ARULE™ – Adaptive Remaining Useful Life Estimator™

Ridgetop’s Adaptive Remaining Useful Life Estimator (ARULE) is a powerful reasoner to determine the remaining useful life (RUL) and state of health (SoH) of complex systems. Working from acquired sensor data, ARULE employs an advanced prediction method related to extended Kalman filtering (EKF) to produce new RUL and SoH estimates for each new sensor data point.

ARULE is versatile and can be used for determining electronic and mechanical fatigue damage. The reasoner calculates fault-to-failure progression (FFP) signatures, accurate RUL (time-to-failure) estimates, and SoH estimates, which provide an early warning indicator for system maintenance personnel to schedule service to the system prior to catastrophic failure.


Remaining useful life (RUL) representation of a system with ARULE API deployed in a Sentinel IT™ application

ARULE relies on diagnostic sensor data and a predefined model to produce an RUL estimate. It requires a sensor to “sense” data that are above a predefined “good-as-new” floor and below a “failed” ceiling. A new RUL estimate is produced based on changes to the model space; additionally, the new RUL estimate is used to produce a new SoH estimate.

ARULE is part of Ridgetop’s prognostics and health management (PHM) family of tools called Sentinel Suite™. In particular, ARULE is an integral part of Sentinel Power™, Sentinel Motion™ and Sentinel IT™, for advanced diagnostics and prognostics for power systems, rotational/vibrating systems, and networks, respectively.


  • Power systems
  • Battery management systems
  • Actuator control systems
  • Industrial automation systems

Click here to contact us, or visit the links below for more information.

Product Brief



Selected White Papers

Check any of the following titles you would like to read and submit your email at the bottom of this list. We will send you an email with your requested information. The email link will expire in one week.

Prognostic Health Management (PHM) of Electrical Systems Using Condition-based Data for Anomaly and Prognostic Reasoning
This paper presents an overview of signature-based PHM technology to detect anomalies and prognostic reasoning. A signature is extracted from condition-based data and is called a fault-failure progression (FFP) signature. Thereafter, a representative PHM system that extracts and processes dynamic degradation signatures for critical DC-regulated power is described beginning with a five-level hierarchical system model.
Prognostic Health Management (PHM) Solutions for Battery Packs Used in Critical Applications
This paper describes the innovative solution to improve the dependability and reliability of a NiCad battery system through monitoring and balancing the state of charge of each individual cell in a series-connected battery pack. This innovation significantly reduces maintenance and unnecessary battery pack replacement costs for critical military applications. The described application-specific integrated circuit (ASIC) solution detailed in this paper provides important prognostic, usage, and life-time feedback to the user and maintenance personnel.

Links to IEEE and AutoTestCon conference presentations on this subject can be found in our Resource Library


Related products