Data Driven Prognostics for Rotating Machinery

Data Driven Prognostics for Rotating Machinery

Eric Bechhoefer (NRG Systems, USA)
DOI: 10.4018/978-1-4666-2095-7.ch006
OnDemand PDF Download:
No Current Special Offers


A prognostic is an estimate of the remaining useful life of a monitored part. While diagnostics alone can support condition based maintenance practices, prognostics facilitates changes to logistics which can greatly reduce cost or increase readiness and availability. A successful prognostic requires four processes: 1) feature extraction of measured data to estimate damage; 2) a threshold for the feature, which, when exceeded, indicates that it is appropriate to perform maintenance; 3) given a future load profile, a model that can estimate the remaining useful life of the component based on the current damage state; and 4) an estimate of the confidence in the prognostic. This chapter outlines a process for data-driven prognostics by: describing appropriate condition indicators (CIs) for gear fault detection; threshold setting for those CIs through fusion into a component health indicator (HI); using a state space process to estimate the remaining useful life given the current component health; and a state estimate to quantify the confidence in the estimate of the remaining useful life.
Chapter Preview


Condition based maintenance (CBM) systems have been shown to reduce costs by decreasing scheduled maintenance costs. However, CBM systems can be leveraged into far greater savings by developing a prognostics capability. The ability to estimate the remaining useful life (RUL) on a component can greatly improve its availability and reduce logistics cost. Prognostics are the maturation of the CBM system.

Consider the effect on wind farm operations if a prognostic capability were available. Major maintenance events require a heavy lift crane. The availability of a crane can be limited and cost of rental is large. Once the decision is made to replace a gearbox, opportunistic maintenance can be performed on other low RUL/marginal turbines. Alternatively, if the operator of a fleet of helicopter knows the RUL of his assets, he can deploy those aircraft that have the highest RUL and be assured that the aircraft will not need major maintenance while deployed.

The knowledge of a RUL allows the logistician to reduce inventory spares. It affects the man power needed for maintenance providers and facilitates more efficient operations. That said, there are currently few deployed prognostic health management (PHM) systems. While CBM is a maturing technology, PHM is relatively immature and difficult to implement.

The ability to estimate the RUL requires four pieces of information:

  • An estimate of the current equipment health,

  • A limit or threshold where it is appropriate to do maintenance,

  • An estimate of the future equipment load, and

  • A model to estimate the time from the current state to the limit/threshold based on projected load.

The current health of a system can be determined by CBM systems. Such systems measure features representing damage. For example, for a pump or generator, shaft order one acceleration is a measure of health. The limit for this vibration for some equipment can be found in standards such as ISO 10816 (2009). However, for gear, bearing, shaft, or equipment not covered by ISO standards, there are no formal or standardized limits. Future load for stationary equipment may be well known, but for helicopter or wind turbines, the load is a variable.

Damage models to predict future equipment health fall into two categories: physics of failure and data- driven. While physics of failure models are in their nature appealing, there is a cost associated with building the models, then validating and testing them. Further, the robustness of these models in application may not be satisfactory; how are material/manufacturing variance, unknown usage and maintenance accounted for in a real application? Data drive methods, while not capable of giving an absolute level of damage, can give a relative limit which may give acceptable performance.

Presented here is an end to end process for a data-driven prognostic for a vibration sensor. Descriptions of how CIs are generated for a gear run to failure test are given. The CIs are fused into a health indicator (HI) through a statistical process (to control the probability of false alarm). Given the current HI, the time until the HI reaches a predetermined value is calculated using Paris’ Law, resulting in an estimation of the remaining useful life. Once the RUL is calculated, a bound can then be calculated and a confidence in the RUL is given. Finally, this process will be demonstrated on a spiral bevel gear.

Complete Chapter List

Search this Book: