Digital Twin (DT) is an emerging technology that has recently been cited as an underpinning element of the digital transformation. DTs are commonly defined as digital replicas of components, systems, products, and services that receive data from the field to support intelligent decision-making. Although several frameworks for DT application in manufacturing have been proposed, there is no systematic methodology in the literature that supports the development of scalable, reusable, interoperable, interchangeable, and extensible DT solutions, while taking into account specific manufacturing environment needs and conditions. This paper introduces a DT solution development methodology as a generic procedure for analyzing and developing DTs for manufacturing systems. The methodology is based on the well-known System Development Life Cycle (SDLC) process and takes into consideration: (1) the specificity of DT characteristics and requirements, (2) an understanding of the manufacturing context in which the DTs will operate, and (3) the object-oriented aspects required to achieve DT capabilities of scalability, reusability, interoperability, interchangeability, and extensibility. A case study illustrates the advantages of the proposed methodology in supporting manufacturing DT solutions.

Rolling element bearings are a common component in rotating equipment, a class of machines that is essential in a wide range of industries. Detecting and predicting bearing failures is then vital for reducing maintenance and production costs due to unplanned downtime. In previous literature, significant efforts have been devoted to building data-driven health models from historical bearing data. However, a common limitation is that these methods are typically tailored to specific failure instances and have limited ability to model bearing failures between repairs in the same system. In this paper, we propose a multi-state health model to predict bearing failures before they occur. The model employs a regression-based method to detect health state transition points and applies an exponential random coefficient model with a Bayesian updating process to estimate time-to-failure distributions. A model training framework is also introduced to make our proposed model applicable to more bearing instances in the same system setting. The proposed method has been tested on a publicly available bearing prognostics dataset. Case study results show that the proposed method provides accurate failure predictions across several system failures, and that the training approach can significantly reduce the time necessary to generate an effective, generalized model.

The development of prognostics and health management solutions in the manufacturing industry has lagged behind academic advances due to a number of practical challenges. This work proposes a framework for the initial development of industrial PHM solutions that is based on the system development life cycle commonly used for software-based applications. Methodologies for completing the planning and design stages, which are critical for industrial solutions, are presented. Two challenges that are inherent to health modeling in manufacturing environments, data quality and modeling systems that experience trend-based degradation, are then identified and methods to overcome them are proposed. Additionally included is a case study documenting the development of an industrial PHM solution for a hyper compressor at a manufacturing facility operated by The Dow Chemical Company. This case study demonstrates the value of the proposed development process and provides guidelines for utilizing it in other applications.

Rotating equipment is widespread in the process industry, where pumps, compressors, and turbines are used to drive continuous manufacturing lines. This class of machinery is meant to run without interruption, but invariably experiences degradation that can lead to equipment failure. Any break in a continuous manufacturing line can halt production, so there is a pressing need to diagnose rotating equipment health before failure occurs. Existing health modeling and diagnosis strategies require supplemental tests to collect model training data, and ignore time-series behavior in machine signals that can be useful for diagnosing equipment health. This work presents a general modeling structure to give context to historical data, which can act as a substitute for supplemental test data, and describes a methodology for assessing repair quality based on trends in signal features. A case study that uses the proposed methodology to assess the quality of repair procedures is provided.