world data for fleet-based event prediction.

Prediction of event such as failure event or critical warning event plays an important role in reliability engineering. In this paper, we present a semiparametric method to predict event occurrences for an individual unit in real time using recurrent event data. The intensity of event occurrence is modeled using the extended Cox proportional-hazard model and the distinction of units is achieved using an additional frailty parameter. The method presented features an online updating scheme, and therefore, can provide the real-time prediction of the occurrence of next event. We demonstrate the efficacy of frailty and the updating scheme through comprehensive numerical experiments and a case study based on real-world data.